diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..efbb782a848e655e29dc7759f7fe715d2bfd793a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5483b93231491dcdadb5963ea78a69366e0ab6aa03183648b5e5e587b20398e +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1a4366e9f6f1e6ab46a93b92e0f433a59be3437 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ec37f8a196a72a97ca9967df7a30c712b3483c36593a578a3c2f921f48fb93 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbd80d32bd762edb0898a2a1b6b69934b811c18e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0ebda40a3924e216542bcb94795169a0eced7e9d1672dd24ea3dc5bd826259 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f59d5b94988809fb36399cd1254b8d365533c7b --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a5a353aa956358db56e4e8110f1cf929e76f1178ff0441174be62305b48b0e +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9a9caccc334b5b1f08f015f84db44c19747c3858 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/trainer_state.json @@ -0,0 +1,261 @@ +{ + "best_metric": 0.64535284, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100", + "epoch": 0.012837382457716871, + "eval_steps": 50, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.887966208382157e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f20b51d3a2b2e585328f641d8ea461501f7e797 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b047ba6ad4ac3fc6b0980080d4d3c0cf69641417e5b7ac54d06a2e96ba9eea +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b5b3ba63254b194c4b5ca42e8381ffb7eb01e83c --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d13564f1b33e65744b4ae00df396b38868578d8aedd49db3aac4d78b0697067 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4278f69528f1f004afd0376a976ea3f19817824 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b78ad66f92e3ca930b0c6b16fe26286bf9120471a4b51538be0d69091971a43 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e0b0bd041703b1f8e60c8171d56f6f12a42ca08 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4077036d99500a708f700f75da24d51b5300e184ad35fda49dc5a4df5596cca2 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b985ba87844562bfbe61d3d6cb268ec2b5456b7a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/trainer_state.json @@ -0,0 +1,2223 @@ +{ + "best_metric": 0.60646284, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850", + "epoch": 0.12837382457716873, + "eval_steps": 50, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + }, + { + "acc": 0.82061501, + "epoch": 0.09692223755576237, + "grad_norm": 0.2477208524942398, + "learning_rate": 1.553232954407171e-05, + "loss": 0.61750922, + "memory(GiB)": 12.9, + "step": 755, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81846237, + "epoch": 0.09756410667864822, + "grad_norm": 0.22278401255607605, + "learning_rate": 1.4938160786375572e-05, + "loss": 0.61280818, + "memory(GiB)": 12.9, + "step": 760, + "train_speed(iter/s)": 0.079391 + }, + { + "acc": 0.81434851, + "epoch": 0.09820597580153406, + "grad_norm": 0.22640761733055115, + "learning_rate": 1.435357758543015e-05, + "loss": 0.63006077, + "memory(GiB)": 12.9, + "step": 765, + "train_speed(iter/s)": 0.079552 + }, + { + "acc": 0.81086941, + "epoch": 0.0988478449244199, + "grad_norm": 0.20250476896762848, + "learning_rate": 1.3778739760445552e-05, + "loss": 0.63865561, + "memory(GiB)": 12.9, + "step": 770, + "train_speed(iter/s)": 0.079713 + }, + { + "acc": 0.81333466, + "epoch": 0.09948971404730575, + "grad_norm": 0.21983562409877777, + "learning_rate": 1.3213804466343421e-05, + "loss": 0.63764729, + "memory(GiB)": 12.9, + "step": 775, + "train_speed(iter/s)": 0.079857 + }, + { + "acc": 0.81033506, + "epoch": 0.1001315831701916, + "grad_norm": 0.21427662670612335, + "learning_rate": 1.2658926150792322e-05, + "loss": 0.62097745, + "memory(GiB)": 12.9, + "step": 780, + "train_speed(iter/s)": 0.080004 + }, + { + "acc": 0.82130699, + "epoch": 0.10077345229307744, + "grad_norm": 0.20593635737895966, + "learning_rate": 1.2114256511983274e-05, + "loss": 0.60655851, + "memory(GiB)": 12.9, + "step": 785, + "train_speed(iter/s)": 0.080173 + }, + { + "acc": 0.82261295, + "epoch": 0.10141532141596328, + "grad_norm": 0.2052464336156845, + "learning_rate": 1.157994445715706e-05, + "loss": 0.61125717, + "memory(GiB)": 12.9, + "step": 790, + "train_speed(iter/s)": 0.080342 + }, + { + "acc": 0.82531328, + "epoch": 0.10205719053884912, + "grad_norm": 0.17600791156291962, + "learning_rate": 1.1056136061894384e-05, + "loss": 0.59510598, + "memory(GiB)": 12.9, + "step": 795, + "train_speed(iter/s)": 0.08049 + }, + { + "acc": 0.81779881, + "epoch": 0.10269905966173497, + "grad_norm": 0.2141779363155365, + "learning_rate": 1.0542974530180327e-05, + "loss": 0.63478656, + "memory(GiB)": 12.9, + "step": 800, + "train_speed(iter/s)": 0.080624 + }, + { + "epoch": 0.10269905966173497, + "eval_acc": 0.8207697400203976, + "eval_loss": 0.6077002882957458, + "eval_runtime": 194.8773, + "eval_samples_per_second": 6.455, + "eval_steps_per_second": 6.455, + "step": 800 + }, + { + "acc": 0.80902939, + "epoch": 0.10334092878462081, + "grad_norm": 0.2090810388326645, + "learning_rate": 1.0040600155253765e-05, + "loss": 0.66100531, + "memory(GiB)": 12.9, + "step": 805, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81437035, + "epoch": 0.10398279790750665, + "grad_norm": 0.22697587311267853, + "learning_rate": 9.549150281252633e-06, + "loss": 0.63930345, + "memory(GiB)": 12.9, + "step": 810, + "train_speed(iter/s)": 0.079387 + }, + { + "acc": 0.81263914, + "epoch": 0.1046246670303925, + "grad_norm": 0.21495579183101654, + "learning_rate": 9.068759265665384e-06, + "loss": 0.63128233, + "memory(GiB)": 12.9, + "step": 815, + "train_speed(iter/s)": 0.079538 + }, + { + "acc": 0.80606184, + "epoch": 0.10526653615327834, + "grad_norm": 0.24026648700237274, + "learning_rate": 8.599558442598998e-06, + "loss": 0.66762576, + "memory(GiB)": 12.9, + "step": 820, + "train_speed(iter/s)": 0.07969 + }, + { + "acc": 0.83144102, + "epoch": 0.10590840527616419, + "grad_norm": 0.2179374396800995, + "learning_rate": 8.141676086873572e-06, + "loss": 0.56980219, + "memory(GiB)": 12.9, + "step": 825, + "train_speed(iter/s)": 0.079849 + }, + { + "acc": 0.81910725, + "epoch": 0.10655027439905003, + "grad_norm": 0.19496454298496246, + "learning_rate": 7.695237378953223e-06, + "loss": 0.61694736, + "memory(GiB)": 12.9, + "step": 830, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.81330662, + "epoch": 0.10719214352193587, + "grad_norm": 0.23187701404094696, + "learning_rate": 7.260364370723044e-06, + "loss": 0.64870877, + "memory(GiB)": 12.9, + "step": 835, + "train_speed(iter/s)": 0.080126 + }, + { + "acc": 0.81870842, + "epoch": 0.10783401264482172, + "grad_norm": 0.20400239527225494, + "learning_rate": 6.837175952121306e-06, + "loss": 0.61115222, + "memory(GiB)": 12.9, + "step": 840, + "train_speed(iter/s)": 0.080258 + }, + { + "acc": 0.82128296, + "epoch": 0.10847588176770756, + "grad_norm": 0.24608130753040314, + "learning_rate": 6.425787818636131e-06, + "loss": 0.61838484, + "memory(GiB)": 12.9, + "step": 845, + "train_speed(iter/s)": 0.080422 + }, + { + "acc": 0.8118104, + "epoch": 0.1091177508905934, + "grad_norm": 0.21192343533039093, + "learning_rate": 6.026312439675552e-06, + "loss": 0.67037339, + "memory(GiB)": 12.9, + "step": 850, + "train_speed(iter/s)": 0.080553 + }, + { + "epoch": 0.1091177508905934, + "eval_acc": 0.8208858520874116, + "eval_loss": 0.606462836265564, + "eval_runtime": 194.9575, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 850 + }, + { + "acc": 0.81058187, + "epoch": 0.10975962001347925, + "grad_norm": 0.2256067544221878, + "learning_rate": 5.6388590278194096e-06, + "loss": 0.63853312, + "memory(GiB)": 12.9, + "step": 855, + "train_speed(iter/s)": 0.079236 + }, + { + "acc": 0.8174571, + "epoch": 0.11040148913636509, + "grad_norm": 0.21500875055789948, + "learning_rate": 5.263533508961827e-06, + "loss": 0.6172534, + "memory(GiB)": 12.9, + "step": 860, + "train_speed(iter/s)": 0.079369 + }, + { + "acc": 0.8093504, + "epoch": 0.11104335825925093, + "grad_norm": 0.23700734972953796, + "learning_rate": 4.900438493352055e-06, + "loss": 0.65724411, + "memory(GiB)": 12.9, + "step": 865, + "train_speed(iter/s)": 0.07952 + }, + { + "acc": 0.81735506, + "epoch": 0.11168522738213678, + "grad_norm": 0.21098878979682922, + "learning_rate": 4.549673247541875e-06, + "loss": 0.61837373, + "memory(GiB)": 12.9, + "step": 870, + "train_speed(iter/s)": 0.079659 + }, + { + "acc": 0.81503067, + "epoch": 0.11232709650502262, + "grad_norm": 0.20609669387340546, + "learning_rate": 4.2113336672471245e-06, + "loss": 0.61365747, + "memory(GiB)": 12.9, + "step": 875, + "train_speed(iter/s)": 0.079794 + }, + { + "acc": 0.80629053, + "epoch": 0.11296896562790847, + "grad_norm": 0.2180800437927246, + "learning_rate": 3.885512251130763e-06, + "loss": 0.66433964, + "memory(GiB)": 12.9, + "step": 880, + "train_speed(iter/s)": 0.079933 + }, + { + "acc": 0.82552185, + "epoch": 0.11361083475079431, + "grad_norm": 0.2074093371629715, + "learning_rate": 3.5722980755146517e-06, + "loss": 0.5967988, + "memory(GiB)": 12.9, + "step": 885, + "train_speed(iter/s)": 0.080078 + }, + { + "acc": 0.81032143, + "epoch": 0.11425270387368015, + "grad_norm": 0.232750803232193, + "learning_rate": 3.271776770026963e-06, + "loss": 0.66238441, + "memory(GiB)": 12.9, + "step": 890, + "train_speed(iter/s)": 0.080218 + }, + { + "acc": 0.8156251, + "epoch": 0.114894572996566, + "grad_norm": 0.24590888619422913, + "learning_rate": 2.9840304941919415e-06, + "loss": 0.6185041, + "memory(GiB)": 12.9, + "step": 895, + "train_speed(iter/s)": 0.080356 + }, + { + "acc": 0.81570625, + "epoch": 0.11553644211945184, + "grad_norm": 0.2058228850364685, + "learning_rate": 2.7091379149682685e-06, + "loss": 0.61333613, + "memory(GiB)": 12.9, + "step": 900, + "train_speed(iter/s)": 0.080474 + }, + { + "epoch": 0.11553644211945184, + "eval_acc": 0.8202886005724797, + "eval_loss": 0.6085067391395569, + "eval_runtime": 194.5686, + "eval_samples_per_second": 6.466, + "eval_steps_per_second": 6.466, + "step": 900 + }, + { + "acc": 0.81097269, + "epoch": 0.11617831124233768, + "grad_norm": 0.23131993412971497, + "learning_rate": 2.4471741852423237e-06, + "loss": 0.64109416, + "memory(GiB)": 12.9, + "step": 905, + "train_speed(iter/s)": 0.079218 + }, + { + "acc": 0.82361622, + "epoch": 0.11682018036522353, + "grad_norm": 0.18522906303405762, + "learning_rate": 2.1982109232821178e-06, + "loss": 0.59271107, + "memory(GiB)": 12.9, + "step": 910, + "train_speed(iter/s)": 0.079368 + }, + { + "acc": 0.81258793, + "epoch": 0.11746204948810937, + "grad_norm": 0.21756961941719055, + "learning_rate": 1.962316193157593e-06, + "loss": 0.65264983, + "memory(GiB)": 12.9, + "step": 915, + "train_speed(iter/s)": 0.07951 + }, + { + "acc": 0.82611704, + "epoch": 0.11810391861099521, + "grad_norm": 0.20278231799602509, + "learning_rate": 1.7395544861325718e-06, + "loss": 0.59875569, + "memory(GiB)": 12.9, + "step": 920, + "train_speed(iter/s)": 0.079655 + }, + { + "acc": 0.82435198, + "epoch": 0.11874578773388106, + "grad_norm": 0.21583449840545654, + "learning_rate": 1.5299867030334814e-06, + "loss": 0.62275109, + "memory(GiB)": 12.9, + "step": 925, + "train_speed(iter/s)": 0.079795 + }, + { + "acc": 0.81717892, + "epoch": 0.1193876568567669, + "grad_norm": 0.22039002180099487, + "learning_rate": 1.333670137599713e-06, + "loss": 0.61020494, + "memory(GiB)": 12.9, + "step": 930, + "train_speed(iter/s)": 0.079939 + }, + { + "acc": 0.80936031, + "epoch": 0.12002952597965275, + "grad_norm": 0.21585673093795776, + "learning_rate": 1.1506584608200367e-06, + "loss": 0.63481708, + "memory(GiB)": 12.9, + "step": 935, + "train_speed(iter/s)": 0.080073 + }, + { + "acc": 0.81828098, + "epoch": 0.12067139510253859, + "grad_norm": 0.22403886914253235, + "learning_rate": 9.810017062595322e-07, + "loss": 0.62871428, + "memory(GiB)": 12.9, + "step": 940, + "train_speed(iter/s)": 0.080211 + }, + { + "acc": 0.82708139, + "epoch": 0.12131326422542443, + "grad_norm": 0.22789925336837769, + "learning_rate": 8.247462563808817e-07, + "loss": 0.59829245, + "memory(GiB)": 12.9, + "step": 945, + "train_speed(iter/s)": 0.080336 + }, + { + "acc": 0.81116629, + "epoch": 0.12195513334831028, + "grad_norm": 0.22641904652118683, + "learning_rate": 6.819348298638839e-07, + "loss": 0.629322, + "memory(GiB)": 12.9, + "step": 950, + "train_speed(iter/s)": 0.080481 + }, + { + "epoch": 0.12195513334831028, + "eval_acc": 0.8201861908583086, + "eval_loss": 0.6082066297531128, + "eval_runtime": 194.2718, + "eval_samples_per_second": 6.475, + "eval_steps_per_second": 6.475, + "step": 950 + }, + { + "acc": 0.81035719, + "epoch": 0.12259700247119612, + "grad_norm": 0.21176832914352417, + "learning_rate": 5.526064699265753e-07, + "loss": 0.65304608, + "memory(GiB)": 12.9, + "step": 955, + "train_speed(iter/s)": 0.079321 + }, + { + "acc": 0.80980167, + "epoch": 0.12323887159408196, + "grad_norm": 0.23720386624336243, + "learning_rate": 4.367965336512403e-07, + "loss": 0.65838566, + "memory(GiB)": 12.9, + "step": 960, + "train_speed(iter/s)": 0.079457 + }, + { + "acc": 0.81608143, + "epoch": 0.12388074071696781, + "grad_norm": 0.19302093982696533, + "learning_rate": 3.3453668231809286e-07, + "loss": 0.64156389, + "memory(GiB)": 12.9, + "step": 965, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81429224, + "epoch": 0.12452260983985365, + "grad_norm": 0.20239369571208954, + "learning_rate": 2.458548727494292e-07, + "loss": 0.63968878, + "memory(GiB)": 12.9, + "step": 970, + "train_speed(iter/s)": 0.079694 + }, + { + "acc": 0.80978498, + "epoch": 0.1251644789627395, + "grad_norm": 0.20085211098194122, + "learning_rate": 1.7077534966650766e-07, + "loss": 0.65152073, + "memory(GiB)": 12.9, + "step": 975, + "train_speed(iter/s)": 0.079826 + }, + { + "acc": 0.82283268, + "epoch": 0.12580634808562535, + "grad_norm": 0.23421017825603485, + "learning_rate": 1.0931863906127327e-07, + "loss": 0.59241028, + "memory(GiB)": 12.9, + "step": 980, + "train_speed(iter/s)": 0.079952 + }, + { + "acc": 0.81115065, + "epoch": 0.12644821720851118, + "grad_norm": 0.19245800375938416, + "learning_rate": 6.150154258476315e-08, + "loss": 0.64031863, + "memory(GiB)": 12.9, + "step": 985, + "train_speed(iter/s)": 0.080066 + }, + { + "acc": 0.81750393, + "epoch": 0.12709008633139704, + "grad_norm": 0.21410977840423584, + "learning_rate": 2.7337132953697554e-08, + "loss": 0.63289447, + "memory(GiB)": 12.9, + "step": 990, + "train_speed(iter/s)": 0.080194 + }, + { + "acc": 0.80839672, + "epoch": 0.12773195545428287, + "grad_norm": 0.24657242000102997, + "learning_rate": 6.834750376549792e-09, + "loss": 0.67404447, + "memory(GiB)": 12.9, + "step": 995, + "train_speed(iter/s)": 0.080318 + }, + { + "acc": 0.82744455, + "epoch": 0.12837382457716873, + "grad_norm": 0.20574873685836792, + "learning_rate": 0.0, + "loss": 0.58532543, + "memory(GiB)": 12.9, + "step": 1000, + "train_speed(iter/s)": 0.080433 + }, + { + "epoch": 0.12837382457716873, + "eval_acc": 0.8205681371523807, + "eval_loss": 0.6072012186050415, + "eval_runtime": 194.0316, + "eval_samples_per_second": 6.483, + "eval_steps_per_second": 6.483, + "step": 1000 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.855587826431877e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db9b4eb1086cf603a4f6f01499f0f910a67db69d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed32b9bb4a7994322f82959b3c889e3d5fcf6df641a4cf87d551f2291096bd65 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a14db9083f3afbe847834901efe137e39a29680c --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5b36d15d3b4cb5d6ac6c45668dd7a4e234996cf5b5bcfa427d6dcfc9581fe0 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1807048a19c34894a9130b7d8313acb5bceb08c4 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f993860293e99c2d3e78d865fcaaf179473939fc9348266d1308c749068004b +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..66024f88932b65cef2e9248752793eafc78ba59a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933907a28d624df5625600b77cfaf69aac83ec99919cf400ec983afa16156fea +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2e7e3a588f4af1779d035655652236938a8c25e3 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/trainer_state.json @@ -0,0 +1,370 @@ +{ + "best_metric": 0.63503182, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150", + "epoch": 0.019256073686575306, + "eval_steps": 50, + "global_step": 150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5.844637904195174e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b5e6f31dffeaa8980e82f5d035dd99dc12b6012 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d844e37c92e6154fc82860952fa7e91a623164af249cd9e431e3f7e2028e23d4 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..02f55af3cbfa44e850192f3bd581a9b1c5615aa4 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1711fa8982f5b6fa02df8213057cc9e18d11d7fa2d89a4fc9aa20d86d7790023 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..663199e9378a49449386079356aebfb9bb204054 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab89609811018c79003d804395390bda2de480fa77651cf4c7d56ad6035a26f0 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8abf6ebe2a73b5166e6eccf1d26d564a3fcba563 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990a1cf86aba2c4ef745bb4fd8a9b7f25fcd3e01d84b539560e7d0b4ac6b96da +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a52c2913bfd48496f02f407df400ae7708c09268 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/trainer_state.json @@ -0,0 +1,479 @@ +{ + "best_metric": 0.6316511, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200", + "epoch": 0.025674764915433742, + "eval_steps": 50, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7.75762245139415e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86f266d5f7ccf52573d6ab37258c70e4260574de --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7f19432210f9ffa2aef19c920f169be7b13c0fd0b99349935ae8dddc1b6e78 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..07901ddacb761f9c19ade09ca275393e01e85f99 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb1afa9628cc3db04283e749722cc167a087b7087bfacae579da1452ec93c65 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d84b56bc9d1eae444f3b47664ea37a8e4196b77 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa16d681f761278546ff55b3081d24bfa9e026db21f119a076d74ccebf46a6c5 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3df6bd074e953c77674c685bf921ebe2c347ba25 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dbce3139ce7219e7bbacc53013247ab594368fbf3c12b28bb9ed93a44fe24d6 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c3a9bab9785b6b64271c407e41500ad73b5fb0cb --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/trainer_state.json @@ -0,0 +1,588 @@ +{ + "best_metric": 0.62229896, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250", + "epoch": 0.03209345614429218, + "eval_steps": 50, + "global_step": 250, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.727748902228378e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-250/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10b2d3b8a2a9deef67d4e0546cd2e5d7338eb8cd --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05a6e67822d61f510471c538629dbe0660f54a83f43f2d232dc854444af4708 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecbc99cd3cb3915b4b60595f725318e3dfba1888 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27067e20662471a4b29fe83e57906f038e8acd04b85174e9da6a6814abd2bf7d +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..056585f90caf4440e29ce9e49232e24749baf010 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb44b89e6cc422656bbc727cbe34436c7cb37da618121dd839b0a638c1820c7 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f28fa6a9027b01cdca4bb496f9932ec1668e397 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd57b8ebd3e3eedd390c8aa02617b1f6e4d087d0815fce353e4e4de004cb0dc +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ee09dc785d2c0cd25be978168b31034e0eb18804 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/trainer_state.json @@ -0,0 +1,697 @@ +{ + "best_metric": 0.62134022, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300", + "epoch": 0.03851214737315061, + "eval_steps": 50, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.1624411367471514e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3c2f18fd69560818fdcb2937c979f3e657980983 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea67fbcf26939072417128edf665c902ffef6b09f5b7293e49eac571cf07963d +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1dee5c73874b35b32e3ca44b3c2c0fc425f22370 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9bb94fcf8974b914eeffaef02cc3c8db4d70b73a5ef626e082a05117891b8f +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..d040ab0d22fd620b424896f6f109bc8492880ede --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c186065e9a9259c77645216a9867ae099be0f2812f9ae1de403a16f821760c +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad37eef7761d7fb68e4649995a40aa70832707b5 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4268ec3d9131daf6cd0fde517642fa90c2dbb174a02a2d3b73a24e927eaa0232 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1ec60c7c006851ed2887721790dddd08f8469550 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/trainer_state.json @@ -0,0 +1,806 @@ +{ + "best_metric": 0.61841357, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350", + "epoch": 0.04493083860200905, + "eval_steps": 50, + "global_step": 350, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.3499328921738854e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-350/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba4a562676adc8d095662014500ddb786c9fb579 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1751bdb3f3988f27e2666797afd96bfb0560814aaab9513dbc6ddf7328633c +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..801015a8c65702f068a01a1e38d2eaee8b9f9e57 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a46515bbe629d0e84b1f48da936c2e05af09f04fca9c4859ae411f435258ad9 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2f9c3b666e2768a5158f1a436c99fba0ec05495 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b456ab311f68d6c88eb0c6117e7888a572c68e4e43c322753383eb25db085d +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..03ea9955545dc38ef8502ef2870a9ddb059de719 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b8454d90de1e79421e9c6e53b3034ecaac6144a1a140dc9bb2c2d8f1c91910 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..70f22d9a24c8fe72e466e038937dd886bfeca709 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/trainer_state.json @@ -0,0 +1,915 @@ +{ + "best_metric": 0.61470592, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400", + "epoch": 0.051349529830867484, + "eval_steps": 50, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.543819736756183e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b1437f1c1e830a4a8336807cc15669a95638b6f --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683d5d677794c128762e6ebf8c8fd8d1865effc343a803c4c11ae9cf00af27dd +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1bfc6f7694ae8142df7612a64df76cf13b5d9e0c --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0f7e68dfd6ea48eb1f9426be5b7333db804ca26e3d640e4392bdfeeceb0220 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ede3553f76a9745cfc4d26c53d2bbfed4a81d62a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c490c75e373667bb57c5c1bde450a062ea3b5693fbf37003eb239277a1087c +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e42552df86748ff0718e17d53ffe1096d6fd684 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf86405e8f40723867b0ddeb781f443f768e2ecab1ab799c6cc531a4939f1f55 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f49272c84278d5928a890278d79e7f92c3454c79 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/trainer_state.json @@ -0,0 +1,1024 @@ +{ + "best_metric": 0.61346853, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450", + "epoch": 0.05776822105972592, + "eval_steps": 50, + "global_step": 450, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.7319285643261133e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cbe4a483c38faa3d6cea325721a8fe8ae1b3b63 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7288117b84ffb15b214f7fb1f3231b2e960b7178731debf37835bd695942b3 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5bbd2ea6dec487d316915c019324b7f6bbf993a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b3481acd8d59f9c66b22cbcb5be8d3c77f33a7b2da5666d634102e38ad0ed8 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..362f3da309fb9fcd6accea1689fb92c5710edee8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e58fc6888abace05ac903753e5faae28eeb8042aa74535b8bbe0340f387a5f0 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9229cad211683cf1afcfc0ccccf315e35858703 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940d423240b39d966113615a1fba0e170b7aa70deeb57e606975b0bf165e01d8 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d1c726e6b51547e2d8d1316bc1e3f198f9e33aa6 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/trainer_state.json @@ -0,0 +1,152 @@ +{ + "best_metric": 0.67293125, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50", + "epoch": 0.0064186912288584355, + "eval_steps": 50, + "global_step": 50, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.9445397602697216e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-50/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e350c09314d6497a8335a63d54b678ae41a643e5 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b363c25c681c8f2c0d03202e277c4e238b5faa8f8d00d8d1f270aecddc1a7dac +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b9252a7e3f195fabe0cea415d6ae2bb939c7a5a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5a5f4460108e7cf460561b79ef74cf92620103bd0f9ee69cf3aaa659b28db7 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ff1b0d00ee5dee5e24f003262db3e7c5af98529 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86126c9f88b7729720201a03b9d182864f717ff49dbe935a58372c2e54fca45c +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..db82086b661018ef010f0005965cfcb18393b6ed --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3339b83515f2623e070455958f08f49d4f93e5c502d9079b9ac5cf780f5c24e8 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9d7d2713862bcaa2386a96deb9e5e46d80df8dd2 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/trainer_state.json @@ -0,0 +1,1133 @@ +{ + "best_metric": 0.61346853, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450", + "epoch": 0.06418691228858436, + "eval_steps": 50, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.9245101295782707e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e26a9bb9860be1fef21ab26bb3c7d12b0289e842 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954f22d1e8724f33cfa641902ecd0d6038b95e2cd9d1bd27583ad6b2d8975087 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ca79cc408e4ac759b09178edc29f214c4521d46 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0096873fcac56525dd7758cf271d33fc8c9647b99773f1c7127cd19220f48b +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..51d11ee66db4c351944cda7a7537b56147e7128a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a8a155fbde6cce8de04c3e60be0a7d05a46ffad805e40bbd67329161c0d0c1 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0925ccf30b0cac5446bd9e54c8ad7c5c5a089fa1 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a3a04336c212af0969a72683e88039d8ba3c8ef319275ba12ddc63eb4e402c +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c6c5bc11d8e93112c07ac87756f3e14c055f5d98 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/trainer_state.json @@ -0,0 +1,1242 @@ +{ + "best_metric": 0.61346853, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-450", + "epoch": 0.0706056035174428, + "eval_steps": 50, + "global_step": 550, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.1145625029667635e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-550/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..834176435d9a01fe40014e958ad0b86e29f613b2 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88143751efabaafd85dcd363dd374116eabbb492a976d4d5a48cd1dc8ed9c055 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..822c9cae2129ac9e78a6e6efba00ed9798e92d3b --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87bc9c145d5521a48a0e42379e84809457c835ca9bf1c47c2984ef5a9c47b0d8 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9a6dc73721fa625b26a761606d2f492fa119ebb --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fab44b8fee39c10c68dc86d3fe42aebb8d1925132dc38a91cb76b8870ac954 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f0b9089516c21db837e72f78ae74715e6132bae5 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0050db64f37138cf6ff1b528a52fd000f96bb8487df28a0044d6b11118b11fb3 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..173316f2995a250f1e11ea0f6c3ded9673118ae3 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/trainer_state.json @@ -0,0 +1,1351 @@ +{ + "best_metric": 0.61097735, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600", + "epoch": 0.07702429474630122, + "eval_steps": 50, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.3054526620246016e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a61e3334e95e75af4433afd4111c0834635173c3 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14e273d5b9d5634aa6fcf9b8b9cfc09cc2d9afb3433c991cade84a062bf7ed8 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..36f71506f3e1cc5d8fd9b1c4f45e4d11d92362b0 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab58407a0c9df12f7669fac4cb298f9ab31e7a9b13f1259df46a15adb86e7228 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..6778f4ec603dbd734233a72b34750d68bf2b3a29 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22454ece769d70bcd012077c4feb95956ec2b5784675e142ff4b00f0e0ea6fc +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f76780c0b652ac772f9dbbb03fe63b3620e6cc3f --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ae07263f5b79c063f09b947a0f2afef7cf40a0336e4d74e8f8be8f47c7d1f3 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9b08cf203e9ebfbacb57e95d9a39a9588109c5b9 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/trainer_state.json @@ -0,0 +1,1460 @@ +{ + "best_metric": 0.60768825, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650", + "epoch": 0.08344298597515966, + "eval_steps": 50, + "global_step": 650, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.4999193059360768e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-650/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6867cb58ca7db38f64adeafea491b4f045e023a5 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6564adad8bf40bb168113e560cc6ff541d2ceb948ad6e06d8a9669664b18c3d0 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb1595d9df26cd593e8ddd77b61dab327964243e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e082117b1981939fa1abbcbc12920f11e6beb354bb69313cd2ef8bc4df10c90e +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a4fa8d1c70eeaee316454fd9475ec013bb1decf --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65ad523e9e25a6b871af66d563e89ca3b8b0343951a3073fa8737b9f2df91cc +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..042758cab3f874a6e0b54cac3e9ac14488ddc479 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5999b483055390e27e04b1b1d124f4d6b9ad1809ea12b3a5471291e305038cce +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dbb92557dded7dcfd256cc358733910c28bce448 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/trainer_state.json @@ -0,0 +1,1569 @@ +{ + "best_metric": 0.60764617, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700", + "epoch": 0.0898616772040181, + "eval_steps": 50, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.6918182671040512e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..408b67020024a8ace6a275f488cf5400af2e8ba7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3109d09171b7f671328ffc3c030035368b7cffa5481072894f90c3d9ba692de7 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f0016d7f75a8ee33df6d7147b6dc4355b61f287 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7e042f13e63175ef6ad8598ed33e3e73a31a6fa257b32648d133e515ab84b1 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..db835ad574ab21a1993fe3d5ba808c6686da7b93 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f93fe8dcd659a69bb5a99fa250d0f5988805499f225619207746b61de72f6e3 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..043475dcb05969a7fcead40772b4465e3a95e34e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c88e80349bd3612cdb2f765fa52cb3a05a8e6138fe92f54e1b7e11b6933ba9a +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d768cf8fe61ff45c4b36e9b22d2932e8a979e260 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/trainer_state.json @@ -0,0 +1,1678 @@ +{ + "best_metric": 0.60764617, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700", + "epoch": 0.09628036843287653, + "eval_steps": 50, + "global_step": 750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.8893020600457216e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f5cfaae1f52714169125ea305c6c1df84eb7650 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f38ba6311956fd1504f960bd88d78d52a349e71d4434c82c1b113183049384 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6929b541461263d70b5bbc47462426dd56677796 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444ac31c6bf2b8d3353d2dcba38cdefc1800f7d7dcb8fad3bb50541536b13ff7 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fffb49b87f50933fc31a0c618b1610ca8461288 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f4278b8acb050453447cf10f1ab976ad244596cd1e14d276458951e120b3d1 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3a2d2a097acdcc84d34b20717044b065f52af82 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4affa781cbd3b4d2d6b13f4c7ca13e85806000ac218062c57aa4f92094be7975 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..94379e5f253bd84e4fab916698fe5f69fbcb7575 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/trainer_state.json @@ -0,0 +1,1787 @@ +{ + "best_metric": 0.60764617, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-700", + "epoch": 0.10269905966173497, + "eval_steps": 50, + "global_step": 800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + }, + { + "acc": 0.82061501, + "epoch": 0.09692223755576237, + "grad_norm": 0.2477208524942398, + "learning_rate": 1.553232954407171e-05, + "loss": 0.61750922, + "memory(GiB)": 12.9, + "step": 755, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81846237, + "epoch": 0.09756410667864822, + "grad_norm": 0.22278401255607605, + "learning_rate": 1.4938160786375572e-05, + "loss": 0.61280818, + "memory(GiB)": 12.9, + "step": 760, + "train_speed(iter/s)": 0.079391 + }, + { + "acc": 0.81434851, + "epoch": 0.09820597580153406, + "grad_norm": 0.22640761733055115, + "learning_rate": 1.435357758543015e-05, + "loss": 0.63006077, + "memory(GiB)": 12.9, + "step": 765, + "train_speed(iter/s)": 0.079552 + }, + { + "acc": 0.81086941, + "epoch": 0.0988478449244199, + "grad_norm": 0.20250476896762848, + "learning_rate": 1.3778739760445552e-05, + "loss": 0.63865561, + "memory(GiB)": 12.9, + "step": 770, + "train_speed(iter/s)": 0.079713 + }, + { + "acc": 0.81333466, + "epoch": 0.09948971404730575, + "grad_norm": 0.21983562409877777, + "learning_rate": 1.3213804466343421e-05, + "loss": 0.63764729, + "memory(GiB)": 12.9, + "step": 775, + "train_speed(iter/s)": 0.079857 + }, + { + "acc": 0.81033506, + "epoch": 0.1001315831701916, + "grad_norm": 0.21427662670612335, + "learning_rate": 1.2658926150792322e-05, + "loss": 0.62097745, + "memory(GiB)": 12.9, + "step": 780, + "train_speed(iter/s)": 0.080004 + }, + { + "acc": 0.82130699, + "epoch": 0.10077345229307744, + "grad_norm": 0.20593635737895966, + "learning_rate": 1.2114256511983274e-05, + "loss": 0.60655851, + "memory(GiB)": 12.9, + "step": 785, + "train_speed(iter/s)": 0.080173 + }, + { + "acc": 0.82261295, + "epoch": 0.10141532141596328, + "grad_norm": 0.2052464336156845, + "learning_rate": 1.157994445715706e-05, + "loss": 0.61125717, + "memory(GiB)": 12.9, + "step": 790, + "train_speed(iter/s)": 0.080342 + }, + { + "acc": 0.82531328, + "epoch": 0.10205719053884912, + "grad_norm": 0.17600791156291962, + "learning_rate": 1.1056136061894384e-05, + "loss": 0.59510598, + "memory(GiB)": 12.9, + "step": 795, + "train_speed(iter/s)": 0.08049 + }, + { + "acc": 0.81779881, + "epoch": 0.10269905966173497, + "grad_norm": 0.2141779363155365, + "learning_rate": 1.0542974530180327e-05, + "loss": 0.63478656, + "memory(GiB)": 12.9, + "step": 800, + "train_speed(iter/s)": 0.080624 + }, + { + "epoch": 0.10269905966173497, + "eval_acc": 0.8207697400203976, + "eval_loss": 0.6077002882957458, + "eval_runtime": 194.8773, + "eval_samples_per_second": 6.455, + "eval_steps_per_second": 6.455, + "step": 800 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.0833426245342e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15091527d49d94b7f7b4bac182696e6f469a7b45 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2981cb572d79cbc255f54fa13fc44e7741362f534953ee36472f3f7ad9b07909 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec277ddc41aeaed2589cc2b9161df762ebcb2c41 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353e51491942a0feef372b601ccff0bd990e4c7636146b3abfd9193a243d5354 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b1fa483b4307b87714d2db74e25c48f060c1a57 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5490b8734486fdc5c2464201b0cfd7d1a8b60a38af275b80b28937bc51211f66 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1fcef8ac4b13c045612ac2c5e33a12b5244b4f4 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fe868f5007d41582c95908bf0f10eb7419df3cb768a8bb30a851d3ddaf4ab6 +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..29be0a795e6944c11ecac719c2d02a7fb37fd758 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/trainer_state.json @@ -0,0 +1,1896 @@ +{ + "best_metric": 0.60646284, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850", + "epoch": 0.1091177508905934, + "eval_steps": 50, + "global_step": 850, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + }, + { + "acc": 0.82061501, + "epoch": 0.09692223755576237, + "grad_norm": 0.2477208524942398, + "learning_rate": 1.553232954407171e-05, + "loss": 0.61750922, + "memory(GiB)": 12.9, + "step": 755, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81846237, + "epoch": 0.09756410667864822, + "grad_norm": 0.22278401255607605, + "learning_rate": 1.4938160786375572e-05, + "loss": 0.61280818, + "memory(GiB)": 12.9, + "step": 760, + "train_speed(iter/s)": 0.079391 + }, + { + "acc": 0.81434851, + "epoch": 0.09820597580153406, + "grad_norm": 0.22640761733055115, + "learning_rate": 1.435357758543015e-05, + "loss": 0.63006077, + "memory(GiB)": 12.9, + "step": 765, + "train_speed(iter/s)": 0.079552 + }, + { + "acc": 0.81086941, + "epoch": 0.0988478449244199, + "grad_norm": 0.20250476896762848, + "learning_rate": 1.3778739760445552e-05, + "loss": 0.63865561, + "memory(GiB)": 12.9, + "step": 770, + "train_speed(iter/s)": 0.079713 + }, + { + "acc": 0.81333466, + "epoch": 0.09948971404730575, + "grad_norm": 0.21983562409877777, + "learning_rate": 1.3213804466343421e-05, + "loss": 0.63764729, + "memory(GiB)": 12.9, + "step": 775, + "train_speed(iter/s)": 0.079857 + }, + { + "acc": 0.81033506, + "epoch": 0.1001315831701916, + "grad_norm": 0.21427662670612335, + "learning_rate": 1.2658926150792322e-05, + "loss": 0.62097745, + "memory(GiB)": 12.9, + "step": 780, + "train_speed(iter/s)": 0.080004 + }, + { + "acc": 0.82130699, + "epoch": 0.10077345229307744, + "grad_norm": 0.20593635737895966, + "learning_rate": 1.2114256511983274e-05, + "loss": 0.60655851, + "memory(GiB)": 12.9, + "step": 785, + "train_speed(iter/s)": 0.080173 + }, + { + "acc": 0.82261295, + "epoch": 0.10141532141596328, + "grad_norm": 0.2052464336156845, + "learning_rate": 1.157994445715706e-05, + "loss": 0.61125717, + "memory(GiB)": 12.9, + "step": 790, + "train_speed(iter/s)": 0.080342 + }, + { + "acc": 0.82531328, + "epoch": 0.10205719053884912, + "grad_norm": 0.17600791156291962, + "learning_rate": 1.1056136061894384e-05, + "loss": 0.59510598, + "memory(GiB)": 12.9, + "step": 795, + "train_speed(iter/s)": 0.08049 + }, + { + "acc": 0.81779881, + "epoch": 0.10269905966173497, + "grad_norm": 0.2141779363155365, + "learning_rate": 1.0542974530180327e-05, + "loss": 0.63478656, + "memory(GiB)": 12.9, + "step": 800, + "train_speed(iter/s)": 0.080624 + }, + { + "epoch": 0.10269905966173497, + "eval_acc": 0.8207697400203976, + "eval_loss": 0.6077002882957458, + "eval_runtime": 194.8773, + "eval_samples_per_second": 6.455, + "eval_steps_per_second": 6.455, + "step": 800 + }, + { + "acc": 0.80902939, + "epoch": 0.10334092878462081, + "grad_norm": 0.2090810388326645, + "learning_rate": 1.0040600155253765e-05, + "loss": 0.66100531, + "memory(GiB)": 12.9, + "step": 805, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81437035, + "epoch": 0.10398279790750665, + "grad_norm": 0.22697587311267853, + "learning_rate": 9.549150281252633e-06, + "loss": 0.63930345, + "memory(GiB)": 12.9, + "step": 810, + "train_speed(iter/s)": 0.079387 + }, + { + "acc": 0.81263914, + "epoch": 0.1046246670303925, + "grad_norm": 0.21495579183101654, + "learning_rate": 9.068759265665384e-06, + "loss": 0.63128233, + "memory(GiB)": 12.9, + "step": 815, + "train_speed(iter/s)": 0.079538 + }, + { + "acc": 0.80606184, + "epoch": 0.10526653615327834, + "grad_norm": 0.24026648700237274, + "learning_rate": 8.599558442598998e-06, + "loss": 0.66762576, + "memory(GiB)": 12.9, + "step": 820, + "train_speed(iter/s)": 0.07969 + }, + { + "acc": 0.83144102, + "epoch": 0.10590840527616419, + "grad_norm": 0.2179374396800995, + "learning_rate": 8.141676086873572e-06, + "loss": 0.56980219, + "memory(GiB)": 12.9, + "step": 825, + "train_speed(iter/s)": 0.079849 + }, + { + "acc": 0.81910725, + "epoch": 0.10655027439905003, + "grad_norm": 0.19496454298496246, + "learning_rate": 7.695237378953223e-06, + "loss": 0.61694736, + "memory(GiB)": 12.9, + "step": 830, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.81330662, + "epoch": 0.10719214352193587, + "grad_norm": 0.23187701404094696, + "learning_rate": 7.260364370723044e-06, + "loss": 0.64870877, + "memory(GiB)": 12.9, + "step": 835, + "train_speed(iter/s)": 0.080126 + }, + { + "acc": 0.81870842, + "epoch": 0.10783401264482172, + "grad_norm": 0.20400239527225494, + "learning_rate": 6.837175952121306e-06, + "loss": 0.61115222, + "memory(GiB)": 12.9, + "step": 840, + "train_speed(iter/s)": 0.080258 + }, + { + "acc": 0.82128296, + "epoch": 0.10847588176770756, + "grad_norm": 0.24608130753040314, + "learning_rate": 6.425787818636131e-06, + "loss": 0.61838484, + "memory(GiB)": 12.9, + "step": 845, + "train_speed(iter/s)": 0.080422 + }, + { + "acc": 0.8118104, + "epoch": 0.1091177508905934, + "grad_norm": 0.21192343533039093, + "learning_rate": 6.026312439675552e-06, + "loss": 0.67037339, + "memory(GiB)": 12.9, + "step": 850, + "train_speed(iter/s)": 0.080553 + }, + { + "epoch": 0.1091177508905934, + "eval_acc": 0.8208858520874116, + "eval_loss": 0.606462836265564, + "eval_runtime": 194.9575, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 850 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.2770957254897254e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96b09edbc63432c15e9e55c22b020b54bcb9c8e4 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db693399dc93f505eb11380a41fd3abd495e01e99b6c44c195b96d85a6fbe643 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6c52dac4a5ae3d9d8a2576d32c3724c96d0e367 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337bdbeacd397f6c7f7992edea78f056ef35ec9bad91e32e95704af78df8f493 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ae9c0199cc5b7c919fb2ba852ef7f6ad0068d99 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8643efc201ee03edfca28c05447be66c9ec9877d520cbc421d2457ec4bfd4ad0 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..47a08515db5e3646657b7fb7f4c6a2d5852bfb2e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0428512ada8c2471b2f37ecbdd4efa5f13e3ba0e777fddbfec0396eebc36c01a +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..7cfe5750e2ef27217473c1c1916440666af661ab --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/trainer_state.json @@ -0,0 +1,2005 @@ +{ + "best_metric": 0.60646284, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850", + "epoch": 0.11553644211945184, + "eval_steps": 50, + "global_step": 900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + }, + { + "acc": 0.82061501, + "epoch": 0.09692223755576237, + "grad_norm": 0.2477208524942398, + "learning_rate": 1.553232954407171e-05, + "loss": 0.61750922, + "memory(GiB)": 12.9, + "step": 755, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81846237, + "epoch": 0.09756410667864822, + "grad_norm": 0.22278401255607605, + "learning_rate": 1.4938160786375572e-05, + "loss": 0.61280818, + "memory(GiB)": 12.9, + "step": 760, + "train_speed(iter/s)": 0.079391 + }, + { + "acc": 0.81434851, + "epoch": 0.09820597580153406, + "grad_norm": 0.22640761733055115, + "learning_rate": 1.435357758543015e-05, + "loss": 0.63006077, + "memory(GiB)": 12.9, + "step": 765, + "train_speed(iter/s)": 0.079552 + }, + { + "acc": 0.81086941, + "epoch": 0.0988478449244199, + "grad_norm": 0.20250476896762848, + "learning_rate": 1.3778739760445552e-05, + "loss": 0.63865561, + "memory(GiB)": 12.9, + "step": 770, + "train_speed(iter/s)": 0.079713 + }, + { + "acc": 0.81333466, + "epoch": 0.09948971404730575, + "grad_norm": 0.21983562409877777, + "learning_rate": 1.3213804466343421e-05, + "loss": 0.63764729, + "memory(GiB)": 12.9, + "step": 775, + "train_speed(iter/s)": 0.079857 + }, + { + "acc": 0.81033506, + "epoch": 0.1001315831701916, + "grad_norm": 0.21427662670612335, + "learning_rate": 1.2658926150792322e-05, + "loss": 0.62097745, + "memory(GiB)": 12.9, + "step": 780, + "train_speed(iter/s)": 0.080004 + }, + { + "acc": 0.82130699, + "epoch": 0.10077345229307744, + "grad_norm": 0.20593635737895966, + "learning_rate": 1.2114256511983274e-05, + "loss": 0.60655851, + "memory(GiB)": 12.9, + "step": 785, + "train_speed(iter/s)": 0.080173 + }, + { + "acc": 0.82261295, + "epoch": 0.10141532141596328, + "grad_norm": 0.2052464336156845, + "learning_rate": 1.157994445715706e-05, + "loss": 0.61125717, + "memory(GiB)": 12.9, + "step": 790, + "train_speed(iter/s)": 0.080342 + }, + { + "acc": 0.82531328, + "epoch": 0.10205719053884912, + "grad_norm": 0.17600791156291962, + "learning_rate": 1.1056136061894384e-05, + "loss": 0.59510598, + "memory(GiB)": 12.9, + "step": 795, + "train_speed(iter/s)": 0.08049 + }, + { + "acc": 0.81779881, + "epoch": 0.10269905966173497, + "grad_norm": 0.2141779363155365, + "learning_rate": 1.0542974530180327e-05, + "loss": 0.63478656, + "memory(GiB)": 12.9, + "step": 800, + "train_speed(iter/s)": 0.080624 + }, + { + "epoch": 0.10269905966173497, + "eval_acc": 0.8207697400203976, + "eval_loss": 0.6077002882957458, + "eval_runtime": 194.8773, + "eval_samples_per_second": 6.455, + "eval_steps_per_second": 6.455, + "step": 800 + }, + { + "acc": 0.80902939, + "epoch": 0.10334092878462081, + "grad_norm": 0.2090810388326645, + "learning_rate": 1.0040600155253765e-05, + "loss": 0.66100531, + "memory(GiB)": 12.9, + "step": 805, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81437035, + "epoch": 0.10398279790750665, + "grad_norm": 0.22697587311267853, + "learning_rate": 9.549150281252633e-06, + "loss": 0.63930345, + "memory(GiB)": 12.9, + "step": 810, + "train_speed(iter/s)": 0.079387 + }, + { + "acc": 0.81263914, + "epoch": 0.1046246670303925, + "grad_norm": 0.21495579183101654, + "learning_rate": 9.068759265665384e-06, + "loss": 0.63128233, + "memory(GiB)": 12.9, + "step": 815, + "train_speed(iter/s)": 0.079538 + }, + { + "acc": 0.80606184, + "epoch": 0.10526653615327834, + "grad_norm": 0.24026648700237274, + "learning_rate": 8.599558442598998e-06, + "loss": 0.66762576, + "memory(GiB)": 12.9, + "step": 820, + "train_speed(iter/s)": 0.07969 + }, + { + "acc": 0.83144102, + "epoch": 0.10590840527616419, + "grad_norm": 0.2179374396800995, + "learning_rate": 8.141676086873572e-06, + "loss": 0.56980219, + "memory(GiB)": 12.9, + "step": 825, + "train_speed(iter/s)": 0.079849 + }, + { + "acc": 0.81910725, + "epoch": 0.10655027439905003, + "grad_norm": 0.19496454298496246, + "learning_rate": 7.695237378953223e-06, + "loss": 0.61694736, + "memory(GiB)": 12.9, + "step": 830, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.81330662, + "epoch": 0.10719214352193587, + "grad_norm": 0.23187701404094696, + "learning_rate": 7.260364370723044e-06, + "loss": 0.64870877, + "memory(GiB)": 12.9, + "step": 835, + "train_speed(iter/s)": 0.080126 + }, + { + "acc": 0.81870842, + "epoch": 0.10783401264482172, + "grad_norm": 0.20400239527225494, + "learning_rate": 6.837175952121306e-06, + "loss": 0.61115222, + "memory(GiB)": 12.9, + "step": 840, + "train_speed(iter/s)": 0.080258 + }, + { + "acc": 0.82128296, + "epoch": 0.10847588176770756, + "grad_norm": 0.24608130753040314, + "learning_rate": 6.425787818636131e-06, + "loss": 0.61838484, + "memory(GiB)": 12.9, + "step": 845, + "train_speed(iter/s)": 0.080422 + }, + { + "acc": 0.8118104, + "epoch": 0.1091177508905934, + "grad_norm": 0.21192343533039093, + "learning_rate": 6.026312439675552e-06, + "loss": 0.67037339, + "memory(GiB)": 12.9, + "step": 850, + "train_speed(iter/s)": 0.080553 + }, + { + "epoch": 0.1091177508905934, + "eval_acc": 0.8208858520874116, + "eval_loss": 0.606462836265564, + "eval_runtime": 194.9575, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 850 + }, + { + "acc": 0.81058187, + "epoch": 0.10975962001347925, + "grad_norm": 0.2256067544221878, + "learning_rate": 5.6388590278194096e-06, + "loss": 0.63853312, + "memory(GiB)": 12.9, + "step": 855, + "train_speed(iter/s)": 0.079236 + }, + { + "acc": 0.8174571, + "epoch": 0.11040148913636509, + "grad_norm": 0.21500875055789948, + "learning_rate": 5.263533508961827e-06, + "loss": 0.6172534, + "memory(GiB)": 12.9, + "step": 860, + "train_speed(iter/s)": 0.079369 + }, + { + "acc": 0.8093504, + "epoch": 0.11104335825925093, + "grad_norm": 0.23700734972953796, + "learning_rate": 4.900438493352055e-06, + "loss": 0.65724411, + "memory(GiB)": 12.9, + "step": 865, + "train_speed(iter/s)": 0.07952 + }, + { + "acc": 0.81735506, + "epoch": 0.11168522738213678, + "grad_norm": 0.21098878979682922, + "learning_rate": 4.549673247541875e-06, + "loss": 0.61837373, + "memory(GiB)": 12.9, + "step": 870, + "train_speed(iter/s)": 0.079659 + }, + { + "acc": 0.81503067, + "epoch": 0.11232709650502262, + "grad_norm": 0.20609669387340546, + "learning_rate": 4.2113336672471245e-06, + "loss": 0.61365747, + "memory(GiB)": 12.9, + "step": 875, + "train_speed(iter/s)": 0.079794 + }, + { + "acc": 0.80629053, + "epoch": 0.11296896562790847, + "grad_norm": 0.2180800437927246, + "learning_rate": 3.885512251130763e-06, + "loss": 0.66433964, + "memory(GiB)": 12.9, + "step": 880, + "train_speed(iter/s)": 0.079933 + }, + { + "acc": 0.82552185, + "epoch": 0.11361083475079431, + "grad_norm": 0.2074093371629715, + "learning_rate": 3.5722980755146517e-06, + "loss": 0.5967988, + "memory(GiB)": 12.9, + "step": 885, + "train_speed(iter/s)": 0.080078 + }, + { + "acc": 0.81032143, + "epoch": 0.11425270387368015, + "grad_norm": 0.232750803232193, + "learning_rate": 3.271776770026963e-06, + "loss": 0.66238441, + "memory(GiB)": 12.9, + "step": 890, + "train_speed(iter/s)": 0.080218 + }, + { + "acc": 0.8156251, + "epoch": 0.114894572996566, + "grad_norm": 0.24590888619422913, + "learning_rate": 2.9840304941919415e-06, + "loss": 0.6185041, + "memory(GiB)": 12.9, + "step": 895, + "train_speed(iter/s)": 0.080356 + }, + { + "acc": 0.81570625, + "epoch": 0.11553644211945184, + "grad_norm": 0.2058228850364685, + "learning_rate": 2.7091379149682685e-06, + "loss": 0.61333613, + "memory(GiB)": 12.9, + "step": 900, + "train_speed(iter/s)": 0.080474 + }, + { + "epoch": 0.11553644211945184, + "eval_acc": 0.8202886005724797, + "eval_loss": 0.6085067391395569, + "eval_runtime": 194.5686, + "eval_samples_per_second": 6.466, + "eval_steps_per_second": 6.466, + "step": 900 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.472378717112156e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/README.md b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d29fbbf329f13361706cd40d9606757b03f19d4e --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/README.md @@ -0,0 +1,202 @@ +--- +base_model: /home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..06036881545aa70a83384e380e9b6fe1ac1f72a7 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_config.json @@ -0,0 +1,26 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": [], + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_model.safetensors b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0081f6b9a5c983c7d98dc4d201c282e20a152fae --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf4f28ed1c0cce5f5ae0f301149ba48722c8b99cdaf1d50637bfd92e0ebc8e4 +size 50792328 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/additional_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/additional_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bbe5159d1d10a158affb4d328c70025d891e16d8 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/additional_config.json @@ -0,0 +1 @@ +{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/configuration.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/configuration.json new file mode 100644 index 0000000000000000000000000000000000000000..218844be602bb3bca1122426e17932b1cbf10d1a --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/configuration.json @@ -0,0 +1,11 @@ +{ + "adapter_cfg": { + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "sft_type": "lora", + "tuner_backend": "peft", + "template_type": "phi3-vl", + "dtype": "bf16", + "system": null + } +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/generation_config.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b22c9341f9ca3117521ad881d7548032f2f2c9fe --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 32000, + "max_new_tokens": 2048, + "pad_token_id": 32000, + "transformers_version": "4.46.3" +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/optimizer.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fbae125692ba0420a9c212b82b8d13988b6d097 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23c425d33d0e54e3c1aabf9ff69c195df52357c37f9ad67a18872ccbb6eacb0 +size 100878458 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/rng_state.pth b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..551e5c0180a22b5a1600382e53048f151eaab54f --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d746d890d5cba1a1fa4e0fed5198da5d328dedd3e52b38b3e664d0ee99dc160 +size 14244 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/scheduler.pt b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..94e174493b8ce94b61d1a523f166053195be1cae --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7813559d5a5b2cf01d9d3f7d90d4db3622ccaa89ce7a52ba8849c81c2b04c32a +size 1064 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/trainer_state.json b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9e8e903b02177f6731e8721961df27c8a4314851 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/trainer_state.json @@ -0,0 +1,2114 @@ +{ + "best_metric": 0.60646284, + "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850", + "epoch": 0.12195513334831028, + "eval_steps": 50, + "global_step": 950, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "acc": 0.77952504, + "epoch": 0.0001283738245771687, + "grad_norm": 0.15511861443519592, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.82634771, + "memory(GiB)": 11.42, + "step": 1, + "train_speed(iter/s)": 0.092016 + }, + { + "acc": 0.77674872, + "epoch": 0.0006418691228858435, + "grad_norm": 0.14591480791568756, + "learning_rate": 1e-05, + "loss": 0.8159712, + "memory(GiB)": 12.15, + "step": 5, + "train_speed(iter/s)": 0.10552 + }, + { + "acc": 0.77379012, + "epoch": 0.001283738245771687, + "grad_norm": 0.151850163936615, + "learning_rate": 2e-05, + "loss": 0.8015564, + "memory(GiB)": 12.15, + "step": 10, + "train_speed(iter/s)": 0.107013 + }, + { + "acc": 0.7784133, + "epoch": 0.0019256073686575307, + "grad_norm": 0.15997682511806488, + "learning_rate": 3e-05, + "loss": 0.79284344, + "memory(GiB)": 12.15, + "step": 15, + "train_speed(iter/s)": 0.110995 + }, + { + "acc": 0.7815052, + "epoch": 0.002567476491543374, + "grad_norm": 0.14427673816680908, + "learning_rate": 4e-05, + "loss": 0.78122258, + "memory(GiB)": 12.9, + "step": 20, + "train_speed(iter/s)": 0.111462 + }, + { + "acc": 0.7915082, + "epoch": 0.0032093456144292177, + "grad_norm": 0.1590222716331482, + "learning_rate": 5e-05, + "loss": 0.7404335, + "memory(GiB)": 12.9, + "step": 25, + "train_speed(iter/s)": 0.112268 + }, + { + "acc": 0.80291214, + "epoch": 0.0038512147373150614, + "grad_norm": 0.13638992607593536, + "learning_rate": 6e-05, + "loss": 0.68063788, + "memory(GiB)": 12.9, + "step": 30, + "train_speed(iter/s)": 0.111517 + }, + { + "acc": 0.79923964, + "epoch": 0.0044930838602009054, + "grad_norm": 0.1271245777606964, + "learning_rate": 7e-05, + "loss": 0.68800621, + "memory(GiB)": 12.9, + "step": 35, + "train_speed(iter/s)": 0.110574 + }, + { + "acc": 0.80240812, + "epoch": 0.005134952983086748, + "grad_norm": 0.11937133222818375, + "learning_rate": 8e-05, + "loss": 0.69939818, + "memory(GiB)": 12.9, + "step": 40, + "train_speed(iter/s)": 0.109469 + }, + { + "acc": 0.78317132, + "epoch": 0.005776822105972592, + "grad_norm": 0.1665358543395996, + "learning_rate": 9e-05, + "loss": 0.75735736, + "memory(GiB)": 12.9, + "step": 45, + "train_speed(iter/s)": 0.108968 + }, + { + "acc": 0.80379133, + "epoch": 0.0064186912288584355, + "grad_norm": 0.14883440732955933, + "learning_rate": 0.0001, + "loss": 0.6824338, + "memory(GiB)": 12.9, + "step": 50, + "train_speed(iter/s)": 0.109163 + }, + { + "epoch": 0.0064186912288584355, + "eval_acc": 0.8081346555994846, + "eval_loss": 0.6729312539100647, + "eval_runtime": 195.4613, + "eval_samples_per_second": 6.436, + "eval_steps_per_second": 6.436, + "step": 50 + }, + { + "acc": 0.7984889, + "epoch": 0.007060560351744279, + "grad_norm": 0.16687534749507904, + "learning_rate": 9.999316524962345e-05, + "loss": 0.7141089, + "memory(GiB)": 12.9, + "step": 55, + "train_speed(iter/s)": 0.078646 + }, + { + "acc": 0.79216175, + "epoch": 0.007702429474630123, + "grad_norm": 0.17546051740646362, + "learning_rate": 9.997266286704631e-05, + "loss": 0.72419305, + "memory(GiB)": 12.9, + "step": 60, + "train_speed(iter/s)": 0.080466 + }, + { + "acc": 0.80358973, + "epoch": 0.008344298597515967, + "grad_norm": 0.16079305112361908, + "learning_rate": 9.993849845741524e-05, + "loss": 0.67717872, + "memory(GiB)": 12.9, + "step": 65, + "train_speed(iter/s)": 0.082252 + }, + { + "acc": 0.80615339, + "epoch": 0.008986167720401811, + "grad_norm": 0.1396234929561615, + "learning_rate": 9.989068136093873e-05, + "loss": 0.70638905, + "memory(GiB)": 12.9, + "step": 70, + "train_speed(iter/s)": 0.084 + }, + { + "acc": 0.79676814, + "epoch": 0.009628036843287653, + "grad_norm": 0.1340462565422058, + "learning_rate": 9.98292246503335e-05, + "loss": 0.71420946, + "memory(GiB)": 12.9, + "step": 75, + "train_speed(iter/s)": 0.08542 + }, + { + "acc": 0.79325166, + "epoch": 0.010269905966173496, + "grad_norm": 0.13259001076221466, + "learning_rate": 9.975414512725057e-05, + "loss": 0.71777782, + "memory(GiB)": 12.9, + "step": 80, + "train_speed(iter/s)": 0.086655 + }, + { + "acc": 0.81705523, + "epoch": 0.01091177508905934, + "grad_norm": 0.15833652019500732, + "learning_rate": 9.966546331768191e-05, + "loss": 0.62526927, + "memory(GiB)": 12.9, + "step": 85, + "train_speed(iter/s)": 0.088014 + }, + { + "acc": 0.80851898, + "epoch": 0.011553644211945184, + "grad_norm": 0.1456330418586731, + "learning_rate": 9.956320346634876e-05, + "loss": 0.68010745, + "memory(GiB)": 12.9, + "step": 90, + "train_speed(iter/s)": 0.088941 + }, + { + "acc": 0.81903477, + "epoch": 0.012195513334831027, + "grad_norm": 0.14285945892333984, + "learning_rate": 9.944739353007344e-05, + "loss": 0.6090106, + "memory(GiB)": 12.9, + "step": 95, + "train_speed(iter/s)": 0.089902 + }, + { + "acc": 0.82483721, + "epoch": 0.012837382457716871, + "grad_norm": 0.1478744000196457, + "learning_rate": 9.931806517013612e-05, + "loss": 0.59807158, + "memory(GiB)": 12.9, + "step": 100, + "train_speed(iter/s)": 0.090663 + }, + { + "epoch": 0.012837382457716871, + "eval_acc": 0.813768508772143, + "eval_loss": 0.645352840423584, + "eval_runtime": 195.755, + "eval_samples_per_second": 6.426, + "eval_steps_per_second": 6.426, + "step": 100 + }, + { + "acc": 0.80671978, + "epoch": 0.013479251580602715, + "grad_norm": 0.15444877743721008, + "learning_rate": 9.917525374361912e-05, + "loss": 0.66537051, + "memory(GiB)": 12.9, + "step": 105, + "train_speed(iter/s)": 0.078062 + }, + { + "acc": 0.81962786, + "epoch": 0.014121120703488558, + "grad_norm": 0.16826578974723816, + "learning_rate": 9.901899829374047e-05, + "loss": 0.60835891, + "memory(GiB)": 12.9, + "step": 110, + "train_speed(iter/s)": 0.079089 + }, + { + "acc": 0.80644588, + "epoch": 0.014762989826374402, + "grad_norm": 0.1519591063261032, + "learning_rate": 9.884934153917997e-05, + "loss": 0.66763787, + "memory(GiB)": 12.9, + "step": 115, + "train_speed(iter/s)": 0.08012 + }, + { + "acc": 0.8235981, + "epoch": 0.015404858949260246, + "grad_norm": 0.20040030777454376, + "learning_rate": 9.86663298624003e-05, + "loss": 0.5919826, + "memory(GiB)": 12.9, + "step": 120, + "train_speed(iter/s)": 0.081125 + }, + { + "acc": 0.81199884, + "epoch": 0.01604672807214609, + "grad_norm": 0.1842738389968872, + "learning_rate": 9.847001329696653e-05, + "loss": 0.63266978, + "memory(GiB)": 12.9, + "step": 125, + "train_speed(iter/s)": 0.082093 + }, + { + "acc": 0.81563005, + "epoch": 0.016688597195031935, + "grad_norm": 0.15375380218029022, + "learning_rate": 9.826044551386744e-05, + "loss": 0.61709371, + "memory(GiB)": 12.9, + "step": 130, + "train_speed(iter/s)": 0.082937 + }, + { + "acc": 0.80918331, + "epoch": 0.017330466317917778, + "grad_norm": 0.14841115474700928, + "learning_rate": 9.803768380684242e-05, + "loss": 0.63595695, + "memory(GiB)": 12.9, + "step": 135, + "train_speed(iter/s)": 0.083738 + }, + { + "acc": 0.81229877, + "epoch": 0.017972335440803622, + "grad_norm": 0.16627077758312225, + "learning_rate": 9.780178907671789e-05, + "loss": 0.64757662, + "memory(GiB)": 12.9, + "step": 140, + "train_speed(iter/s)": 0.084642 + }, + { + "acc": 0.804142, + "epoch": 0.018614204563689465, + "grad_norm": 0.1714244931936264, + "learning_rate": 9.755282581475769e-05, + "loss": 0.6832706, + "memory(GiB)": 12.9, + "step": 145, + "train_speed(iter/s)": 0.085406 + }, + { + "acc": 0.79688311, + "epoch": 0.019256073686575306, + "grad_norm": 0.18916593492031097, + "learning_rate": 9.729086208503174e-05, + "loss": 0.70668921, + "memory(GiB)": 12.9, + "step": 150, + "train_speed(iter/s)": 0.086183 + }, + { + "epoch": 0.019256073686575306, + "eval_acc": 0.8153510047395746, + "eval_loss": 0.6350318193435669, + "eval_runtime": 196.0265, + "eval_samples_per_second": 6.417, + "eval_steps_per_second": 6.417, + "step": 150 + }, + { + "acc": 0.80884809, + "epoch": 0.01989794280946115, + "grad_norm": 0.17633555829524994, + "learning_rate": 9.701596950580806e-05, + "loss": 0.63387117, + "memory(GiB)": 12.9, + "step": 155, + "train_speed(iter/s)": 0.078254 + }, + { + "acc": 0.81135025, + "epoch": 0.020539811932346993, + "grad_norm": 0.18200528621673584, + "learning_rate": 9.672822322997305e-05, + "loss": 0.65075536, + "memory(GiB)": 12.9, + "step": 160, + "train_speed(iter/s)": 0.078985 + }, + { + "acc": 0.82410259, + "epoch": 0.021181681055232836, + "grad_norm": 0.14853200316429138, + "learning_rate": 9.642770192448536e-05, + "loss": 0.60177903, + "memory(GiB)": 12.9, + "step": 165, + "train_speed(iter/s)": 0.079746 + }, + { + "acc": 0.80189457, + "epoch": 0.02182355017811868, + "grad_norm": 0.17732569575309753, + "learning_rate": 9.611448774886924e-05, + "loss": 0.68190188, + "memory(GiB)": 12.9, + "step": 170, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.81763601, + "epoch": 0.022465419301004524, + "grad_norm": 0.3583473563194275, + "learning_rate": 9.578866633275288e-05, + "loss": 0.62211475, + "memory(GiB)": 12.9, + "step": 175, + "train_speed(iter/s)": 0.081173 + }, + { + "acc": 0.81451321, + "epoch": 0.023107288423890367, + "grad_norm": 0.19369152188301086, + "learning_rate": 9.545032675245813e-05, + "loss": 0.63143706, + "memory(GiB)": 12.9, + "step": 180, + "train_speed(iter/s)": 0.081877 + }, + { + "acc": 0.809447, + "epoch": 0.02374915754677621, + "grad_norm": 0.16049319505691528, + "learning_rate": 9.509956150664796e-05, + "loss": 0.6451148, + "memory(GiB)": 12.9, + "step": 185, + "train_speed(iter/s)": 0.082533 + }, + { + "acc": 0.80372143, + "epoch": 0.024391026669662055, + "grad_norm": 0.19566483795642853, + "learning_rate": 9.473646649103818e-05, + "loss": 0.65715637, + "memory(GiB)": 12.9, + "step": 190, + "train_speed(iter/s)": 0.083203 + }, + { + "acc": 0.81516018, + "epoch": 0.0250328957925479, + "grad_norm": 0.1836969554424286, + "learning_rate": 9.43611409721806e-05, + "loss": 0.63388405, + "memory(GiB)": 12.9, + "step": 195, + "train_speed(iter/s)": 0.083851 + }, + { + "acc": 0.80683355, + "epoch": 0.025674764915433742, + "grad_norm": 0.15840834379196167, + "learning_rate": 9.397368756032445e-05, + "loss": 0.65765018, + "memory(GiB)": 12.9, + "step": 200, + "train_speed(iter/s)": 0.084362 + }, + { + "epoch": 0.025674764915433742, + "eval_acc": 0.8154263931167957, + "eval_loss": 0.6316511034965515, + "eval_runtime": 194.3299, + "eval_samples_per_second": 6.474, + "eval_steps_per_second": 6.474, + "step": 200 + }, + { + "acc": 0.81476297, + "epoch": 0.026316634038319586, + "grad_norm": 0.18683095276355743, + "learning_rate": 9.357421218136386e-05, + "loss": 0.64739652, + "memory(GiB)": 12.9, + "step": 205, + "train_speed(iter/s)": 0.078515 + }, + { + "acc": 0.80957623, + "epoch": 0.02695850316120543, + "grad_norm": 0.16226844489574432, + "learning_rate": 9.316282404787871e-05, + "loss": 0.65772038, + "memory(GiB)": 12.9, + "step": 210, + "train_speed(iter/s)": 0.079027 + }, + { + "acc": 0.81580648, + "epoch": 0.027600372284091273, + "grad_norm": 0.16426005959510803, + "learning_rate": 9.273963562927695e-05, + "loss": 0.63748703, + "memory(GiB)": 12.9, + "step": 215, + "train_speed(iter/s)": 0.079584 + }, + { + "acc": 0.80812073, + "epoch": 0.028242241406977116, + "grad_norm": 0.1749752312898636, + "learning_rate": 9.230476262104677e-05, + "loss": 0.66415677, + "memory(GiB)": 12.9, + "step": 220, + "train_speed(iter/s)": 0.080111 + }, + { + "acc": 0.81957884, + "epoch": 0.02888411052986296, + "grad_norm": 0.15272143483161926, + "learning_rate": 9.185832391312644e-05, + "loss": 0.62169385, + "memory(GiB)": 12.9, + "step": 225, + "train_speed(iter/s)": 0.080603 + }, + { + "acc": 0.80860453, + "epoch": 0.029525979652748804, + "grad_norm": 0.1689305603504181, + "learning_rate": 9.140044155740101e-05, + "loss": 0.6528583, + "memory(GiB)": 12.9, + "step": 230, + "train_speed(iter/s)": 0.081113 + }, + { + "acc": 0.81558657, + "epoch": 0.030167848775634647, + "grad_norm": 0.20389845967292786, + "learning_rate": 9.093124073433463e-05, + "loss": 0.62348075, + "memory(GiB)": 12.9, + "step": 235, + "train_speed(iter/s)": 0.081633 + }, + { + "acc": 0.83771782, + "epoch": 0.03080971789852049, + "grad_norm": 0.1833639293909073, + "learning_rate": 9.045084971874738e-05, + "loss": 0.54310794, + "memory(GiB)": 12.9, + "step": 240, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81091404, + "epoch": 0.03145158702140634, + "grad_norm": 0.1823006570339203, + "learning_rate": 8.995939984474624e-05, + "loss": 0.65011134, + "memory(GiB)": 12.9, + "step": 245, + "train_speed(iter/s)": 0.082662 + }, + { + "acc": 0.8202961, + "epoch": 0.03209345614429218, + "grad_norm": 0.19047267735004425, + "learning_rate": 8.945702546981969e-05, + "loss": 0.61326828, + "memory(GiB)": 12.9, + "step": 250, + "train_speed(iter/s)": 0.083111 + }, + { + "epoch": 0.03209345614429218, + "eval_acc": 0.8174640226702884, + "eval_loss": 0.6222989559173584, + "eval_runtime": 194.2619, + "eval_samples_per_second": 6.476, + "eval_steps_per_second": 6.476, + "step": 250 + }, + { + "acc": 0.81616802, + "epoch": 0.032735325267178025, + "grad_norm": 0.19024300575256348, + "learning_rate": 8.894386393810563e-05, + "loss": 0.65217943, + "memory(GiB)": 12.9, + "step": 255, + "train_speed(iter/s)": 0.078534 + }, + { + "acc": 0.81027069, + "epoch": 0.03337719439006387, + "grad_norm": 0.19169311225414276, + "learning_rate": 8.842005554284296e-05, + "loss": 0.65409112, + "memory(GiB)": 12.9, + "step": 260, + "train_speed(iter/s)": 0.078979 + }, + { + "acc": 0.80319004, + "epoch": 0.03401906351294971, + "grad_norm": 0.20081347227096558, + "learning_rate": 8.788574348801675e-05, + "loss": 0.67106547, + "memory(GiB)": 12.9, + "step": 265, + "train_speed(iter/s)": 0.079517 + }, + { + "acc": 0.82499094, + "epoch": 0.034660932635835556, + "grad_norm": 0.16266761720180511, + "learning_rate": 8.73410738492077e-05, + "loss": 0.57896609, + "memory(GiB)": 12.9, + "step": 270, + "train_speed(iter/s)": 0.079959 + }, + { + "acc": 0.83434772, + "epoch": 0.0353028017587214, + "grad_norm": 0.19760368764400482, + "learning_rate": 8.678619553365659e-05, + "loss": 0.56308613, + "memory(GiB)": 12.9, + "step": 275, + "train_speed(iter/s)": 0.080441 + }, + { + "acc": 0.81103878, + "epoch": 0.035944670881607244, + "grad_norm": 0.20421290397644043, + "learning_rate": 8.622126023955446e-05, + "loss": 0.62751951, + "memory(GiB)": 12.9, + "step": 280, + "train_speed(iter/s)": 0.080888 + }, + { + "acc": 0.80577688, + "epoch": 0.03658654000449309, + "grad_norm": 0.18944613635540009, + "learning_rate": 8.564642241456986e-05, + "loss": 0.67880988, + "memory(GiB)": 12.9, + "step": 285, + "train_speed(iter/s)": 0.081351 + }, + { + "acc": 0.81629257, + "epoch": 0.03722840912737893, + "grad_norm": 0.16580034792423248, + "learning_rate": 8.506183921362443e-05, + "loss": 0.63270054, + "memory(GiB)": 12.9, + "step": 290, + "train_speed(iter/s)": 0.081754 + }, + { + "acc": 0.81265612, + "epoch": 0.037870278250264774, + "grad_norm": 0.20476555824279785, + "learning_rate": 8.44676704559283e-05, + "loss": 0.63396297, + "memory(GiB)": 12.9, + "step": 295, + "train_speed(iter/s)": 0.082163 + }, + { + "acc": 0.81665688, + "epoch": 0.03851214737315061, + "grad_norm": 0.1685812920331955, + "learning_rate": 8.386407858128706e-05, + "loss": 0.63431234, + "memory(GiB)": 12.9, + "step": 300, + "train_speed(iter/s)": 0.082563 + }, + { + "epoch": 0.03851214737315061, + "eval_acc": 0.8180910416791721, + "eval_loss": 0.6213402152061462, + "eval_runtime": 194.9277, + "eval_samples_per_second": 6.454, + "eval_steps_per_second": 6.454, + "step": 300 + }, + { + "acc": 0.81313, + "epoch": 0.039154016496036455, + "grad_norm": 0.19343021512031555, + "learning_rate": 8.32512286056924e-05, + "loss": 0.65134788, + "memory(GiB)": 12.9, + "step": 305, + "train_speed(iter/s)": 0.078839 + }, + { + "acc": 0.80900688, + "epoch": 0.0397958856189223, + "grad_norm": 0.20626357197761536, + "learning_rate": 8.262928807620843e-05, + "loss": 0.66552057, + "memory(GiB)": 12.9, + "step": 310, + "train_speed(iter/s)": 0.07924 + }, + { + "acc": 0.81944618, + "epoch": 0.04043775474180814, + "grad_norm": 0.22261416912078857, + "learning_rate": 8.199842702516583e-05, + "loss": 0.6285687, + "memory(GiB)": 12.9, + "step": 315, + "train_speed(iter/s)": 0.079651 + }, + { + "acc": 0.82105675, + "epoch": 0.041079623864693986, + "grad_norm": 0.17977821826934814, + "learning_rate": 8.135881792367686e-05, + "loss": 0.61407933, + "memory(GiB)": 12.9, + "step": 320, + "train_speed(iter/s)": 0.080053 + }, + { + "acc": 0.81391029, + "epoch": 0.04172149298757983, + "grad_norm": 0.1734636276960373, + "learning_rate": 8.07106356344834e-05, + "loss": 0.63154807, + "memory(GiB)": 12.9, + "step": 325, + "train_speed(iter/s)": 0.080427 + }, + { + "acc": 0.80443487, + "epoch": 0.04236336211046567, + "grad_norm": 0.20138931274414062, + "learning_rate": 8.005405736415126e-05, + "loss": 0.67294674, + "memory(GiB)": 12.9, + "step": 330, + "train_speed(iter/s)": 0.08081 + }, + { + "acc": 0.8138341, + "epoch": 0.04300523123335152, + "grad_norm": 0.2296956181526184, + "learning_rate": 7.938926261462366e-05, + "loss": 0.62769508, + "memory(GiB)": 12.9, + "step": 335, + "train_speed(iter/s)": 0.081179 + }, + { + "acc": 0.81060715, + "epoch": 0.04364710035623736, + "grad_norm": 0.18877319991588593, + "learning_rate": 7.871643313414718e-05, + "loss": 0.65062008, + "memory(GiB)": 12.9, + "step": 340, + "train_speed(iter/s)": 0.081555 + }, + { + "acc": 0.80925789, + "epoch": 0.044288969479123204, + "grad_norm": 0.20824845135211945, + "learning_rate": 7.803575286758364e-05, + "loss": 0.65066905, + "memory(GiB)": 12.9, + "step": 345, + "train_speed(iter/s)": 0.081899 + }, + { + "acc": 0.80743494, + "epoch": 0.04493083860200905, + "grad_norm": 0.1929645985364914, + "learning_rate": 7.734740790612136e-05, + "loss": 0.64833279, + "memory(GiB)": 12.9, + "step": 350, + "train_speed(iter/s)": 0.082229 + }, + { + "epoch": 0.04493083860200905, + "eval_acc": 0.818597113383227, + "eval_loss": 0.6184135675430298, + "eval_runtime": 195.2572, + "eval_samples_per_second": 6.443, + "eval_steps_per_second": 6.443, + "step": 350 + }, + { + "acc": 0.81946774, + "epoch": 0.04557270772489489, + "grad_norm": 0.185298889875412, + "learning_rate": 7.66515864363997e-05, + "loss": 0.63578596, + "memory(GiB)": 12.9, + "step": 355, + "train_speed(iter/s)": 0.078909 + }, + { + "acc": 0.82359991, + "epoch": 0.046214576847780735, + "grad_norm": 0.16975072026252747, + "learning_rate": 7.594847868906076e-05, + "loss": 0.59197049, + "memory(GiB)": 12.9, + "step": 360, + "train_speed(iter/s)": 0.079228 + }, + { + "acc": 0.82826347, + "epoch": 0.04685644597066658, + "grad_norm": 0.19332191348075867, + "learning_rate": 7.52382768867422e-05, + "loss": 0.58269887, + "memory(GiB)": 12.9, + "step": 365, + "train_speed(iter/s)": 0.079527 + }, + { + "acc": 0.81692057, + "epoch": 0.04749831509355242, + "grad_norm": 0.1801847517490387, + "learning_rate": 7.452117519152542e-05, + "loss": 0.62563605, + "memory(GiB)": 12.9, + "step": 370, + "train_speed(iter/s)": 0.079855 + }, + { + "acc": 0.81458244, + "epoch": 0.048140184216438266, + "grad_norm": 0.2671217620372772, + "learning_rate": 7.379736965185368e-05, + "loss": 0.62537222, + "memory(GiB)": 12.9, + "step": 375, + "train_speed(iter/s)": 0.080167 + }, + { + "acc": 0.80892944, + "epoch": 0.04878205333932411, + "grad_norm": 0.20377114415168762, + "learning_rate": 7.30670581489344e-05, + "loss": 0.6464529, + "memory(GiB)": 12.9, + "step": 380, + "train_speed(iter/s)": 0.080535 + }, + { + "acc": 0.81387253, + "epoch": 0.04942392246220995, + "grad_norm": 0.21851402521133423, + "learning_rate": 7.233044034264034e-05, + "loss": 0.64175944, + "memory(GiB)": 12.9, + "step": 385, + "train_speed(iter/s)": 0.080866 + }, + { + "acc": 0.81104851, + "epoch": 0.0500657915850958, + "grad_norm": 0.17920850217342377, + "learning_rate": 7.158771761692464e-05, + "loss": 0.65399485, + "memory(GiB)": 12.9, + "step": 390, + "train_speed(iter/s)": 0.081177 + }, + { + "acc": 0.81167917, + "epoch": 0.05070766070798164, + "grad_norm": 0.21850617229938507, + "learning_rate": 7.083909302476453e-05, + "loss": 0.65062542, + "memory(GiB)": 12.9, + "step": 395, + "train_speed(iter/s)": 0.081491 + }, + { + "acc": 0.82351618, + "epoch": 0.051349529830867484, + "grad_norm": 0.1936645656824112, + "learning_rate": 7.008477123264848e-05, + "loss": 0.62041502, + "memory(GiB)": 12.9, + "step": 400, + "train_speed(iter/s)": 0.081765 + }, + { + "epoch": 0.051349529830867484, + "eval_acc": 0.8192219173956314, + "eval_loss": 0.6147059202194214, + "eval_runtime": 194.2328, + "eval_samples_per_second": 6.477, + "eval_steps_per_second": 6.477, + "step": 400 + }, + { + "acc": 0.81023674, + "epoch": 0.05199139895375333, + "grad_norm": 0.1859249472618103, + "learning_rate": 6.932495846462261e-05, + "loss": 0.63979912, + "memory(GiB)": 12.9, + "step": 405, + "train_speed(iter/s)": 0.078921 + }, + { + "acc": 0.81422606, + "epoch": 0.05263326807663917, + "grad_norm": 0.18879809975624084, + "learning_rate": 6.855986244591104e-05, + "loss": 0.63082585, + "memory(GiB)": 12.9, + "step": 410, + "train_speed(iter/s)": 0.079225 + }, + { + "acc": 0.82355537, + "epoch": 0.053275137199525015, + "grad_norm": 0.1991114318370819, + "learning_rate": 6.778969234612584e-05, + "loss": 0.60244231, + "memory(GiB)": 12.9, + "step": 415, + "train_speed(iter/s)": 0.079522 + }, + { + "acc": 0.80394392, + "epoch": 0.05391700632241086, + "grad_norm": 0.18245312571525574, + "learning_rate": 6.701465872208216e-05, + "loss": 0.68041868, + "memory(GiB)": 12.9, + "step": 420, + "train_speed(iter/s)": 0.079822 + }, + { + "acc": 0.82535486, + "epoch": 0.0545588754452967, + "grad_norm": 0.18471555411815643, + "learning_rate": 6.623497346023418e-05, + "loss": 0.58148174, + "memory(GiB)": 12.9, + "step": 425, + "train_speed(iter/s)": 0.080165 + }, + { + "acc": 0.8145462, + "epoch": 0.055200744568182546, + "grad_norm": 0.21886418759822845, + "learning_rate": 6.545084971874738e-05, + "loss": 0.64324603, + "memory(GiB)": 12.9, + "step": 430, + "train_speed(iter/s)": 0.080479 + }, + { + "acc": 0.80875597, + "epoch": 0.05584261369106839, + "grad_norm": 0.2046084851026535, + "learning_rate": 6.466250186922325e-05, + "loss": 0.64245248, + "memory(GiB)": 12.9, + "step": 435, + "train_speed(iter/s)": 0.080772 + }, + { + "acc": 0.81591587, + "epoch": 0.05648448281395423, + "grad_norm": 0.1934758424758911, + "learning_rate": 6.387014543809223e-05, + "loss": 0.63060322, + "memory(GiB)": 12.9, + "step": 440, + "train_speed(iter/s)": 0.081046 + }, + { + "acc": 0.81191225, + "epoch": 0.05712635193684008, + "grad_norm": 0.2059066742658615, + "learning_rate": 6.307399704769099e-05, + "loss": 0.64218235, + "memory(GiB)": 12.9, + "step": 445, + "train_speed(iter/s)": 0.081334 + }, + { + "acc": 0.81284475, + "epoch": 0.05776822105972592, + "grad_norm": 0.18999861180782318, + "learning_rate": 6.227427435703997e-05, + "loss": 0.64007626, + "memory(GiB)": 12.9, + "step": 450, + "train_speed(iter/s)": 0.081619 + }, + { + "epoch": 0.05776822105972592, + "eval_acc": 0.8195972020245513, + "eval_loss": 0.6134685277938843, + "eval_runtime": 194.9348, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 450 + }, + { + "acc": 0.81439934, + "epoch": 0.058410090182611764, + "grad_norm": 0.20194242894649506, + "learning_rate": 6.147119600233758e-05, + "loss": 0.63169065, + "memory(GiB)": 12.9, + "step": 455, + "train_speed(iter/s)": 0.07909 + }, + { + "acc": 0.80925694, + "epoch": 0.05905195930549761, + "grad_norm": 0.22199371457099915, + "learning_rate": 6.066498153718735e-05, + "loss": 0.65331206, + "memory(GiB)": 12.9, + "step": 460, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.81743002, + "epoch": 0.05969382842838345, + "grad_norm": 0.1933964639902115, + "learning_rate": 5.985585137257401e-05, + "loss": 0.62136326, + "memory(GiB)": 12.9, + "step": 465, + "train_speed(iter/s)": 0.079664 + }, + { + "acc": 0.82081652, + "epoch": 0.060335697551269295, + "grad_norm": 0.19113869965076447, + "learning_rate": 5.90440267166055e-05, + "loss": 0.58844328, + "memory(GiB)": 12.9, + "step": 470, + "train_speed(iter/s)": 0.079903 + }, + { + "acc": 0.82189302, + "epoch": 0.06097756667415514, + "grad_norm": 0.21947172284126282, + "learning_rate": 5.8229729514036705e-05, + "loss": 0.6088398, + "memory(GiB)": 12.9, + "step": 475, + "train_speed(iter/s)": 0.080178 + }, + { + "acc": 0.81938705, + "epoch": 0.06161943579704098, + "grad_norm": 0.19398923218250275, + "learning_rate": 5.74131823855921e-05, + "loss": 0.62442837, + "memory(GiB)": 12.9, + "step": 480, + "train_speed(iter/s)": 0.080433 + }, + { + "acc": 0.82784338, + "epoch": 0.062261304919926826, + "grad_norm": 0.17412325739860535, + "learning_rate": 5.6594608567103456e-05, + "loss": 0.57895641, + "memory(GiB)": 12.9, + "step": 485, + "train_speed(iter/s)": 0.080668 + }, + { + "acc": 0.82182274, + "epoch": 0.06290317404281268, + "grad_norm": 0.2373647540807724, + "learning_rate": 5.577423184847932e-05, + "loss": 0.61787653, + "memory(GiB)": 12.9, + "step": 490, + "train_speed(iter/s)": 0.080927 + }, + { + "acc": 0.82861795, + "epoch": 0.06354504316569852, + "grad_norm": 0.18874205648899078, + "learning_rate": 5.495227651252315e-05, + "loss": 0.57188206, + "memory(GiB)": 12.9, + "step": 495, + "train_speed(iter/s)": 0.081151 + }, + { + "acc": 0.80789671, + "epoch": 0.06418691228858436, + "grad_norm": 0.1971614509820938, + "learning_rate": 5.4128967273616625e-05, + "loss": 0.67568989, + "memory(GiB)": 12.9, + "step": 500, + "train_speed(iter/s)": 0.081405 + }, + { + "epoch": 0.06418691228858436, + "eval_acc": 0.8191289863904123, + "eval_loss": 0.6154261827468872, + "eval_runtime": 194.8211, + "eval_samples_per_second": 6.457, + "eval_steps_per_second": 6.457, + "step": 500 + }, + { + "acc": 0.80737734, + "epoch": 0.06482878141147021, + "grad_norm": 0.2034166306257248, + "learning_rate": 5.330452921628497e-05, + "loss": 0.64408102, + "memory(GiB)": 12.9, + "step": 505, + "train_speed(iter/s)": 0.079157 + }, + { + "acc": 0.83580818, + "epoch": 0.06547065053435605, + "grad_norm": 0.1943274289369583, + "learning_rate": 5.247918773366112e-05, + "loss": 0.55616164, + "memory(GiB)": 12.9, + "step": 510, + "train_speed(iter/s)": 0.079418 + }, + { + "acc": 0.81569843, + "epoch": 0.0661125196572419, + "grad_norm": 0.21546119451522827, + "learning_rate": 5.165316846586541e-05, + "loss": 0.63107128, + "memory(GiB)": 12.9, + "step": 515, + "train_speed(iter/s)": 0.079676 + }, + { + "acc": 0.82521887, + "epoch": 0.06675438878012774, + "grad_norm": 0.18064647912979126, + "learning_rate": 5.0826697238317935e-05, + "loss": 0.60510926, + "memory(GiB)": 12.9, + "step": 520, + "train_speed(iter/s)": 0.079928 + }, + { + "acc": 0.8060174, + "epoch": 0.06739625790301358, + "grad_norm": 0.2181115299463272, + "learning_rate": 5e-05, + "loss": 0.65878468, + "memory(GiB)": 12.9, + "step": 525, + "train_speed(iter/s)": 0.080188 + }, + { + "acc": 0.81847181, + "epoch": 0.06803812702589943, + "grad_norm": 0.19227808713912964, + "learning_rate": 4.917330276168208e-05, + "loss": 0.61963496, + "memory(GiB)": 12.9, + "step": 530, + "train_speed(iter/s)": 0.080404 + }, + { + "acc": 0.81498117, + "epoch": 0.06867999614878527, + "grad_norm": 0.22034384310245514, + "learning_rate": 4.834683153413459e-05, + "loss": 0.6185873, + "memory(GiB)": 12.9, + "step": 535, + "train_speed(iter/s)": 0.080637 + }, + { + "acc": 0.80154915, + "epoch": 0.06932186527167111, + "grad_norm": 0.19249100983142853, + "learning_rate": 4.7520812266338885e-05, + "loss": 0.6963346, + "memory(GiB)": 12.9, + "step": 540, + "train_speed(iter/s)": 0.080856 + }, + { + "acc": 0.81683502, + "epoch": 0.06996373439455696, + "grad_norm": 0.1994090974330902, + "learning_rate": 4.669547078371504e-05, + "loss": 0.6188817, + "memory(GiB)": 12.9, + "step": 545, + "train_speed(iter/s)": 0.081075 + }, + { + "acc": 0.82736206, + "epoch": 0.0706056035174428, + "grad_norm": 0.18659113347530365, + "learning_rate": 4.5871032726383386e-05, + "loss": 0.59354177, + "memory(GiB)": 12.9, + "step": 550, + "train_speed(iter/s)": 0.081266 + }, + { + "epoch": 0.0706056035174428, + "eval_acc": 0.8192911509362449, + "eval_loss": 0.6139300465583801, + "eval_runtime": 200.9073, + "eval_samples_per_second": 6.262, + "eval_steps_per_second": 6.262, + "step": 550 + }, + { + "acc": 0.81306267, + "epoch": 0.07124747264032864, + "grad_norm": 0.17537347972393036, + "learning_rate": 4.504772348747687e-05, + "loss": 0.63172441, + "memory(GiB)": 12.9, + "step": 555, + "train_speed(iter/s)": 0.079145 + }, + { + "acc": 0.82534027, + "epoch": 0.07188934176321449, + "grad_norm": 0.21789848804473877, + "learning_rate": 4.4225768151520694e-05, + "loss": 0.58555121, + "memory(GiB)": 12.9, + "step": 560, + "train_speed(iter/s)": 0.079394 + }, + { + "acc": 0.82140818, + "epoch": 0.07253121088610033, + "grad_norm": 0.19700835645198822, + "learning_rate": 4.3405391432896555e-05, + "loss": 0.59516869, + "memory(GiB)": 12.9, + "step": 565, + "train_speed(iter/s)": 0.079597 + }, + { + "acc": 0.81845322, + "epoch": 0.07317308000898617, + "grad_norm": 0.1818612515926361, + "learning_rate": 4.2586817614407895e-05, + "loss": 0.60017176, + "memory(GiB)": 12.9, + "step": 570, + "train_speed(iter/s)": 0.079791 + }, + { + "acc": 0.82169409, + "epoch": 0.07381494913187202, + "grad_norm": 0.2091558277606964, + "learning_rate": 4.17702704859633e-05, + "loss": 0.59121842, + "memory(GiB)": 12.9, + "step": 575, + "train_speed(iter/s)": 0.080013 + }, + { + "acc": 0.81168118, + "epoch": 0.07445681825475786, + "grad_norm": 0.20149122178554535, + "learning_rate": 4.095597328339452e-05, + "loss": 0.64874387, + "memory(GiB)": 12.9, + "step": 580, + "train_speed(iter/s)": 0.080249 + }, + { + "acc": 0.82017975, + "epoch": 0.0750986873776437, + "grad_norm": 0.21395570039749146, + "learning_rate": 4.0144148627425993e-05, + "loss": 0.63141985, + "memory(GiB)": 12.9, + "step": 585, + "train_speed(iter/s)": 0.080445 + }, + { + "acc": 0.8225503, + "epoch": 0.07574055650052955, + "grad_norm": 0.21270450949668884, + "learning_rate": 3.933501846281267e-05, + "loss": 0.59338393, + "memory(GiB)": 12.9, + "step": 590, + "train_speed(iter/s)": 0.080661 + }, + { + "acc": 0.80733299, + "epoch": 0.07638242562341538, + "grad_norm": 0.21861939132213593, + "learning_rate": 3.852880399766243e-05, + "loss": 0.65440679, + "memory(GiB)": 12.9, + "step": 595, + "train_speed(iter/s)": 0.080898 + }, + { + "acc": 0.81755505, + "epoch": 0.07702429474630122, + "grad_norm": 0.1930130422115326, + "learning_rate": 3.772572564296005e-05, + "loss": 0.61422372, + "memory(GiB)": 12.9, + "step": 600, + "train_speed(iter/s)": 0.081091 + }, + { + "epoch": 0.07702429474630122, + "eval_acc": 0.8198276458076612, + "eval_loss": 0.6109773516654968, + "eval_runtime": 195.2232, + "eval_samples_per_second": 6.444, + "eval_steps_per_second": 6.444, + "step": 600 + }, + { + "acc": 0.82081652, + "epoch": 0.07766616386918707, + "grad_norm": 0.20753733813762665, + "learning_rate": 3.6926002952309016e-05, + "loss": 0.6057888, + "memory(GiB)": 12.9, + "step": 605, + "train_speed(iter/s)": 0.07921 + }, + { + "acc": 0.82343655, + "epoch": 0.07830803299207291, + "grad_norm": 0.1979513019323349, + "learning_rate": 3.612985456190778e-05, + "loss": 0.61725841, + "memory(GiB)": 12.9, + "step": 610, + "train_speed(iter/s)": 0.079401 + }, + { + "acc": 0.81410999, + "epoch": 0.07894990211495875, + "grad_norm": 0.20070388913154602, + "learning_rate": 3.533749813077677e-05, + "loss": 0.62781944, + "memory(GiB)": 12.9, + "step": 615, + "train_speed(iter/s)": 0.079569 + }, + { + "acc": 0.81817207, + "epoch": 0.0795917712378446, + "grad_norm": 0.2327299267053604, + "learning_rate": 3.4549150281252636e-05, + "loss": 0.62505813, + "memory(GiB)": 12.9, + "step": 620, + "train_speed(iter/s)": 0.079788 + }, + { + "acc": 0.82294455, + "epoch": 0.08023364036073044, + "grad_norm": 0.18113943934440613, + "learning_rate": 3.3765026539765834e-05, + "loss": 0.60028605, + "memory(GiB)": 12.9, + "step": 625, + "train_speed(iter/s)": 0.079975 + }, + { + "acc": 0.82047234, + "epoch": 0.08087550948361628, + "grad_norm": 0.20408566296100616, + "learning_rate": 3.298534127791785e-05, + "loss": 0.61079011, + "memory(GiB)": 12.9, + "step": 630, + "train_speed(iter/s)": 0.080162 + }, + { + "acc": 0.82677517, + "epoch": 0.08151737860650213, + "grad_norm": 0.2132798135280609, + "learning_rate": 3.221030765387417e-05, + "loss": 0.57911015, + "memory(GiB)": 12.9, + "step": 635, + "train_speed(iter/s)": 0.08036 + }, + { + "acc": 0.81979742, + "epoch": 0.08215924772938797, + "grad_norm": 0.20325441658496857, + "learning_rate": 3.144013755408895e-05, + "loss": 0.60286283, + "memory(GiB)": 12.9, + "step": 640, + "train_speed(iter/s)": 0.080558 + }, + { + "acc": 0.83071327, + "epoch": 0.08280111685227382, + "grad_norm": 0.20148617029190063, + "learning_rate": 3.0675041535377405e-05, + "loss": 0.58266845, + "memory(GiB)": 12.9, + "step": 645, + "train_speed(iter/s)": 0.080764 + }, + { + "acc": 0.83186378, + "epoch": 0.08344298597515966, + "grad_norm": 0.19807127118110657, + "learning_rate": 2.991522876735154e-05, + "loss": 0.55458455, + "memory(GiB)": 12.9, + "step": 650, + "train_speed(iter/s)": 0.080948 + }, + { + "epoch": 0.08344298597515966, + "eval_acc": 0.8209896385738762, + "eval_loss": 0.6076882481575012, + "eval_runtime": 194.4544, + "eval_samples_per_second": 6.469, + "eval_steps_per_second": 6.469, + "step": 650 + }, + { + "acc": 0.82214499, + "epoch": 0.0840848550980455, + "grad_norm": 0.18806923925876617, + "learning_rate": 2.916090697523549e-05, + "loss": 0.61260557, + "memory(GiB)": 12.9, + "step": 655, + "train_speed(iter/s)": 0.079195 + }, + { + "acc": 0.82406235, + "epoch": 0.08472672422093135, + "grad_norm": 0.19712701439857483, + "learning_rate": 2.8412282383075363e-05, + "loss": 0.59967513, + "memory(GiB)": 12.9, + "step": 660, + "train_speed(iter/s)": 0.079403 + }, + { + "acc": 0.80978308, + "epoch": 0.08536859334381719, + "grad_norm": 0.19845040142536163, + "learning_rate": 2.766955965735968e-05, + "loss": 0.64144659, + "memory(GiB)": 12.9, + "step": 665, + "train_speed(iter/s)": 0.079587 + }, + { + "acc": 0.81445723, + "epoch": 0.08601046246670303, + "grad_norm": 0.21892952919006348, + "learning_rate": 2.693294185106562e-05, + "loss": 0.62947636, + "memory(GiB)": 12.9, + "step": 670, + "train_speed(iter/s)": 0.079776 + }, + { + "acc": 0.82742786, + "epoch": 0.08665233158958888, + "grad_norm": 0.21680107712745667, + "learning_rate": 2.6202630348146324e-05, + "loss": 0.58508019, + "memory(GiB)": 12.9, + "step": 675, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.82206249, + "epoch": 0.08729420071247472, + "grad_norm": 0.19368013739585876, + "learning_rate": 2.547882480847461e-05, + "loss": 0.60457458, + "memory(GiB)": 12.9, + "step": 680, + "train_speed(iter/s)": 0.080131 + }, + { + "acc": 0.8187645, + "epoch": 0.08793606983536056, + "grad_norm": 0.21237029135227203, + "learning_rate": 2.476172311325783e-05, + "loss": 0.61911306, + "memory(GiB)": 12.9, + "step": 685, + "train_speed(iter/s)": 0.080301 + }, + { + "acc": 0.81704865, + "epoch": 0.08857793895824641, + "grad_norm": 0.22553302347660065, + "learning_rate": 2.405152131093926e-05, + "loss": 0.63167734, + "memory(GiB)": 12.9, + "step": 690, + "train_speed(iter/s)": 0.080481 + }, + { + "acc": 0.81163187, + "epoch": 0.08921980808113225, + "grad_norm": 0.21230626106262207, + "learning_rate": 2.3348413563600325e-05, + "loss": 0.63321238, + "memory(GiB)": 12.9, + "step": 695, + "train_speed(iter/s)": 0.080651 + }, + { + "acc": 0.81947212, + "epoch": 0.0898616772040181, + "grad_norm": 0.23210006952285767, + "learning_rate": 2.2652592093878666e-05, + "loss": 0.61235924, + "memory(GiB)": 12.9, + "step": 700, + "train_speed(iter/s)": 0.08085 + }, + { + "epoch": 0.0898616772040181, + "eval_acc": 0.8203855599214145, + "eval_loss": 0.6076461672782898, + "eval_runtime": 194.4087, + "eval_samples_per_second": 6.471, + "eval_steps_per_second": 6.471, + "step": 700 + }, + { + "acc": 0.81527042, + "epoch": 0.09050354632690394, + "grad_norm": 0.20815226435661316, + "learning_rate": 2.196424713241637e-05, + "loss": 0.63990374, + "memory(GiB)": 12.9, + "step": 705, + "train_speed(iter/s)": 0.079227 + }, + { + "acc": 0.82444172, + "epoch": 0.09114541544978978, + "grad_norm": 0.21324452757835388, + "learning_rate": 2.128356686585282e-05, + "loss": 0.59049015, + "memory(GiB)": 12.9, + "step": 710, + "train_speed(iter/s)": 0.079404 + }, + { + "acc": 0.81617746, + "epoch": 0.09178728457267563, + "grad_norm": 0.19047819077968597, + "learning_rate": 2.061073738537635e-05, + "loss": 0.60989962, + "memory(GiB)": 12.9, + "step": 715, + "train_speed(iter/s)": 0.079576 + }, + { + "acc": 0.80728264, + "epoch": 0.09242915369556147, + "grad_norm": 0.2062956988811493, + "learning_rate": 1.9945942635848748e-05, + "loss": 0.67080445, + "memory(GiB)": 12.9, + "step": 720, + "train_speed(iter/s)": 0.079742 + }, + { + "acc": 0.81671677, + "epoch": 0.09307102281844731, + "grad_norm": 0.19861043989658356, + "learning_rate": 1.928936436551661e-05, + "loss": 0.61908646, + "memory(GiB)": 12.9, + "step": 725, + "train_speed(iter/s)": 0.079905 + }, + { + "acc": 0.81090012, + "epoch": 0.09371289194133316, + "grad_norm": 0.19133475422859192, + "learning_rate": 1.8641182076323148e-05, + "loss": 0.66370716, + "memory(GiB)": 12.9, + "step": 730, + "train_speed(iter/s)": 0.08006 + }, + { + "acc": 0.81192856, + "epoch": 0.094354761064219, + "grad_norm": 0.22429423034191132, + "learning_rate": 1.800157297483417e-05, + "loss": 0.66476107, + "memory(GiB)": 12.9, + "step": 735, + "train_speed(iter/s)": 0.080239 + }, + { + "acc": 0.82513466, + "epoch": 0.09499663018710484, + "grad_norm": 0.21653637290000916, + "learning_rate": 1.7370711923791567e-05, + "loss": 0.58692684, + "memory(GiB)": 12.9, + "step": 740, + "train_speed(iter/s)": 0.080402 + }, + { + "acc": 0.82555256, + "epoch": 0.09563849930999069, + "grad_norm": 0.17780368030071259, + "learning_rate": 1.6748771394307585e-05, + "loss": 0.57462683, + "memory(GiB)": 12.9, + "step": 745, + "train_speed(iter/s)": 0.080553 + }, + { + "acc": 0.81813164, + "epoch": 0.09628036843287653, + "grad_norm": 0.2015465795993805, + "learning_rate": 1.6135921418712956e-05, + "loss": 0.61962047, + "memory(GiB)": 12.9, + "step": 750, + "train_speed(iter/s)": 0.080707 + }, + { + "epoch": 0.09628036843287653, + "eval_acc": 0.8204207990619473, + "eval_loss": 0.6083427667617798, + "eval_runtime": 194.7163, + "eval_samples_per_second": 6.461, + "eval_steps_per_second": 6.461, + "step": 750 + }, + { + "acc": 0.82061501, + "epoch": 0.09692223755576237, + "grad_norm": 0.2477208524942398, + "learning_rate": 1.553232954407171e-05, + "loss": 0.61750922, + "memory(GiB)": 12.9, + "step": 755, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81846237, + "epoch": 0.09756410667864822, + "grad_norm": 0.22278401255607605, + "learning_rate": 1.4938160786375572e-05, + "loss": 0.61280818, + "memory(GiB)": 12.9, + "step": 760, + "train_speed(iter/s)": 0.079391 + }, + { + "acc": 0.81434851, + "epoch": 0.09820597580153406, + "grad_norm": 0.22640761733055115, + "learning_rate": 1.435357758543015e-05, + "loss": 0.63006077, + "memory(GiB)": 12.9, + "step": 765, + "train_speed(iter/s)": 0.079552 + }, + { + "acc": 0.81086941, + "epoch": 0.0988478449244199, + "grad_norm": 0.20250476896762848, + "learning_rate": 1.3778739760445552e-05, + "loss": 0.63865561, + "memory(GiB)": 12.9, + "step": 770, + "train_speed(iter/s)": 0.079713 + }, + { + "acc": 0.81333466, + "epoch": 0.09948971404730575, + "grad_norm": 0.21983562409877777, + "learning_rate": 1.3213804466343421e-05, + "loss": 0.63764729, + "memory(GiB)": 12.9, + "step": 775, + "train_speed(iter/s)": 0.079857 + }, + { + "acc": 0.81033506, + "epoch": 0.1001315831701916, + "grad_norm": 0.21427662670612335, + "learning_rate": 1.2658926150792322e-05, + "loss": 0.62097745, + "memory(GiB)": 12.9, + "step": 780, + "train_speed(iter/s)": 0.080004 + }, + { + "acc": 0.82130699, + "epoch": 0.10077345229307744, + "grad_norm": 0.20593635737895966, + "learning_rate": 1.2114256511983274e-05, + "loss": 0.60655851, + "memory(GiB)": 12.9, + "step": 785, + "train_speed(iter/s)": 0.080173 + }, + { + "acc": 0.82261295, + "epoch": 0.10141532141596328, + "grad_norm": 0.2052464336156845, + "learning_rate": 1.157994445715706e-05, + "loss": 0.61125717, + "memory(GiB)": 12.9, + "step": 790, + "train_speed(iter/s)": 0.080342 + }, + { + "acc": 0.82531328, + "epoch": 0.10205719053884912, + "grad_norm": 0.17600791156291962, + "learning_rate": 1.1056136061894384e-05, + "loss": 0.59510598, + "memory(GiB)": 12.9, + "step": 795, + "train_speed(iter/s)": 0.08049 + }, + { + "acc": 0.81779881, + "epoch": 0.10269905966173497, + "grad_norm": 0.2141779363155365, + "learning_rate": 1.0542974530180327e-05, + "loss": 0.63478656, + "memory(GiB)": 12.9, + "step": 800, + "train_speed(iter/s)": 0.080624 + }, + { + "epoch": 0.10269905966173497, + "eval_acc": 0.8207697400203976, + "eval_loss": 0.6077002882957458, + "eval_runtime": 194.8773, + "eval_samples_per_second": 6.455, + "eval_steps_per_second": 6.455, + "step": 800 + }, + { + "acc": 0.80902939, + "epoch": 0.10334092878462081, + "grad_norm": 0.2090810388326645, + "learning_rate": 1.0040600155253765e-05, + "loss": 0.66100531, + "memory(GiB)": 12.9, + "step": 805, + "train_speed(iter/s)": 0.079226 + }, + { + "acc": 0.81437035, + "epoch": 0.10398279790750665, + "grad_norm": 0.22697587311267853, + "learning_rate": 9.549150281252633e-06, + "loss": 0.63930345, + "memory(GiB)": 12.9, + "step": 810, + "train_speed(iter/s)": 0.079387 + }, + { + "acc": 0.81263914, + "epoch": 0.1046246670303925, + "grad_norm": 0.21495579183101654, + "learning_rate": 9.068759265665384e-06, + "loss": 0.63128233, + "memory(GiB)": 12.9, + "step": 815, + "train_speed(iter/s)": 0.079538 + }, + { + "acc": 0.80606184, + "epoch": 0.10526653615327834, + "grad_norm": 0.24026648700237274, + "learning_rate": 8.599558442598998e-06, + "loss": 0.66762576, + "memory(GiB)": 12.9, + "step": 820, + "train_speed(iter/s)": 0.07969 + }, + { + "acc": 0.83144102, + "epoch": 0.10590840527616419, + "grad_norm": 0.2179374396800995, + "learning_rate": 8.141676086873572e-06, + "loss": 0.56980219, + "memory(GiB)": 12.9, + "step": 825, + "train_speed(iter/s)": 0.079849 + }, + { + "acc": 0.81910725, + "epoch": 0.10655027439905003, + "grad_norm": 0.19496454298496246, + "learning_rate": 7.695237378953223e-06, + "loss": 0.61694736, + "memory(GiB)": 12.9, + "step": 830, + "train_speed(iter/s)": 0.07997 + }, + { + "acc": 0.81330662, + "epoch": 0.10719214352193587, + "grad_norm": 0.23187701404094696, + "learning_rate": 7.260364370723044e-06, + "loss": 0.64870877, + "memory(GiB)": 12.9, + "step": 835, + "train_speed(iter/s)": 0.080126 + }, + { + "acc": 0.81870842, + "epoch": 0.10783401264482172, + "grad_norm": 0.20400239527225494, + "learning_rate": 6.837175952121306e-06, + "loss": 0.61115222, + "memory(GiB)": 12.9, + "step": 840, + "train_speed(iter/s)": 0.080258 + }, + { + "acc": 0.82128296, + "epoch": 0.10847588176770756, + "grad_norm": 0.24608130753040314, + "learning_rate": 6.425787818636131e-06, + "loss": 0.61838484, + "memory(GiB)": 12.9, + "step": 845, + "train_speed(iter/s)": 0.080422 + }, + { + "acc": 0.8118104, + "epoch": 0.1091177508905934, + "grad_norm": 0.21192343533039093, + "learning_rate": 6.026312439675552e-06, + "loss": 0.67037339, + "memory(GiB)": 12.9, + "step": 850, + "train_speed(iter/s)": 0.080553 + }, + { + "epoch": 0.1091177508905934, + "eval_acc": 0.8208858520874116, + "eval_loss": 0.606462836265564, + "eval_runtime": 194.9575, + "eval_samples_per_second": 6.453, + "eval_steps_per_second": 6.453, + "step": 850 + }, + { + "acc": 0.81058187, + "epoch": 0.10975962001347925, + "grad_norm": 0.2256067544221878, + "learning_rate": 5.6388590278194096e-06, + "loss": 0.63853312, + "memory(GiB)": 12.9, + "step": 855, + "train_speed(iter/s)": 0.079236 + }, + { + "acc": 0.8174571, + "epoch": 0.11040148913636509, + "grad_norm": 0.21500875055789948, + "learning_rate": 5.263533508961827e-06, + "loss": 0.6172534, + "memory(GiB)": 12.9, + "step": 860, + "train_speed(iter/s)": 0.079369 + }, + { + "acc": 0.8093504, + "epoch": 0.11104335825925093, + "grad_norm": 0.23700734972953796, + "learning_rate": 4.900438493352055e-06, + "loss": 0.65724411, + "memory(GiB)": 12.9, + "step": 865, + "train_speed(iter/s)": 0.07952 + }, + { + "acc": 0.81735506, + "epoch": 0.11168522738213678, + "grad_norm": 0.21098878979682922, + "learning_rate": 4.549673247541875e-06, + "loss": 0.61837373, + "memory(GiB)": 12.9, + "step": 870, + "train_speed(iter/s)": 0.079659 + }, + { + "acc": 0.81503067, + "epoch": 0.11232709650502262, + "grad_norm": 0.20609669387340546, + "learning_rate": 4.2113336672471245e-06, + "loss": 0.61365747, + "memory(GiB)": 12.9, + "step": 875, + "train_speed(iter/s)": 0.079794 + }, + { + "acc": 0.80629053, + "epoch": 0.11296896562790847, + "grad_norm": 0.2180800437927246, + "learning_rate": 3.885512251130763e-06, + "loss": 0.66433964, + "memory(GiB)": 12.9, + "step": 880, + "train_speed(iter/s)": 0.079933 + }, + { + "acc": 0.82552185, + "epoch": 0.11361083475079431, + "grad_norm": 0.2074093371629715, + "learning_rate": 3.5722980755146517e-06, + "loss": 0.5967988, + "memory(GiB)": 12.9, + "step": 885, + "train_speed(iter/s)": 0.080078 + }, + { + "acc": 0.81032143, + "epoch": 0.11425270387368015, + "grad_norm": 0.232750803232193, + "learning_rate": 3.271776770026963e-06, + "loss": 0.66238441, + "memory(GiB)": 12.9, + "step": 890, + "train_speed(iter/s)": 0.080218 + }, + { + "acc": 0.8156251, + "epoch": 0.114894572996566, + "grad_norm": 0.24590888619422913, + "learning_rate": 2.9840304941919415e-06, + "loss": 0.6185041, + "memory(GiB)": 12.9, + "step": 895, + "train_speed(iter/s)": 0.080356 + }, + { + "acc": 0.81570625, + "epoch": 0.11553644211945184, + "grad_norm": 0.2058228850364685, + "learning_rate": 2.7091379149682685e-06, + "loss": 0.61333613, + "memory(GiB)": 12.9, + "step": 900, + "train_speed(iter/s)": 0.080474 + }, + { + "epoch": 0.11553644211945184, + "eval_acc": 0.8202886005724797, + "eval_loss": 0.6085067391395569, + "eval_runtime": 194.5686, + "eval_samples_per_second": 6.466, + "eval_steps_per_second": 6.466, + "step": 900 + }, + { + "acc": 0.81097269, + "epoch": 0.11617831124233768, + "grad_norm": 0.23131993412971497, + "learning_rate": 2.4471741852423237e-06, + "loss": 0.64109416, + "memory(GiB)": 12.9, + "step": 905, + "train_speed(iter/s)": 0.079218 + }, + { + "acc": 0.82361622, + "epoch": 0.11682018036522353, + "grad_norm": 0.18522906303405762, + "learning_rate": 2.1982109232821178e-06, + "loss": 0.59271107, + "memory(GiB)": 12.9, + "step": 910, + "train_speed(iter/s)": 0.079368 + }, + { + "acc": 0.81258793, + "epoch": 0.11746204948810937, + "grad_norm": 0.21756961941719055, + "learning_rate": 1.962316193157593e-06, + "loss": 0.65264983, + "memory(GiB)": 12.9, + "step": 915, + "train_speed(iter/s)": 0.07951 + }, + { + "acc": 0.82611704, + "epoch": 0.11810391861099521, + "grad_norm": 0.20278231799602509, + "learning_rate": 1.7395544861325718e-06, + "loss": 0.59875569, + "memory(GiB)": 12.9, + "step": 920, + "train_speed(iter/s)": 0.079655 + }, + { + "acc": 0.82435198, + "epoch": 0.11874578773388106, + "grad_norm": 0.21583449840545654, + "learning_rate": 1.5299867030334814e-06, + "loss": 0.62275109, + "memory(GiB)": 12.9, + "step": 925, + "train_speed(iter/s)": 0.079795 + }, + { + "acc": 0.81717892, + "epoch": 0.1193876568567669, + "grad_norm": 0.22039002180099487, + "learning_rate": 1.333670137599713e-06, + "loss": 0.61020494, + "memory(GiB)": 12.9, + "step": 930, + "train_speed(iter/s)": 0.079939 + }, + { + "acc": 0.80936031, + "epoch": 0.12002952597965275, + "grad_norm": 0.21585673093795776, + "learning_rate": 1.1506584608200367e-06, + "loss": 0.63481708, + "memory(GiB)": 12.9, + "step": 935, + "train_speed(iter/s)": 0.080073 + }, + { + "acc": 0.81828098, + "epoch": 0.12067139510253859, + "grad_norm": 0.22403886914253235, + "learning_rate": 9.810017062595322e-07, + "loss": 0.62871428, + "memory(GiB)": 12.9, + "step": 940, + "train_speed(iter/s)": 0.080211 + }, + { + "acc": 0.82708139, + "epoch": 0.12131326422542443, + "grad_norm": 0.22789925336837769, + "learning_rate": 8.247462563808817e-07, + "loss": 0.59829245, + "memory(GiB)": 12.9, + "step": 945, + "train_speed(iter/s)": 0.080336 + }, + { + "acc": 0.81116629, + "epoch": 0.12195513334831028, + "grad_norm": 0.22641904652118683, + "learning_rate": 6.819348298638839e-07, + "loss": 0.629322, + "memory(GiB)": 12.9, + "step": 950, + "train_speed(iter/s)": 0.080481 + }, + { + "epoch": 0.12195513334831028, + "eval_acc": 0.8201861908583086, + "eval_loss": 0.6082066297531128, + "eval_runtime": 194.2718, + "eval_samples_per_second": 6.475, + "eval_steps_per_second": 6.475, + "step": 950 + } + ], + "logging_steps": 5, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.6616878267387494e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/training_args.bin b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e400a8cc8b644698616136972639fca9fe57363 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-950/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ca841f7bd4a855ee575421abc61a664c4a5bac12d5a654d3adfe5e4f1cc45d +size 7480 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/eval_acc.png b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_acc.png new file mode 100644 index 0000000000000000000000000000000000000000..564737e3a07290ffc27180c65566caa4a5cc5743 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_acc.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/eval_loss.png b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..3c1f4c05ef653669508c73b6619ef099bde4486c Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_loss.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/eval_runtime.png b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_runtime.png new file mode 100644 index 0000000000000000000000000000000000000000..21ab04c5a84e2997afe566d34271be7028aee400 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_runtime.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/eval_samples_per_second.png b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_samples_per_second.png new file mode 100644 index 0000000000000000000000000000000000000000..522b553184496166c31eb54a43a31030d4d6dd7c Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_samples_per_second.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/eval_steps_per_second.png b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_steps_per_second.png new file mode 100644 index 0000000000000000000000000000000000000000..4a16d54c536a71c343acfd4f2aac8c13e2ac7803 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/eval_steps_per_second.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_acc.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_acc.png new file mode 100644 index 0000000000000000000000000000000000000000..7c0421372dd8460d99b4b29899403c2ce258d776 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_acc.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_epoch.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_epoch.png new file mode 100644 index 0000000000000000000000000000000000000000..7afb3c878e02ee2c02595f2c6789f3d4daabdb7c Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_epoch.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_grad_norm.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_grad_norm.png new file mode 100644 index 0000000000000000000000000000000000000000..754292ee1dc23fa2a8a6acaca58f2b1c448c5d8e Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_grad_norm.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_learning_rate.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_learning_rate.png new file mode 100644 index 0000000000000000000000000000000000000000..bbf29ac21c68a008b15b1dfb1562202029fecc29 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_learning_rate.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_loss.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..019cfaa8d44540f07454fb91b3503020e6accf55 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_loss.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_memory(GiB).png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_memory(GiB).png new file mode 100644 index 0000000000000000000000000000000000000000..508329e46895933a17381f49b6055211390adc18 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_memory(GiB).png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_total_flos.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_total_flos.png new file mode 100644 index 0000000000000000000000000000000000000000..a4d3af0669b0798ee01f6894153e0e07c1d4ecfd Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_total_flos.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_loss.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..a366947ba7be3adc3618b4140e0fb0a0815dba69 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_loss.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_runtime.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_runtime.png new file mode 100644 index 0000000000000000000000000000000000000000..7298dfabcd43ad06ef20a23ebe3c71347d52d48b Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_runtime.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_samples_per_second.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_samples_per_second.png new file mode 100644 index 0000000000000000000000000000000000000000..c1f2b294251114c7d280afe32809ed6390a6fa48 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_samples_per_second.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_speed(iter_s).png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_speed(iter_s).png new file mode 100644 index 0000000000000000000000000000000000000000..a8f6015c30bdb5af6e56781417c633fb5ff76316 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_speed(iter_s).png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_steps_per_second.png b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_steps_per_second.png new file mode 100644 index 0000000000000000000000000000000000000000..6129117180d51d69d5a650eaaa8d28b731f076c7 Binary files /dev/null and b/phi3_5-vision-instruct/v6-20241130-010713/images/train_train_steps_per_second.png differ diff --git a/phi3_5-vision-instruct/v6-20241130-010713/logging.jsonl b/phi3_5-vision-instruct/v6-20241130-010713/logging.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a108b6b45fb866f8bfb73de32bed99cd4688d565 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/logging.jsonl @@ -0,0 +1,223 @@ +{"loss": 0.82634771, "acc": 0.77952504, "grad_norm": 0.15511861, "learning_rate": 2e-06, "memory(GiB)": 11.42, "train_speed(iter/s)": 0.092016, "epoch": 0.00012837, "global_step/max_steps": "1/1000", "percentage": "0.10%", "elapsed_time": "10s", "remaining_time": "2h 55m 20s"} +{"loss": 0.8159712, "acc": 0.77674872, "grad_norm": 0.14591481, "learning_rate": 1e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.10552, "epoch": 0.00064187, "global_step/max_steps": "5/1000", "percentage": "0.50%", "elapsed_time": "47s", "remaining_time": "2h 36m 2s"} +{"loss": 0.8015564, "acc": 0.77379012, "grad_norm": 0.15185016, "learning_rate": 2e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.107013, "epoch": 0.00128374, "global_step/max_steps": "10/1000", "percentage": "1.00%", "elapsed_time": "1m 33s", "remaining_time": "2h 33m 37s"} +{"loss": 0.79284344, "acc": 0.7784133, "grad_norm": 0.15997683, "learning_rate": 3e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.110995, "epoch": 0.00192561, "global_step/max_steps": "15/1000", "percentage": "1.50%", "elapsed_time": "2m 14s", "remaining_time": "2h 27m 32s"} +{"loss": 0.78122258, "acc": 0.7815052, "grad_norm": 0.14427674, "learning_rate": 4e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.111462, "epoch": 0.00256748, "global_step/max_steps": "20/1000", "percentage": "2.00%", "elapsed_time": "2m 59s", "remaining_time": "2h 26m 15s"} +{"loss": 0.7404335, "acc": 0.7915082, "grad_norm": 0.15902227, "learning_rate": 5e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.112268, "epoch": 0.00320935, "global_step/max_steps": "25/1000", "percentage": "2.50%", "elapsed_time": "3m 42s", "remaining_time": "2h 24m 31s"} +{"loss": 0.68063788, "acc": 0.80291214, "grad_norm": 0.13638993, "learning_rate": 6e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.111517, "epoch": 0.00385121, "global_step/max_steps": "30/1000", "percentage": "3.00%", "elapsed_time": "4m 28s", "remaining_time": "2h 24m 47s"} +{"loss": 0.68800621, "acc": 0.79923964, "grad_norm": 0.12712458, "learning_rate": 7e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.110574, "epoch": 0.00449308, "global_step/max_steps": "35/1000", "percentage": "3.50%", "elapsed_time": "5m 16s", "remaining_time": "2h 25m 17s"} +{"loss": 0.69939818, "acc": 0.80240812, "grad_norm": 0.11937133, "learning_rate": 8e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.109469, "epoch": 0.00513495, "global_step/max_steps": "40/1000", "percentage": "4.00%", "elapsed_time": "6m 5s", "remaining_time": "2h 26m 1s"} +{"loss": 0.75735736, "acc": 0.78317132, "grad_norm": 0.16653585, "learning_rate": 9e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.108968, "epoch": 0.00577682, "global_step/max_steps": "45/1000", "percentage": "4.50%", "elapsed_time": "6m 52s", "remaining_time": "2h 25m 56s"} +{"loss": 0.6824338, "acc": 0.80379133, "grad_norm": 0.14883441, "learning_rate": 0.0001, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.109163, "epoch": 0.00641869, "global_step/max_steps": "50/1000", "percentage": "5.00%", "elapsed_time": "7m 37s", "remaining_time": "2h 24m 56s"} +{"eval_loss": 0.67293125, "eval_acc": 0.80813466, "eval_runtime": 195.4613, "eval_samples_per_second": 6.436, "eval_steps_per_second": 6.436, "epoch": 0.00641869, "global_step/max_steps": "50/1000", "percentage": "5.00%", "elapsed_time": "10m 53s", "remaining_time": "3h 26m 50s"} +{"loss": 0.7141089, "acc": 0.7984889, "grad_norm": 0.16687535, "learning_rate": 9.999e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078646, "epoch": 0.00706056, "global_step/max_steps": "55/1000", "percentage": "5.50%", "elapsed_time": "11m 38s", "remaining_time": "3h 20m 10s"} +{"loss": 0.72419305, "acc": 0.79216175, "grad_norm": 0.17546052, "learning_rate": 9.997e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080466, "epoch": 0.00770243, "global_step/max_steps": "60/1000", "percentage": "6.00%", "elapsed_time": "12m 25s", "remaining_time": "3h 14m 36s"} +{"loss": 0.67717872, "acc": 0.80358973, "grad_norm": 0.16079305, "learning_rate": 9.994e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082252, "epoch": 0.0083443, "global_step/max_steps": "65/1000", "percentage": "6.50%", "elapsed_time": "13m 9s", "remaining_time": "3h 9m 22s"} +{"loss": 0.70638905, "acc": 0.80615339, "grad_norm": 0.13962349, "learning_rate": 9.989e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084, "epoch": 0.00898617, "global_step/max_steps": "70/1000", "percentage": "7.00%", "elapsed_time": "13m 52s", "remaining_time": "3h 4m 26s"} +{"loss": 0.71420946, "acc": 0.79676814, "grad_norm": 0.13404626, "learning_rate": 9.983e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08542, "epoch": 0.00962804, "global_step/max_steps": "75/1000", "percentage": "7.50%", "elapsed_time": "14m 37s", "remaining_time": "3h 0m 24s"} +{"loss": 0.71777782, "acc": 0.79325166, "grad_norm": 0.13259001, "learning_rate": 9.975e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.086655, "epoch": 0.01026991, "global_step/max_steps": "80/1000", "percentage": "8.00%", "elapsed_time": "15m 22s", "remaining_time": "2h 56m 52s"} +{"loss": 0.62526927, "acc": 0.81705523, "grad_norm": 0.15833652, "learning_rate": 9.967e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.088014, "epoch": 0.01091178, "global_step/max_steps": "85/1000", "percentage": "8.50%", "elapsed_time": "16m 5s", "remaining_time": "2h 53m 12s"} +{"loss": 0.68010745, "acc": 0.80851898, "grad_norm": 0.14563304, "learning_rate": 9.956e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.088941, "epoch": 0.01155364, "global_step/max_steps": "90/1000", "percentage": "9.00%", "elapsed_time": "16m 51s", "remaining_time": "2h 50m 28s"} +{"loss": 0.6090106, "acc": 0.81903477, "grad_norm": 0.14285946, "learning_rate": 9.945e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.089902, "epoch": 0.01219551, "global_step/max_steps": "95/1000", "percentage": "9.50%", "elapsed_time": "17m 36s", "remaining_time": "2h 47m 43s"} +{"loss": 0.59807158, "acc": 0.82483721, "grad_norm": 0.1478744, "learning_rate": 9.932e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.090663, "epoch": 0.01283738, "global_step/max_steps": "100/1000", "percentage": "10.00%", "elapsed_time": "18m 22s", "remaining_time": "2h 45m 23s"} +{"eval_loss": 0.64535284, "eval_acc": 0.81376851, "eval_runtime": 195.755, "eval_samples_per_second": 6.426, "eval_steps_per_second": 6.426, "epoch": 0.01283738, "global_step/max_steps": "100/1000", "percentage": "10.00%", "elapsed_time": "21m 38s", "remaining_time": "3h 14m 45s"} +{"loss": 0.66537051, "acc": 0.80671978, "grad_norm": 0.15444878, "learning_rate": 9.918e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078062, "epoch": 0.01347925, "global_step/max_steps": "105/1000", "percentage": "10.50%", "elapsed_time": "22m 24s", "remaining_time": "3h 11m 2s"} +{"loss": 0.60835891, "acc": 0.81962786, "grad_norm": 0.16826579, "learning_rate": 9.902e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079089, "epoch": 0.01412112, "global_step/max_steps": "110/1000", "percentage": "11.00%", "elapsed_time": "23m 10s", "remaining_time": "3h 7m 30s"} +{"loss": 0.66763787, "acc": 0.80644588, "grad_norm": 0.15195911, "learning_rate": 9.885e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08012, "epoch": 0.01476299, "global_step/max_steps": "115/1000", "percentage": "11.50%", "elapsed_time": "23m 55s", "remaining_time": "3h 4m 3s"} +{"loss": 0.5919826, "acc": 0.8235981, "grad_norm": 0.20040031, "learning_rate": 9.867e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081125, "epoch": 0.01540486, "global_step/max_steps": "120/1000", "percentage": "12.00%", "elapsed_time": "24m 38s", "remaining_time": "3h 0m 45s"} +{"loss": 0.63266978, "acc": 0.81199884, "grad_norm": 0.18427384, "learning_rate": 9.847e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082093, "epoch": 0.01604673, "global_step/max_steps": "125/1000", "percentage": "12.50%", "elapsed_time": "25m 22s", "remaining_time": "2h 57m 36s"} +{"loss": 0.61709371, "acc": 0.81563005, "grad_norm": 0.1537538, "learning_rate": 9.826e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082937, "epoch": 0.0166886, "global_step/max_steps": "130/1000", "percentage": "13.00%", "elapsed_time": "26m 7s", "remaining_time": "2h 54m 47s"} +{"loss": 0.63595695, "acc": 0.80918331, "grad_norm": 0.14841115, "learning_rate": 9.804e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083738, "epoch": 0.01733047, "global_step/max_steps": "135/1000", "percentage": "13.50%", "elapsed_time": "26m 51s", "remaining_time": "2h 52m 7s"} +{"loss": 0.64757662, "acc": 0.81229877, "grad_norm": 0.16627078, "learning_rate": 9.78e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084642, "epoch": 0.01797234, "global_step/max_steps": "140/1000", "percentage": "14.00%", "elapsed_time": "27m 33s", "remaining_time": "2h 49m 18s"} +{"loss": 0.6832706, "acc": 0.804142, "grad_norm": 0.17142449, "learning_rate": 9.755e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.085406, "epoch": 0.0186142, "global_step/max_steps": "145/1000", "percentage": "14.50%", "elapsed_time": "28m 17s", "remaining_time": "2h 46m 49s"} +{"loss": 0.70668921, "acc": 0.79688311, "grad_norm": 0.18916593, "learning_rate": 9.729e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.086183, "epoch": 0.01925607, "global_step/max_steps": "150/1000", "percentage": "15.00%", "elapsed_time": "29m 0s", "remaining_time": "2h 44m 20s"} +{"eval_loss": 0.63503182, "eval_acc": 0.815351, "eval_runtime": 196.0265, "eval_samples_per_second": 6.417, "eval_steps_per_second": 6.417, "epoch": 0.01925607, "global_step/max_steps": "150/1000", "percentage": "15.00%", "elapsed_time": "32m 16s", "remaining_time": "3h 2m 51s"} +{"loss": 0.63387117, "acc": 0.80884809, "grad_norm": 0.17633556, "learning_rate": 9.702e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078254, "epoch": 0.01989794, "global_step/max_steps": "155/1000", "percentage": "15.50%", "elapsed_time": "33m 0s", "remaining_time": "2h 59m 56s"} +{"loss": 0.65075536, "acc": 0.81135025, "grad_norm": 0.18200529, "learning_rate": 9.673e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078985, "epoch": 0.02053981, "global_step/max_steps": "160/1000", "percentage": "16.00%", "elapsed_time": "33m 45s", "remaining_time": "2h 57m 13s"} +{"loss": 0.60177903, "acc": 0.82410259, "grad_norm": 0.148532, "learning_rate": 9.643e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079746, "epoch": 0.02118168, "global_step/max_steps": "165/1000", "percentage": "16.50%", "elapsed_time": "34m 28s", "remaining_time": "2h 54m 29s"} +{"loss": 0.68190188, "acc": 0.80189457, "grad_norm": 0.1773257, "learning_rate": 9.611e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080445, "epoch": 0.02182355, "global_step/max_steps": "170/1000", "percentage": "17.00%", "elapsed_time": "35m 12s", "remaining_time": "2h 51m 56s"} +{"loss": 0.62211475, "acc": 0.81763601, "grad_norm": 0.35834736, "learning_rate": 9.579e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081173, "epoch": 0.02246542, "global_step/max_steps": "175/1000", "percentage": "17.50%", "elapsed_time": "35m 55s", "remaining_time": "2h 49m 21s"} +{"loss": 0.63143706, "acc": 0.81451321, "grad_norm": 0.19369152, "learning_rate": 9.545e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081877, "epoch": 0.02310729, "global_step/max_steps": "180/1000", "percentage": "18.00%", "elapsed_time": "36m 38s", "remaining_time": "2h 46m 53s"} +{"loss": 0.6451148, "acc": 0.809447, "grad_norm": 0.1604932, "learning_rate": 9.51e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082533, "epoch": 0.02374916, "global_step/max_steps": "185/1000", "percentage": "18.50%", "elapsed_time": "37m 21s", "remaining_time": "2h 44m 33s"} +{"loss": 0.65715637, "acc": 0.80372143, "grad_norm": 0.19566484, "learning_rate": 9.474e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083203, "epoch": 0.02439103, "global_step/max_steps": "190/1000", "percentage": "19.00%", "elapsed_time": "38m 3s", "remaining_time": "2h 42m 13s"} +{"loss": 0.63388405, "acc": 0.81516018, "grad_norm": 0.18369696, "learning_rate": 9.436e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083851, "epoch": 0.0250329, "global_step/max_steps": "195/1000", "percentage": "19.50%", "elapsed_time": "38m 45s", "remaining_time": "2h 39m 59s"} +{"loss": 0.65765018, "acc": 0.80683355, "grad_norm": 0.15840834, "learning_rate": 9.397e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084362, "epoch": 0.02567476, "global_step/max_steps": "200/1000", "percentage": "20.00%", "elapsed_time": "39m 30s", "remaining_time": "2h 38m 1s"} +{"eval_loss": 0.6316511, "eval_acc": 0.81542639, "eval_runtime": 194.3299, "eval_samples_per_second": 6.474, "eval_steps_per_second": 6.474, "epoch": 0.02567476, "global_step/max_steps": "200/1000", "percentage": "20.00%", "elapsed_time": "42m 44s", "remaining_time": "2h 50m 58s"} +{"loss": 0.64739652, "acc": 0.81476297, "grad_norm": 0.18683095, "learning_rate": 9.357e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078515, "epoch": 0.02631663, "global_step/max_steps": "205/1000", "percentage": "20.50%", "elapsed_time": "43m 30s", "remaining_time": "2h 48m 44s"} +{"loss": 0.65772038, "acc": 0.80957623, "grad_norm": 0.16226844, "learning_rate": 9.316e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079027, "epoch": 0.0269585, "global_step/max_steps": "210/1000", "percentage": "21.00%", "elapsed_time": "44m 17s", "remaining_time": "2h 46m 35s"} +{"loss": 0.63748703, "acc": 0.81580648, "grad_norm": 0.16426006, "learning_rate": 9.274e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079584, "epoch": 0.02760037, "global_step/max_steps": "215/1000", "percentage": "21.50%", "elapsed_time": "45m 1s", "remaining_time": "2h 44m 22s"} +{"loss": 0.66415677, "acc": 0.80812073, "grad_norm": 0.17497523, "learning_rate": 9.23e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080111, "epoch": 0.02824224, "global_step/max_steps": "220/1000", "percentage": "22.00%", "elapsed_time": "45m 45s", "remaining_time": "2h 42m 15s"} +{"loss": 0.62169385, "acc": 0.81957884, "grad_norm": 0.15272143, "learning_rate": 9.186e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080603, "epoch": 0.02888411, "global_step/max_steps": "225/1000", "percentage": "22.50%", "elapsed_time": "46m 31s", "remaining_time": "2h 40m 13s"} +{"loss": 0.6528583, "acc": 0.80860453, "grad_norm": 0.16893056, "learning_rate": 9.14e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081113, "epoch": 0.02952598, "global_step/max_steps": "230/1000", "percentage": "23.00%", "elapsed_time": "47m 15s", "remaining_time": "2h 38m 11s"} +{"loss": 0.62348075, "acc": 0.81558657, "grad_norm": 0.20389846, "learning_rate": 9.093e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081633, "epoch": 0.03016785, "global_step/max_steps": "235/1000", "percentage": "23.50%", "elapsed_time": "47m 58s", "remaining_time": "2h 36m 10s"} +{"loss": 0.54310794, "acc": 0.83771782, "grad_norm": 0.18336393, "learning_rate": 9.045e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082163, "epoch": 0.03080972, "global_step/max_steps": "240/1000", "percentage": "24.00%", "elapsed_time": "48m 40s", "remaining_time": "2h 34m 8s"} +{"loss": 0.65011134, "acc": 0.81091404, "grad_norm": 0.18230066, "learning_rate": 8.996e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082662, "epoch": 0.03145159, "global_step/max_steps": "245/1000", "percentage": "24.50%", "elapsed_time": "49m 23s", "remaining_time": "2h 32m 12s"} +{"loss": 0.61326828, "acc": 0.8202961, "grad_norm": 0.19047268, "learning_rate": 8.946e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083111, "epoch": 0.03209346, "global_step/max_steps": "250/1000", "percentage": "25.00%", "elapsed_time": "50m 7s", "remaining_time": "2h 30m 23s"} +{"eval_loss": 0.62229896, "eval_acc": 0.81746402, "eval_runtime": 194.2619, "eval_samples_per_second": 6.476, "eval_steps_per_second": 6.476, "epoch": 0.03209346, "global_step/max_steps": "250/1000", "percentage": "25.00%", "elapsed_time": "53m 21s", "remaining_time": "2h 40m 5s"} +{"loss": 0.65217943, "acc": 0.81616802, "grad_norm": 0.19024301, "learning_rate": 8.894e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078534, "epoch": 0.03273533, "global_step/max_steps": "255/1000", "percentage": "25.50%", "elapsed_time": "54m 6s", "remaining_time": "2h 38m 5s"} +{"loss": 0.65409112, "acc": 0.81027069, "grad_norm": 0.19169311, "learning_rate": 8.842e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078979, "epoch": 0.03337719, "global_step/max_steps": "260/1000", "percentage": "26.00%", "elapsed_time": "54m 51s", "remaining_time": "2h 36m 8s"} +{"loss": 0.67106547, "acc": 0.80319004, "grad_norm": 0.20081347, "learning_rate": 8.789e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079517, "epoch": 0.03401906, "global_step/max_steps": "265/1000", "percentage": "26.50%", "elapsed_time": "55m 32s", "remaining_time": "2h 34m 2s"} +{"loss": 0.57896609, "acc": 0.82499094, "grad_norm": 0.16266762, "learning_rate": 8.734e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079959, "epoch": 0.03466093, "global_step/max_steps": "270/1000", "percentage": "27.00%", "elapsed_time": "56m 16s", "remaining_time": "2h 32m 8s"} +{"loss": 0.56308613, "acc": 0.83434772, "grad_norm": 0.19760369, "learning_rate": 8.679e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080441, "epoch": 0.0353028, "global_step/max_steps": "275/1000", "percentage": "27.50%", "elapsed_time": "56m 58s", "remaining_time": "2h 30m 11s"} +{"loss": 0.62751951, "acc": 0.81103878, "grad_norm": 0.2042129, "learning_rate": 8.622e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080888, "epoch": 0.03594467, "global_step/max_steps": "280/1000", "percentage": "28.00%", "elapsed_time": "57m 41s", "remaining_time": "2h 28m 20s"} +{"loss": 0.67880988, "acc": 0.80577688, "grad_norm": 0.18944614, "learning_rate": 8.565e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081351, "epoch": 0.03658654, "global_step/max_steps": "285/1000", "percentage": "28.50%", "elapsed_time": "58m 22s", "remaining_time": "2h 26m 28s"} +{"loss": 0.63270054, "acc": 0.81629257, "grad_norm": 0.16580035, "learning_rate": 8.506e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081754, "epoch": 0.03722841, "global_step/max_steps": "290/1000", "percentage": "29.00%", "elapsed_time": "59m 6s", "remaining_time": "2h 24m 43s"} +{"loss": 0.63396297, "acc": 0.81265612, "grad_norm": 0.20476556, "learning_rate": 8.447e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082163, "epoch": 0.03787028, "global_step/max_steps": "295/1000", "percentage": "29.50%", "elapsed_time": "59m 50s", "remaining_time": "2h 22m 59s"} +{"loss": 0.63431234, "acc": 0.81665688, "grad_norm": 0.16858129, "learning_rate": 8.386e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082563, "epoch": 0.03851215, "global_step/max_steps": "300/1000", "percentage": "30.00%", "elapsed_time": "1h 0m 33s", "remaining_time": "2h 21m 17s"} +{"eval_loss": 0.62134022, "eval_acc": 0.81809104, "eval_runtime": 194.9277, "eval_samples_per_second": 6.454, "eval_steps_per_second": 6.454, "epoch": 0.03851215, "global_step/max_steps": "300/1000", "percentage": "30.00%", "elapsed_time": "1h 3m 48s", "remaining_time": "2h 28m 52s"} +{"loss": 0.65134788, "acc": 0.81313, "grad_norm": 0.19343022, "learning_rate": 8.325e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078839, "epoch": 0.03915402, "global_step/max_steps": "305/1000", "percentage": "30.50%", "elapsed_time": "1h 4m 28s", "remaining_time": "2h 26m 54s"} +{"loss": 0.66552057, "acc": 0.80900688, "grad_norm": 0.20626357, "learning_rate": 8.263e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07924, "epoch": 0.03979589, "global_step/max_steps": "310/1000", "percentage": "31.00%", "elapsed_time": "1h 5m 11s", "remaining_time": "2h 25m 6s"} +{"loss": 0.6285687, "acc": 0.81944618, "grad_norm": 0.22261417, "learning_rate": 8.2e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079651, "epoch": 0.04043775, "global_step/max_steps": "315/1000", "percentage": "31.50%", "elapsed_time": "1h 5m 54s", "remaining_time": "2h 23m 19s"} +{"loss": 0.61407933, "acc": 0.82105675, "grad_norm": 0.17977822, "learning_rate": 8.136e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080053, "epoch": 0.04107962, "global_step/max_steps": "320/1000", "percentage": "32.00%", "elapsed_time": "1h 6m 37s", "remaining_time": "2h 21m 33s"} +{"loss": 0.63154807, "acc": 0.81391029, "grad_norm": 0.17346363, "learning_rate": 8.071e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080427, "epoch": 0.04172149, "global_step/max_steps": "325/1000", "percentage": "32.50%", "elapsed_time": "1h 7m 20s", "remaining_time": "2h 19m 52s"} +{"loss": 0.67294674, "acc": 0.80443487, "grad_norm": 0.20138931, "learning_rate": 8.005e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08081, "epoch": 0.04236336, "global_step/max_steps": "330/1000", "percentage": "33.00%", "elapsed_time": "1h 8m 3s", "remaining_time": "2h 18m 10s"} +{"loss": 0.62769508, "acc": 0.8138341, "grad_norm": 0.22969562, "learning_rate": 7.939e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081179, "epoch": 0.04300523, "global_step/max_steps": "335/1000", "percentage": "33.50%", "elapsed_time": "1h 8m 46s", "remaining_time": "2h 16m 31s"} +{"loss": 0.65062008, "acc": 0.81060715, "grad_norm": 0.1887732, "learning_rate": 7.872e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081555, "epoch": 0.0436471, "global_step/max_steps": "340/1000", "percentage": "34.00%", "elapsed_time": "1h 9m 28s", "remaining_time": "2h 14m 52s"} +{"loss": 0.65066905, "acc": 0.80925789, "grad_norm": 0.20824845, "learning_rate": 7.804e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081899, "epoch": 0.04428897, "global_step/max_steps": "345/1000", "percentage": "34.50%", "elapsed_time": "1h 10m 12s", "remaining_time": "2h 13m 16s"} +{"loss": 0.64833279, "acc": 0.80743494, "grad_norm": 0.1929646, "learning_rate": 7.735e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082229, "epoch": 0.04493084, "global_step/max_steps": "350/1000", "percentage": "35.00%", "elapsed_time": "1h 10m 56s", "remaining_time": "2h 11m 44s"} +{"eval_loss": 0.61841357, "eval_acc": 0.81859711, "eval_runtime": 195.2572, "eval_samples_per_second": 6.443, "eval_steps_per_second": 6.443, "epoch": 0.04493084, "global_step/max_steps": "350/1000", "percentage": "35.00%", "elapsed_time": "1h 14m 11s", "remaining_time": "2h 17m 46s"} +{"loss": 0.63578596, "acc": 0.81946774, "grad_norm": 0.18529889, "learning_rate": 7.665e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078909, "epoch": 0.04557271, "global_step/max_steps": "355/1000", "percentage": "35.50%", "elapsed_time": "1h 14m 58s", "remaining_time": "2h 16m 13s"} +{"loss": 0.59197049, "acc": 0.82359991, "grad_norm": 0.16975072, "learning_rate": 7.595e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079228, "epoch": 0.04621458, "global_step/max_steps": "360/1000", "percentage": "36.00%", "elapsed_time": "1h 15m 43s", "remaining_time": "2h 14m 37s"} +{"loss": 0.58269887, "acc": 0.82826347, "grad_norm": 0.19332191, "learning_rate": 7.524e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079527, "epoch": 0.04685645, "global_step/max_steps": "365/1000", "percentage": "36.50%", "elapsed_time": "1h 16m 29s", "remaining_time": "2h 13m 4s"} +{"loss": 0.62563605, "acc": 0.81692057, "grad_norm": 0.18018475, "learning_rate": 7.452e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079855, "epoch": 0.04749832, "global_step/max_steps": "370/1000", "percentage": "37.00%", "elapsed_time": "1h 17m 13s", "remaining_time": "2h 11m 28s"} +{"loss": 0.62537222, "acc": 0.81458244, "grad_norm": 0.26712176, "learning_rate": 7.38e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080167, "epoch": 0.04814018, "global_step/max_steps": "375/1000", "percentage": "37.50%", "elapsed_time": "1h 17m 57s", "remaining_time": "2h 9m 55s"} +{"loss": 0.6464529, "acc": 0.80892944, "grad_norm": 0.20377114, "learning_rate": 7.307e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080535, "epoch": 0.04878205, "global_step/max_steps": "380/1000", "percentage": "38.00%", "elapsed_time": "1h 18m 38s", "remaining_time": "2h 8m 17s"} +{"loss": 0.64175944, "acc": 0.81387253, "grad_norm": 0.21851403, "learning_rate": 7.233e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080866, "epoch": 0.04942392, "global_step/max_steps": "385/1000", "percentage": "38.50%", "elapsed_time": "1h 19m 20s", "remaining_time": "2h 6m 44s"} +{"loss": 0.65399485, "acc": 0.81104851, "grad_norm": 0.1792085, "learning_rate": 7.159e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081177, "epoch": 0.05006579, "global_step/max_steps": "390/1000", "percentage": "39.00%", "elapsed_time": "1h 20m 3s", "remaining_time": "2h 5m 13s"} +{"loss": 0.65062542, "acc": 0.81167917, "grad_norm": 0.21850617, "learning_rate": 7.084e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081491, "epoch": 0.05070766, "global_step/max_steps": "395/1000", "percentage": "39.50%", "elapsed_time": "1h 20m 46s", "remaining_time": "2h 3m 43s"} +{"loss": 0.62041502, "acc": 0.82351618, "grad_norm": 0.19366457, "learning_rate": 7.008e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081765, "epoch": 0.05134953, "global_step/max_steps": "400/1000", "percentage": "40.00%", "elapsed_time": "1h 21m 31s", "remaining_time": "2h 2m 17s"} +{"eval_loss": 0.61470592, "eval_acc": 0.81922192, "eval_runtime": 194.2328, "eval_samples_per_second": 6.477, "eval_steps_per_second": 6.477, "epoch": 0.05134953, "global_step/max_steps": "400/1000", "percentage": "40.00%", "elapsed_time": "1h 24m 45s", "remaining_time": "2h 7m 8s"} +{"loss": 0.63979912, "acc": 0.81023674, "grad_norm": 0.18592495, "learning_rate": 6.932e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078921, "epoch": 0.0519914, "global_step/max_steps": "405/1000", "percentage": "40.50%", "elapsed_time": "1h 25m 31s", "remaining_time": "2h 5m 38s"} +{"loss": 0.63082585, "acc": 0.81422606, "grad_norm": 0.1887981, "learning_rate": 6.856e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079225, "epoch": 0.05263327, "global_step/max_steps": "410/1000", "percentage": "41.00%", "elapsed_time": "1h 26m 14s", "remaining_time": "2h 4m 6s"} +{"loss": 0.60244231, "acc": 0.82355537, "grad_norm": 0.19911143, "learning_rate": 6.779e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079522, "epoch": 0.05327514, "global_step/max_steps": "415/1000", "percentage": "41.50%", "elapsed_time": "1h 26m 58s", "remaining_time": "2h 2m 35s"} +{"loss": 0.68041868, "acc": 0.80394392, "grad_norm": 0.18245313, "learning_rate": 6.701e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079822, "epoch": 0.05391701, "global_step/max_steps": "420/1000", "percentage": "42.00%", "elapsed_time": "1h 27m 41s", "remaining_time": "2h 1m 5s"} +{"loss": 0.58148174, "acc": 0.82535486, "grad_norm": 0.18471555, "learning_rate": 6.623e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080165, "epoch": 0.05455888, "global_step/max_steps": "425/1000", "percentage": "42.50%", "elapsed_time": "1h 28m 21s", "remaining_time": "1h 59m 32s"} +{"loss": 0.64324603, "acc": 0.8145462, "grad_norm": 0.21886419, "learning_rate": 6.545e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080479, "epoch": 0.05520074, "global_step/max_steps": "430/1000", "percentage": "43.00%", "elapsed_time": "1h 29m 2s", "remaining_time": "1h 58m 2s"} +{"loss": 0.64245248, "acc": 0.80875597, "grad_norm": 0.20460849, "learning_rate": 6.466e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080772, "epoch": 0.05584261, "global_step/max_steps": "435/1000", "percentage": "43.50%", "elapsed_time": "1h 29m 45s", "remaining_time": "1h 56m 34s"} +{"loss": 0.63060322, "acc": 0.81591587, "grad_norm": 0.19347584, "learning_rate": 6.387e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081046, "epoch": 0.05648448, "global_step/max_steps": "440/1000", "percentage": "44.00%", "elapsed_time": "1h 30m 28s", "remaining_time": "1h 55m 9s"} +{"loss": 0.64218235, "acc": 0.81191225, "grad_norm": 0.20590667, "learning_rate": 6.307e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081334, "epoch": 0.05712635, "global_step/max_steps": "445/1000", "percentage": "44.50%", "elapsed_time": "1h 31m 10s", "remaining_time": "1h 53m 43s"} +{"loss": 0.64007626, "acc": 0.81284475, "grad_norm": 0.18999861, "learning_rate": 6.227e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081619, "epoch": 0.05776822, "global_step/max_steps": "450/1000", "percentage": "45.00%", "elapsed_time": "1h 31m 53s", "remaining_time": "1h 52m 18s"} +{"eval_loss": 0.61346853, "eval_acc": 0.8195972, "eval_runtime": 194.9348, "eval_samples_per_second": 6.453, "eval_steps_per_second": 6.453, "epoch": 0.05776822, "global_step/max_steps": "450/1000", "percentage": "45.00%", "elapsed_time": "1h 35m 8s", "remaining_time": "1h 56m 16s"} +{"loss": 0.63169065, "acc": 0.81439934, "grad_norm": 0.20194243, "learning_rate": 6.147e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07909, "epoch": 0.05841009, "global_step/max_steps": "455/1000", "percentage": "45.50%", "elapsed_time": "1h 35m 52s", "remaining_time": "1h 54m 50s"} +{"loss": 0.65331206, "acc": 0.80925694, "grad_norm": 0.22199371, "learning_rate": 6.066e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079394, "epoch": 0.05905196, "global_step/max_steps": "460/1000", "percentage": "46.00%", "elapsed_time": "1h 36m 33s", "remaining_time": "1h 53m 21s"} +{"loss": 0.62136326, "acc": 0.81743002, "grad_norm": 0.19339646, "learning_rate": 5.986e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079664, "epoch": 0.05969383, "global_step/max_steps": "465/1000", "percentage": "46.50%", "elapsed_time": "1h 37m 16s", "remaining_time": "1h 51m 55s"} +{"loss": 0.58844328, "acc": 0.82081652, "grad_norm": 0.1911387, "learning_rate": 5.904e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079903, "epoch": 0.0603357, "global_step/max_steps": "470/1000", "percentage": "47.00%", "elapsed_time": "1h 38m 1s", "remaining_time": "1h 50m 32s"} +{"loss": 0.6088398, "acc": 0.82189302, "grad_norm": 0.21947172, "learning_rate": 5.823e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080178, "epoch": 0.06097757, "global_step/max_steps": "475/1000", "percentage": "47.50%", "elapsed_time": "1h 38m 43s", "remaining_time": "1h 49m 7s"} +{"loss": 0.62442837, "acc": 0.81938705, "grad_norm": 0.19398923, "learning_rate": 5.741e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080433, "epoch": 0.06161944, "global_step/max_steps": "480/1000", "percentage": "48.00%", "elapsed_time": "1h 39m 27s", "remaining_time": "1h 47m 44s"} +{"loss": 0.57895641, "acc": 0.82784338, "grad_norm": 0.17412326, "learning_rate": 5.659e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080668, "epoch": 0.0622613, "global_step/max_steps": "485/1000", "percentage": "48.50%", "elapsed_time": "1h 40m 11s", "remaining_time": "1h 46m 23s"} +{"loss": 0.61787653, "acc": 0.82182274, "grad_norm": 0.23736475, "learning_rate": 5.577e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080927, "epoch": 0.06290317, "global_step/max_steps": "490/1000", "percentage": "49.00%", "elapsed_time": "1h 40m 54s", "remaining_time": "1h 45m 1s"} +{"loss": 0.57188206, "acc": 0.82861795, "grad_norm": 0.18874206, "learning_rate": 5.495e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081151, "epoch": 0.06354504, "global_step/max_steps": "495/1000", "percentage": "49.50%", "elapsed_time": "1h 41m 39s", "remaining_time": "1h 43m 42s"} +{"loss": 0.67568989, "acc": 0.80789671, "grad_norm": 0.19716145, "learning_rate": 5.413e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081405, "epoch": 0.06418691, "global_step/max_steps": "500/1000", "percentage": "50.00%", "elapsed_time": "1h 42m 21s", "remaining_time": "1h 42m 21s"} +{"eval_loss": 0.61542618, "eval_acc": 0.81912899, "eval_runtime": 194.8211, "eval_samples_per_second": 6.457, "eval_steps_per_second": 6.457, "epoch": 0.06418691, "global_step/max_steps": "500/1000", "percentage": "50.00%", "elapsed_time": "1h 45m 36s", "remaining_time": "1h 45m 36s"} +{"loss": 0.64408102, "acc": 0.80737734, "grad_norm": 0.20341663, "learning_rate": 5.33e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079157, "epoch": 0.06482878, "global_step/max_steps": "505/1000", "percentage": "50.50%", "elapsed_time": "1h 46m 19s", "remaining_time": "1h 44m 13s"} +{"loss": 0.55616164, "acc": 0.83580818, "grad_norm": 0.19432743, "learning_rate": 5.248e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079418, "epoch": 0.06547065, "global_step/max_steps": "510/1000", "percentage": "51.00%", "elapsed_time": "1h 47m 1s", "remaining_time": "1h 42m 49s"} +{"loss": 0.63107128, "acc": 0.81569843, "grad_norm": 0.21546119, "learning_rate": 5.165e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079676, "epoch": 0.06611252, "global_step/max_steps": "515/1000", "percentage": "51.50%", "elapsed_time": "1h 47m 43s", "remaining_time": "1h 41m 26s"} +{"loss": 0.60510926, "acc": 0.82521887, "grad_norm": 0.18064648, "learning_rate": 5.083e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079928, "epoch": 0.06675439, "global_step/max_steps": "520/1000", "percentage": "52.00%", "elapsed_time": "1h 48m 25s", "remaining_time": "1h 40m 5s"} +{"loss": 0.65878468, "acc": 0.8060174, "grad_norm": 0.21811153, "learning_rate": 5e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080188, "epoch": 0.06739626, "global_step/max_steps": "525/1000", "percentage": "52.50%", "elapsed_time": "1h 49m 6s", "remaining_time": "1h 38m 43s"} +{"loss": 0.61963496, "acc": 0.81847181, "grad_norm": 0.19227809, "learning_rate": 4.917e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080404, "epoch": 0.06803813, "global_step/max_steps": "530/1000", "percentage": "53.00%", "elapsed_time": "1h 49m 51s", "remaining_time": "1h 37m 25s"} +{"loss": 0.6185873, "acc": 0.81498117, "grad_norm": 0.22034384, "learning_rate": 4.835e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080637, "epoch": 0.06868, "global_step/max_steps": "535/1000", "percentage": "53.50%", "elapsed_time": "1h 50m 34s", "remaining_time": "1h 36m 6s"} +{"loss": 0.6963346, "acc": 0.80154915, "grad_norm": 0.19249101, "learning_rate": 4.752e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080856, "epoch": 0.06932187, "global_step/max_steps": "540/1000", "percentage": "54.00%", "elapsed_time": "1h 51m 18s", "remaining_time": "1h 34m 48s"} +{"loss": 0.6188817, "acc": 0.81683502, "grad_norm": 0.1994091, "learning_rate": 4.67e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081075, "epoch": 0.06996373, "global_step/max_steps": "545/1000", "percentage": "54.50%", "elapsed_time": "1h 52m 1s", "remaining_time": "1h 33m 31s"} +{"loss": 0.59354177, "acc": 0.82736206, "grad_norm": 0.18659113, "learning_rate": 4.587e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081266, "epoch": 0.0706056, "global_step/max_steps": "550/1000", "percentage": "55.00%", "elapsed_time": "1h 52m 47s", "remaining_time": "1h 32m 17s"} +{"eval_loss": 0.61393005, "eval_acc": 0.81929115, "eval_runtime": 200.9073, "eval_samples_per_second": 6.262, "eval_steps_per_second": 6.262, "epoch": 0.0706056, "global_step/max_steps": "550/1000", "percentage": "55.00%", "elapsed_time": "1h 56m 8s", "remaining_time": "1h 35m 1s"} +{"loss": 0.63172441, "acc": 0.81306267, "grad_norm": 0.17537348, "learning_rate": 4.505e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079145, "epoch": 0.07124747, "global_step/max_steps": "555/1000", "percentage": "55.50%", "elapsed_time": "1h 56m 52s", "remaining_time": "1h 33m 42s"} +{"loss": 0.58555121, "acc": 0.82534027, "grad_norm": 0.21789849, "learning_rate": 4.423e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079394, "epoch": 0.07188934, "global_step/max_steps": "560/1000", "percentage": "56.00%", "elapsed_time": "1h 57m 33s", "remaining_time": "1h 32m 21s"} +{"loss": 0.59516869, "acc": 0.82140818, "grad_norm": 0.19700836, "learning_rate": 4.341e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079597, "epoch": 0.07253121, "global_step/max_steps": "565/1000", "percentage": "56.50%", "elapsed_time": "1h 58m 17s", "remaining_time": "1h 31m 4s"} +{"loss": 0.60017176, "acc": 0.81845322, "grad_norm": 0.18186125, "learning_rate": 4.259e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079791, "epoch": 0.07317308, "global_step/max_steps": "570/1000", "percentage": "57.00%", "elapsed_time": "1h 59m 3s", "remaining_time": "1h 29m 48s"} +{"loss": 0.59121842, "acc": 0.82169409, "grad_norm": 0.20915583, "learning_rate": 4.177e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080013, "epoch": 0.07381495, "global_step/max_steps": "575/1000", "percentage": "57.50%", "elapsed_time": "1h 59m 46s", "remaining_time": "1h 28m 31s"} +{"loss": 0.64874387, "acc": 0.81168118, "grad_norm": 0.20149122, "learning_rate": 4.096e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080249, "epoch": 0.07445682, "global_step/max_steps": "580/1000", "percentage": "58.00%", "elapsed_time": "2h 0m 27s", "remaining_time": "1h 27m 13s"} +{"loss": 0.63141985, "acc": 0.82017975, "grad_norm": 0.2139557, "learning_rate": 4.014e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080445, "epoch": 0.07509869, "global_step/max_steps": "585/1000", "percentage": "58.50%", "elapsed_time": "2h 1m 11s", "remaining_time": "1h 25m 58s"} +{"loss": 0.59338393, "acc": 0.8225503, "grad_norm": 0.21270451, "learning_rate": 3.934e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080661, "epoch": 0.07574056, "global_step/max_steps": "590/1000", "percentage": "59.00%", "elapsed_time": "2h 1m 54s", "remaining_time": "1h 24m 42s"} +{"loss": 0.65440679, "acc": 0.80733299, "grad_norm": 0.21861939, "learning_rate": 3.853e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080898, "epoch": 0.07638243, "global_step/max_steps": "595/1000", "percentage": "59.50%", "elapsed_time": "2h 2m 34s", "remaining_time": "1h 23m 26s"} +{"loss": 0.61422372, "acc": 0.81755505, "grad_norm": 0.19301304, "learning_rate": 3.773e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081091, "epoch": 0.07702429, "global_step/max_steps": "600/1000", "percentage": "60.00%", "elapsed_time": "2h 3m 18s", "remaining_time": "1h 22m 12s"} +{"eval_loss": 0.61097735, "eval_acc": 0.81982765, "eval_runtime": 195.2232, "eval_samples_per_second": 6.444, "eval_steps_per_second": 6.444, "epoch": 0.07702429, "global_step/max_steps": "600/1000", "percentage": "60.00%", "elapsed_time": "2h 6m 33s", "remaining_time": "1h 24m 22s"} +{"loss": 0.6057888, "acc": 0.82081652, "grad_norm": 0.20753734, "learning_rate": 3.693e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07921, "epoch": 0.07766616, "global_step/max_steps": "605/1000", "percentage": "60.50%", "elapsed_time": "2h 7m 17s", "remaining_time": "1h 23m 6s"} +{"loss": 0.61725841, "acc": 0.82343655, "grad_norm": 0.1979513, "learning_rate": 3.613e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079401, "epoch": 0.07830803, "global_step/max_steps": "610/1000", "percentage": "61.00%", "elapsed_time": "2h 8m 2s", "remaining_time": "1h 21m 51s"} +{"loss": 0.62781944, "acc": 0.81410999, "grad_norm": 0.20070389, "learning_rate": 3.534e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079569, "epoch": 0.0789499, "global_step/max_steps": "615/1000", "percentage": "61.50%", "elapsed_time": "2h 8m 48s", "remaining_time": "1h 20m 38s"} +{"loss": 0.62505813, "acc": 0.81817207, "grad_norm": 0.23272993, "learning_rate": 3.455e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079788, "epoch": 0.07959177, "global_step/max_steps": "620/1000", "percentage": "62.00%", "elapsed_time": "2h 9m 30s", "remaining_time": "1h 19m 22s"} +{"loss": 0.60028605, "acc": 0.82294455, "grad_norm": 0.18113944, "learning_rate": 3.377e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079975, "epoch": 0.08023364, "global_step/max_steps": "625/1000", "percentage": "62.50%", "elapsed_time": "2h 10m 14s", "remaining_time": "1h 18m 8s"} +{"loss": 0.61079011, "acc": 0.82047234, "grad_norm": 0.20408566, "learning_rate": 3.299e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080162, "epoch": 0.08087551, "global_step/max_steps": "630/1000", "percentage": "63.00%", "elapsed_time": "2h 10m 58s", "remaining_time": "1h 16m 55s"} +{"loss": 0.57911015, "acc": 0.82677517, "grad_norm": 0.21327981, "learning_rate": 3.221e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08036, "epoch": 0.08151738, "global_step/max_steps": "635/1000", "percentage": "63.50%", "elapsed_time": "2h 11m 41s", "remaining_time": "1h 15m 41s"} +{"loss": 0.60286283, "acc": 0.81979742, "grad_norm": 0.20325442, "learning_rate": 3.144e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080558, "epoch": 0.08215925, "global_step/max_steps": "640/1000", "percentage": "64.00%", "elapsed_time": "2h 12m 24s", "remaining_time": "1h 14m 28s"} +{"loss": 0.58266845, "acc": 0.83071327, "grad_norm": 0.20148617, "learning_rate": 3.068e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080764, "epoch": 0.08280112, "global_step/max_steps": "645/1000", "percentage": "64.50%", "elapsed_time": "2h 13m 5s", "remaining_time": "1h 13m 15s"} +{"loss": 0.55458455, "acc": 0.83186378, "grad_norm": 0.19807127, "learning_rate": 2.992e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080948, "epoch": 0.08344299, "global_step/max_steps": "650/1000", "percentage": "65.00%", "elapsed_time": "2h 13m 49s", "remaining_time": "1h 12m 3s"} +{"eval_loss": 0.60768825, "eval_acc": 0.82098964, "eval_runtime": 194.4544, "eval_samples_per_second": 6.469, "eval_steps_per_second": 6.469, "epoch": 0.08344299, "global_step/max_steps": "650/1000", "percentage": "65.00%", "elapsed_time": "2h 17m 4s", "remaining_time": "1h 13m 48s"} +{"loss": 0.61260557, "acc": 0.82214499, "grad_norm": 0.18806924, "learning_rate": 2.916e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079195, "epoch": 0.08408486, "global_step/max_steps": "655/1000", "percentage": "65.50%", "elapsed_time": "2h 17m 50s", "remaining_time": "1h 12m 36s"} +{"loss": 0.59967513, "acc": 0.82406235, "grad_norm": 0.19712701, "learning_rate": 2.841e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079403, "epoch": 0.08472672, "global_step/max_steps": "660/1000", "percentage": "66.00%", "elapsed_time": "2h 18m 31s", "remaining_time": "1h 11m 21s"} +{"loss": 0.64144659, "acc": 0.80978308, "grad_norm": 0.1984504, "learning_rate": 2.767e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079587, "epoch": 0.08536859, "global_step/max_steps": "665/1000", "percentage": "66.50%", "elapsed_time": "2h 19m 15s", "remaining_time": "1h 10m 9s"} +{"loss": 0.62947636, "acc": 0.81445723, "grad_norm": 0.21892953, "learning_rate": 2.693e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079776, "epoch": 0.08601046, "global_step/max_steps": "670/1000", "percentage": "67.00%", "elapsed_time": "2h 19m 58s", "remaining_time": "1h 8m 56s"} +{"loss": 0.58508019, "acc": 0.82742786, "grad_norm": 0.21680108, "learning_rate": 2.62e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07997, "epoch": 0.08665233, "global_step/max_steps": "675/1000", "percentage": "67.50%", "elapsed_time": "2h 20m 40s", "remaining_time": "1h 7m 43s"} +{"loss": 0.60457458, "acc": 0.82206249, "grad_norm": 0.19368014, "learning_rate": 2.548e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080131, "epoch": 0.0872942, "global_step/max_steps": "680/1000", "percentage": "68.00%", "elapsed_time": "2h 21m 25s", "remaining_time": "1h 6m 33s"} +{"loss": 0.61911306, "acc": 0.8187645, "grad_norm": 0.21237029, "learning_rate": 2.476e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080301, "epoch": 0.08793607, "global_step/max_steps": "685/1000", "percentage": "68.50%", "elapsed_time": "2h 22m 10s", "remaining_time": "1h 5m 22s"} +{"loss": 0.63167734, "acc": 0.81704865, "grad_norm": 0.22553302, "learning_rate": 2.405e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080481, "epoch": 0.08857794, "global_step/max_steps": "690/1000", "percentage": "69.00%", "elapsed_time": "2h 22m 53s", "remaining_time": "1h 4m 11s"} +{"loss": 0.63321238, "acc": 0.81163187, "grad_norm": 0.21230626, "learning_rate": 2.335e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080651, "epoch": 0.08921981, "global_step/max_steps": "695/1000", "percentage": "69.50%", "elapsed_time": "2h 23m 37s", "remaining_time": "1h 3m 1s"} +{"loss": 0.61235924, "acc": 0.81947212, "grad_norm": 0.23210007, "learning_rate": 2.265e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08085, "epoch": 0.08986168, "global_step/max_steps": "700/1000", "percentage": "70.00%", "elapsed_time": "2h 24m 17s", "remaining_time": "1h 1m 50s"} +{"eval_loss": 0.60764617, "eval_acc": 0.82038556, "eval_runtime": 194.4087, "eval_samples_per_second": 6.471, "eval_steps_per_second": 6.471, "epoch": 0.08986168, "global_step/max_steps": "700/1000", "percentage": "70.00%", "elapsed_time": "2h 27m 32s", "remaining_time": "1h 3m 13s"} +{"loss": 0.63990374, "acc": 0.81527042, "grad_norm": 0.20815226, "learning_rate": 2.196e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079227, "epoch": 0.09050355, "global_step/max_steps": "705/1000", "percentage": "70.50%", "elapsed_time": "2h 28m 18s", "remaining_time": "1h 2m 3s"} +{"loss": 0.59049015, "acc": 0.82444172, "grad_norm": 0.21324453, "learning_rate": 2.128e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079404, "epoch": 0.09114542, "global_step/max_steps": "710/1000", "percentage": "71.00%", "elapsed_time": "2h 29m 1s", "remaining_time": "1h 0m 52s"} +{"loss": 0.60989962, "acc": 0.81617746, "grad_norm": 0.19047819, "learning_rate": 2.061e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079576, "epoch": 0.09178728, "global_step/max_steps": "715/1000", "percentage": "71.50%", "elapsed_time": "2h 29m 44s", "remaining_time": "59m 41s"} +{"loss": 0.67080445, "acc": 0.80728264, "grad_norm": 0.2062957, "learning_rate": 1.995e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079742, "epoch": 0.09242915, "global_step/max_steps": "720/1000", "percentage": "72.00%", "elapsed_time": "2h 30m 28s", "remaining_time": "58m 31s"} +{"loss": 0.61908646, "acc": 0.81671677, "grad_norm": 0.19861044, "learning_rate": 1.929e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079905, "epoch": 0.09307102, "global_step/max_steps": "725/1000", "percentage": "72.50%", "elapsed_time": "2h 31m 12s", "remaining_time": "57m 21s"} +{"loss": 0.66370716, "acc": 0.81090012, "grad_norm": 0.19133475, "learning_rate": 1.864e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08006, "epoch": 0.09371289, "global_step/max_steps": "730/1000", "percentage": "73.00%", "elapsed_time": "2h 31m 57s", "remaining_time": "56m 12s"} +{"loss": 0.66476107, "acc": 0.81192856, "grad_norm": 0.22429423, "learning_rate": 1.8e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080239, "epoch": 0.09435476, "global_step/max_steps": "735/1000", "percentage": "73.50%", "elapsed_time": "2h 32m 39s", "remaining_time": "55m 2s"} +{"loss": 0.58692684, "acc": 0.82513466, "grad_norm": 0.21653637, "learning_rate": 1.737e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080402, "epoch": 0.09499663, "global_step/max_steps": "740/1000", "percentage": "74.00%", "elapsed_time": "2h 33m 23s", "remaining_time": "53m 53s"} +{"loss": 0.57462683, "acc": 0.82555256, "grad_norm": 0.17780368, "learning_rate": 1.675e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080553, "epoch": 0.0956385, "global_step/max_steps": "745/1000", "percentage": "74.50%", "elapsed_time": "2h 34m 8s", "remaining_time": "52m 45s"} +{"loss": 0.61962047, "acc": 0.81813164, "grad_norm": 0.20154658, "learning_rate": 1.614e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080707, "epoch": 0.09628037, "global_step/max_steps": "750/1000", "percentage": "75.00%", "elapsed_time": "2h 34m 52s", "remaining_time": "51m 37s"} +{"eval_loss": 0.60834277, "eval_acc": 0.8204208, "eval_runtime": 194.7163, "eval_samples_per_second": 6.461, "eval_steps_per_second": 6.461, "epoch": 0.09628037, "global_step/max_steps": "750/1000", "percentage": "75.00%", "elapsed_time": "2h 38m 7s", "remaining_time": "52m 42s"} +{"loss": 0.61750922, "acc": 0.82061501, "grad_norm": 0.24772085, "learning_rate": 1.553e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079226, "epoch": 0.09692224, "global_step/max_steps": "755/1000", "percentage": "75.50%", "elapsed_time": "2h 38m 49s", "remaining_time": "51m 32s"} +{"loss": 0.61280818, "acc": 0.81846237, "grad_norm": 0.22278401, "learning_rate": 1.494e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079391, "epoch": 0.09756411, "global_step/max_steps": "760/1000", "percentage": "76.00%", "elapsed_time": "2h 39m 32s", "remaining_time": "50m 22s"} +{"loss": 0.63006077, "acc": 0.81434851, "grad_norm": 0.22640762, "learning_rate": 1.435e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079552, "epoch": 0.09820598, "global_step/max_steps": "765/1000", "percentage": "76.50%", "elapsed_time": "2h 40m 16s", "remaining_time": "49m 13s"} +{"loss": 0.63865561, "acc": 0.81086941, "grad_norm": 0.20250477, "learning_rate": 1.378e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079713, "epoch": 0.09884784, "global_step/max_steps": "770/1000", "percentage": "77.00%", "elapsed_time": "2h 40m 59s", "remaining_time": "48m 5s"} +{"loss": 0.63764729, "acc": 0.81333466, "grad_norm": 0.21983562, "learning_rate": 1.321e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079857, "epoch": 0.09948971, "global_step/max_steps": "775/1000", "percentage": "77.50%", "elapsed_time": "2h 41m 44s", "remaining_time": "46m 57s"} +{"loss": 0.62097745, "acc": 0.81033506, "grad_norm": 0.21427663, "learning_rate": 1.266e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080004, "epoch": 0.10013158, "global_step/max_steps": "780/1000", "percentage": "78.00%", "elapsed_time": "2h 42m 29s", "remaining_time": "45m 49s"} +{"loss": 0.60655851, "acc": 0.82130699, "grad_norm": 0.20593636, "learning_rate": 1.211e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080173, "epoch": 0.10077345, "global_step/max_steps": "785/1000", "percentage": "78.50%", "elapsed_time": "2h 43m 11s", "remaining_time": "44m 41s"} +{"loss": 0.61125717, "acc": 0.82261295, "grad_norm": 0.20524643, "learning_rate": 1.158e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080342, "epoch": 0.10141532, "global_step/max_steps": "790/1000", "percentage": "79.00%", "elapsed_time": "2h 43m 52s", "remaining_time": "43m 33s"} +{"loss": 0.59510598, "acc": 0.82531328, "grad_norm": 0.17600791, "learning_rate": 1.106e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08049, "epoch": 0.10205719, "global_step/max_steps": "795/1000", "percentage": "79.50%", "elapsed_time": "2h 44m 36s", "remaining_time": "42m 26s"} +{"loss": 0.63478656, "acc": 0.81779881, "grad_norm": 0.21417794, "learning_rate": 1.054e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080624, "epoch": 0.10269906, "global_step/max_steps": "800/1000", "percentage": "80.00%", "elapsed_time": "2h 45m 22s", "remaining_time": "41m 20s"} +{"eval_loss": 0.60770029, "eval_acc": 0.82076974, "eval_runtime": 194.8773, "eval_samples_per_second": 6.455, "eval_steps_per_second": 6.455, "epoch": 0.10269906, "global_step/max_steps": "800/1000", "percentage": "80.00%", "elapsed_time": "2h 48m 37s", "remaining_time": "42m 9s"} +{"loss": 0.66100531, "acc": 0.80902939, "grad_norm": 0.20908104, "learning_rate": 1.004e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079226, "epoch": 0.10334093, "global_step/max_steps": "805/1000", "percentage": "80.50%", "elapsed_time": "2h 49m 20s", "remaining_time": "41m 1s"} +{"loss": 0.63930345, "acc": 0.81437035, "grad_norm": 0.22697587, "learning_rate": 9.55e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079387, "epoch": 0.1039828, "global_step/max_steps": "810/1000", "percentage": "81.00%", "elapsed_time": "2h 50m 2s", "remaining_time": "39m 53s"} +{"loss": 0.63128233, "acc": 0.81263914, "grad_norm": 0.21495579, "learning_rate": 9.07e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079538, "epoch": 0.10462467, "global_step/max_steps": "815/1000", "percentage": "81.50%", "elapsed_time": "2h 50m 46s", "remaining_time": "38m 45s"} +{"loss": 0.66762576, "acc": 0.80606184, "grad_norm": 0.24026649, "learning_rate": 8.6e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07969, "epoch": 0.10526654, "global_step/max_steps": "820/1000", "percentage": "82.00%", "elapsed_time": "2h 51m 29s", "remaining_time": "37m 38s"} +{"loss": 0.56980219, "acc": 0.83144102, "grad_norm": 0.21793744, "learning_rate": 8.14e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079849, "epoch": 0.10590841, "global_step/max_steps": "825/1000", "percentage": "82.50%", "elapsed_time": "2h 52m 11s", "remaining_time": "36m 31s"} +{"loss": 0.61694736, "acc": 0.81910725, "grad_norm": 0.19496454, "learning_rate": 7.7e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07997, "epoch": 0.10655027, "global_step/max_steps": "830/1000", "percentage": "83.00%", "elapsed_time": "2h 52m 58s", "remaining_time": "35m 25s"} +{"loss": 0.64870877, "acc": 0.81330662, "grad_norm": 0.23187701, "learning_rate": 7.26e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080126, "epoch": 0.10719214, "global_step/max_steps": "835/1000", "percentage": "83.50%", "elapsed_time": "2h 53m 40s", "remaining_time": "34m 19s"} +{"loss": 0.61115222, "acc": 0.81870842, "grad_norm": 0.2040024, "learning_rate": 6.84e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080258, "epoch": 0.10783401, "global_step/max_steps": "840/1000", "percentage": "84.00%", "elapsed_time": "2h 54m 25s", "remaining_time": "33m 13s"} +{"loss": 0.61838484, "acc": 0.82128296, "grad_norm": 0.24608131, "learning_rate": 6.43e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080422, "epoch": 0.10847588, "global_step/max_steps": "845/1000", "percentage": "84.50%", "elapsed_time": "2h 55m 6s", "remaining_time": "32m 7s"} +{"loss": 0.67037339, "acc": 0.8118104, "grad_norm": 0.21192344, "learning_rate": 6.03e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080553, "epoch": 0.10911775, "global_step/max_steps": "850/1000", "percentage": "85.00%", "elapsed_time": "2h 55m 51s", "remaining_time": "31m 2s"} +{"eval_loss": 0.60646284, "eval_acc": 0.82088585, "eval_runtime": 194.9575, "eval_samples_per_second": 6.453, "eval_steps_per_second": 6.453, "epoch": 0.10911775, "global_step/max_steps": "850/1000", "percentage": "85.00%", "elapsed_time": "2h 59m 6s", "remaining_time": "31m 36s"} +{"loss": 0.63853312, "acc": 0.81058187, "grad_norm": 0.22560675, "learning_rate": 5.64e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079236, "epoch": 0.10975962, "global_step/max_steps": "855/1000", "percentage": "85.50%", "elapsed_time": "2h 59m 50s", "remaining_time": "30m 29s"} +{"loss": 0.6172534, "acc": 0.8174571, "grad_norm": 0.21500875, "learning_rate": 5.26e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079369, "epoch": 0.11040149, "global_step/max_steps": "860/1000", "percentage": "86.00%", "elapsed_time": "3h 0m 35s", "remaining_time": "29m 23s"} +{"loss": 0.65724411, "acc": 0.8093504, "grad_norm": 0.23700735, "learning_rate": 4.9e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07952, "epoch": 0.11104336, "global_step/max_steps": "865/1000", "percentage": "86.50%", "elapsed_time": "3h 1m 17s", "remaining_time": "28m 17s"} +{"loss": 0.61837373, "acc": 0.81735506, "grad_norm": 0.21098879, "learning_rate": 4.55e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079659, "epoch": 0.11168523, "global_step/max_steps": "870/1000", "percentage": "87.00%", "elapsed_time": "3h 2m 1s", "remaining_time": "27m 11s"} +{"loss": 0.61365747, "acc": 0.81503067, "grad_norm": 0.20609669, "learning_rate": 4.21e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079794, "epoch": 0.1123271, "global_step/max_steps": "875/1000", "percentage": "87.50%", "elapsed_time": "3h 2m 45s", "remaining_time": "26m 6s"} +{"loss": 0.66433964, "acc": 0.80629053, "grad_norm": 0.21808004, "learning_rate": 3.89e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079933, "epoch": 0.11296897, "global_step/max_steps": "880/1000", "percentage": "88.00%", "elapsed_time": "3h 3m 28s", "remaining_time": "25m 1s"} +{"loss": 0.5967988, "acc": 0.82552185, "grad_norm": 0.20740934, "learning_rate": 3.57e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080078, "epoch": 0.11361083, "global_step/max_steps": "885/1000", "percentage": "88.50%", "elapsed_time": "3h 4m 11s", "remaining_time": "23m 56s"} +{"loss": 0.66238441, "acc": 0.81032143, "grad_norm": 0.2327508, "learning_rate": 3.27e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080218, "epoch": 0.1142527, "global_step/max_steps": "890/1000", "percentage": "89.00%", "elapsed_time": "3h 4m 54s", "remaining_time": "22m 51s"} +{"loss": 0.6185041, "acc": 0.8156251, "grad_norm": 0.24590889, "learning_rate": 2.98e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080356, "epoch": 0.11489457, "global_step/max_steps": "895/1000", "percentage": "89.50%", "elapsed_time": "3h 5m 37s", "remaining_time": "21m 46s"} +{"loss": 0.61333613, "acc": 0.81570625, "grad_norm": 0.20582289, "learning_rate": 2.71e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080474, "epoch": 0.11553644, "global_step/max_steps": "900/1000", "percentage": "90.00%", "elapsed_time": "3h 6m 23s", "remaining_time": "20m 42s"} +{"eval_loss": 0.60850674, "eval_acc": 0.8202886, "eval_runtime": 194.5686, "eval_samples_per_second": 6.466, "eval_steps_per_second": 6.466, "epoch": 0.11553644, "global_step/max_steps": "900/1000", "percentage": "90.00%", "elapsed_time": "3h 9m 37s", "remaining_time": "21m 4s"} +{"loss": 0.64109416, "acc": 0.81097269, "grad_norm": 0.23131993, "learning_rate": 2.45e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079218, "epoch": 0.11617831, "global_step/max_steps": "905/1000", "percentage": "90.50%", "elapsed_time": "3h 10m 23s", "remaining_time": "19m 59s"} +{"loss": 0.59271107, "acc": 0.82361622, "grad_norm": 0.18522906, "learning_rate": 2.2e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079368, "epoch": 0.11682018, "global_step/max_steps": "910/1000", "percentage": "91.00%", "elapsed_time": "3h 11m 5s", "remaining_time": "18m 53s"} +{"loss": 0.65264983, "acc": 0.81258793, "grad_norm": 0.21756962, "learning_rate": 1.96e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07951, "epoch": 0.11746205, "global_step/max_steps": "915/1000", "percentage": "91.50%", "elapsed_time": "3h 11m 47s", "remaining_time": "17m 49s"} +{"loss": 0.59875569, "acc": 0.82611704, "grad_norm": 0.20278232, "learning_rate": 1.74e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079655, "epoch": 0.11810392, "global_step/max_steps": "920/1000", "percentage": "92.00%", "elapsed_time": "3h 12m 29s", "remaining_time": "16m 44s"} +{"loss": 0.62275109, "acc": 0.82435198, "grad_norm": 0.2158345, "learning_rate": 1.53e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079795, "epoch": 0.11874579, "global_step/max_steps": "925/1000", "percentage": "92.50%", "elapsed_time": "3h 13m 11s", "remaining_time": "15m 39s"} +{"loss": 0.61020494, "acc": 0.81717892, "grad_norm": 0.22039002, "learning_rate": 1.33e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079939, "epoch": 0.11938766, "global_step/max_steps": "930/1000", "percentage": "93.00%", "elapsed_time": "3h 13m 53s", "remaining_time": "14m 35s"} +{"loss": 0.63481708, "acc": 0.80936031, "grad_norm": 0.21585673, "learning_rate": 1.15e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080073, "epoch": 0.12002953, "global_step/max_steps": "935/1000", "percentage": "93.50%", "elapsed_time": "3h 14m 36s", "remaining_time": "13m 31s"} +{"loss": 0.62871428, "acc": 0.81828098, "grad_norm": 0.22403887, "learning_rate": 9.8e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080211, "epoch": 0.1206714, "global_step/max_steps": "940/1000", "percentage": "94.00%", "elapsed_time": "3h 15m 18s", "remaining_time": "12m 28s"} +{"loss": 0.59829245, "acc": 0.82708139, "grad_norm": 0.22789925, "learning_rate": 8.2e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080336, "epoch": 0.12131326, "global_step/max_steps": "945/1000", "percentage": "94.50%", "elapsed_time": "3h 16m 2s", "remaining_time": "11m 24s"} +{"loss": 0.629322, "acc": 0.81116629, "grad_norm": 0.22641905, "learning_rate": 6.8e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080481, "epoch": 0.12195513, "global_step/max_steps": "950/1000", "percentage": "95.00%", "elapsed_time": "3h 16m 43s", "remaining_time": "10m 21s"} +{"eval_loss": 0.60820663, "eval_acc": 0.82018619, "eval_runtime": 194.2718, "eval_samples_per_second": 6.475, "eval_steps_per_second": 6.475, "epoch": 0.12195513, "global_step/max_steps": "950/1000", "percentage": "95.00%", "elapsed_time": "3h 19m 57s", "remaining_time": "10m 31s"} +{"loss": 0.65304608, "acc": 0.81035719, "grad_norm": 0.21176833, "learning_rate": 5.5e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079321, "epoch": 0.122597, "global_step/max_steps": "955/1000", "percentage": "95.50%", "elapsed_time": "3h 20m 39s", "remaining_time": "9m 27s"} +{"loss": 0.65838566, "acc": 0.80980167, "grad_norm": 0.23720387, "learning_rate": 4.4e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079457, "epoch": 0.12323887, "global_step/max_steps": "960/1000", "percentage": "96.00%", "elapsed_time": "3h 21m 21s", "remaining_time": "8m 23s"} +{"loss": 0.64156389, "acc": 0.81608143, "grad_norm": 0.19302094, "learning_rate": 3.3e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079569, "epoch": 0.12388074, "global_step/max_steps": "965/1000", "percentage": "96.50%", "elapsed_time": "3h 22m 7s", "remaining_time": "7m 19s"} +{"loss": 0.63968878, "acc": 0.81429224, "grad_norm": 0.2023937, "learning_rate": 2.5e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079694, "epoch": 0.12452261, "global_step/max_steps": "970/1000", "percentage": "97.00%", "elapsed_time": "3h 22m 51s", "remaining_time": "6m 16s"} +{"loss": 0.65152073, "acc": 0.80978498, "grad_norm": 0.20085211, "learning_rate": 1.7e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079826, "epoch": 0.12516448, "global_step/max_steps": "975/1000", "percentage": "97.50%", "elapsed_time": "3h 23m 33s", "remaining_time": "5m 13s"} +{"loss": 0.59241028, "acc": 0.82283268, "grad_norm": 0.23421018, "learning_rate": 1.1e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079952, "epoch": 0.12580635, "global_step/max_steps": "980/1000", "percentage": "98.00%", "elapsed_time": "3h 24m 16s", "remaining_time": "4m 10s"} +{"loss": 0.64031863, "acc": 0.81115065, "grad_norm": 0.192458, "learning_rate": 6e-08, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080066, "epoch": 0.12644822, "global_step/max_steps": "985/1000", "percentage": "98.50%", "elapsed_time": "3h 25m 1s", "remaining_time": "3m 7s"} +{"loss": 0.63289447, "acc": 0.81750393, "grad_norm": 0.21410978, "learning_rate": 3e-08, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080194, "epoch": 0.12709009, "global_step/max_steps": "990/1000", "percentage": "99.00%", "elapsed_time": "3h 25m 44s", "remaining_time": "2m 4s"} +{"loss": 0.67404447, "acc": 0.80839672, "grad_norm": 0.24657242, "learning_rate": 1e-08, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080318, "epoch": 0.12773196, "global_step/max_steps": "995/1000", "percentage": "99.50%", "elapsed_time": "3h 26m 27s", "remaining_time": "1m 2s"} +{"loss": 0.58532543, "acc": 0.82744455, "grad_norm": 0.20574874, "learning_rate": 0.0, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080433, "epoch": 0.12837382, "global_step/max_steps": "1000/1000", "percentage": "100.00%", "elapsed_time": "3h 27m 12s", "remaining_time": "0s"} +{"eval_loss": 0.60720122, "eval_acc": 0.82056814, "eval_runtime": 194.0316, "eval_samples_per_second": 6.483, "eval_steps_per_second": 6.483, "epoch": 0.12837382, "global_step/max_steps": "1000/1000", "percentage": "100.00%", "elapsed_time": "3h 30m 26s", "remaining_time": "0s"} +{"train_runtime": 12626.7242, "train_samples_per_second": 1.267, "train_steps_per_second": 0.079, "total_flos": 3.855587826431877e+17, "train_loss": 0.63581455, "epoch": 0.12837382, "global_step/max_steps": "1000/1000", "percentage": "100.00%", "elapsed_time": "3h 30m 26s", "remaining_time": "0s"} +{"memory": {"cuda": "12.90GiB"}, "last_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-1000", "best_model_checkpoint": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/checkpoint-850", "best_metric": 0.60646284, "global_step": 1000, "log_history": [{"loss": 0.82634771, "acc": 0.77952504, "grad_norm": 0.15511861443519592, "learning_rate": 2.0000000000000003e-06, "memory(GiB)": 11.42, "train_speed(iter/s)": 0.092016, "epoch": 0.0001283738245771687, "step": 1}, {"loss": 0.8159712, "acc": 0.77674872, "grad_norm": 0.14591480791568756, "learning_rate": 1e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.10552, "epoch": 0.0006418691228858435, "step": 5}, {"loss": 0.8015564, "acc": 0.77379012, "grad_norm": 0.151850163936615, "learning_rate": 2e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.107013, "epoch": 0.001283738245771687, "step": 10}, {"loss": 0.79284344, "acc": 0.7784133, "grad_norm": 0.15997682511806488, "learning_rate": 3e-05, "memory(GiB)": 12.15, "train_speed(iter/s)": 0.110995, "epoch": 0.0019256073686575307, "step": 15}, {"loss": 0.78122258, "acc": 0.7815052, "grad_norm": 0.14427673816680908, "learning_rate": 4e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.111462, "epoch": 0.002567476491543374, "step": 20}, {"loss": 0.7404335, "acc": 0.7915082, "grad_norm": 0.1590222716331482, "learning_rate": 5e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.112268, "epoch": 0.0032093456144292177, "step": 25}, {"loss": 0.68063788, "acc": 0.80291214, "grad_norm": 0.13638992607593536, "learning_rate": 6e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.111517, "epoch": 0.0038512147373150614, "step": 30}, {"loss": 0.68800621, "acc": 0.79923964, "grad_norm": 0.1271245777606964, "learning_rate": 7e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.110574, "epoch": 0.0044930838602009054, "step": 35}, {"loss": 0.69939818, "acc": 0.80240812, "grad_norm": 0.11937133222818375, "learning_rate": 8e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.109469, "epoch": 0.005134952983086748, "step": 40}, {"loss": 0.75735736, "acc": 0.78317132, "grad_norm": 0.1665358543395996, "learning_rate": 9e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.108968, "epoch": 0.005776822105972592, "step": 45}, {"loss": 0.6824338, "acc": 0.80379133, "grad_norm": 0.14883440732955933, "learning_rate": 0.0001, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.109163, "epoch": 0.0064186912288584355, "step": 50}, {"eval_loss": 0.6729312539100647, "eval_acc": 0.8081346555994846, "eval_runtime": 195.4613, "eval_samples_per_second": 6.436, "eval_steps_per_second": 6.436, "epoch": 0.0064186912288584355, "step": 50}, {"loss": 0.7141089, "acc": 0.7984889, "grad_norm": 0.16687534749507904, "learning_rate": 9.999316524962345e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078646, "epoch": 0.007060560351744279, "step": 55}, {"loss": 0.72419305, "acc": 0.79216175, "grad_norm": 0.17546051740646362, "learning_rate": 9.997266286704631e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080466, "epoch": 0.007702429474630123, "step": 60}, {"loss": 0.67717872, "acc": 0.80358973, "grad_norm": 0.16079305112361908, "learning_rate": 9.993849845741524e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082252, "epoch": 0.008344298597515967, "step": 65}, {"loss": 0.70638905, "acc": 0.80615339, "grad_norm": 0.1396234929561615, "learning_rate": 9.989068136093873e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084, "epoch": 0.008986167720401811, "step": 70}, {"loss": 0.71420946, "acc": 0.79676814, "grad_norm": 0.1340462565422058, "learning_rate": 9.98292246503335e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08542, "epoch": 0.009628036843287653, "step": 75}, {"loss": 0.71777782, "acc": 0.79325166, "grad_norm": 0.13259001076221466, "learning_rate": 9.975414512725057e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.086655, "epoch": 0.010269905966173496, "step": 80}, {"loss": 0.62526927, "acc": 0.81705523, "grad_norm": 0.15833652019500732, "learning_rate": 9.966546331768191e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.088014, "epoch": 0.01091177508905934, "step": 85}, {"loss": 0.68010745, "acc": 0.80851898, "grad_norm": 0.1456330418586731, "learning_rate": 9.956320346634876e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.088941, "epoch": 0.011553644211945184, "step": 90}, {"loss": 0.6090106, "acc": 0.81903477, "grad_norm": 0.14285945892333984, "learning_rate": 9.944739353007344e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.089902, "epoch": 0.012195513334831027, "step": 95}, {"loss": 0.59807158, "acc": 0.82483721, "grad_norm": 0.1478744000196457, "learning_rate": 9.931806517013612e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.090663, "epoch": 0.012837382457716871, "step": 100}, {"eval_loss": 0.645352840423584, "eval_acc": 0.813768508772143, "eval_runtime": 195.755, "eval_samples_per_second": 6.426, "eval_steps_per_second": 6.426, "epoch": 0.012837382457716871, "step": 100}, {"loss": 0.66537051, "acc": 0.80671978, "grad_norm": 0.15444877743721008, "learning_rate": 9.917525374361912e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078062, "epoch": 0.013479251580602715, "step": 105}, {"loss": 0.60835891, "acc": 0.81962786, "grad_norm": 0.16826578974723816, "learning_rate": 9.901899829374047e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079089, "epoch": 0.014121120703488558, "step": 110}, {"loss": 0.66763787, "acc": 0.80644588, "grad_norm": 0.1519591063261032, "learning_rate": 9.884934153917997e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08012, "epoch": 0.014762989826374402, "step": 115}, {"loss": 0.5919826, "acc": 0.8235981, "grad_norm": 0.20040030777454376, "learning_rate": 9.86663298624003e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081125, "epoch": 0.015404858949260246, "step": 120}, {"loss": 0.63266978, "acc": 0.81199884, "grad_norm": 0.1842738389968872, "learning_rate": 9.847001329696653e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082093, "epoch": 0.01604672807214609, "step": 125}, {"loss": 0.61709371, "acc": 0.81563005, "grad_norm": 0.15375380218029022, "learning_rate": 9.826044551386744e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082937, "epoch": 0.016688597195031935, "step": 130}, {"loss": 0.63595695, "acc": 0.80918331, "grad_norm": 0.14841115474700928, "learning_rate": 9.803768380684242e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083738, "epoch": 0.017330466317917778, "step": 135}, {"loss": 0.64757662, "acc": 0.81229877, "grad_norm": 0.16627077758312225, "learning_rate": 9.780178907671789e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084642, "epoch": 0.017972335440803622, "step": 140}, {"loss": 0.6832706, "acc": 0.804142, "grad_norm": 0.1714244931936264, "learning_rate": 9.755282581475769e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.085406, "epoch": 0.018614204563689465, "step": 145}, {"loss": 0.70668921, "acc": 0.79688311, "grad_norm": 0.18916593492031097, "learning_rate": 9.729086208503174e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.086183, "epoch": 0.019256073686575306, "step": 150}, {"eval_loss": 0.6350318193435669, "eval_acc": 0.8153510047395746, "eval_runtime": 196.0265, "eval_samples_per_second": 6.417, "eval_steps_per_second": 6.417, "epoch": 0.019256073686575306, "step": 150}, {"loss": 0.63387117, "acc": 0.80884809, "grad_norm": 0.17633555829524994, "learning_rate": 9.701596950580806e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078254, "epoch": 0.01989794280946115, "step": 155}, {"loss": 0.65075536, "acc": 0.81135025, "grad_norm": 0.18200528621673584, "learning_rate": 9.672822322997305e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078985, "epoch": 0.020539811932346993, "step": 160}, {"loss": 0.60177903, "acc": 0.82410259, "grad_norm": 0.14853200316429138, "learning_rate": 9.642770192448536e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079746, "epoch": 0.021181681055232836, "step": 165}, {"loss": 0.68190188, "acc": 0.80189457, "grad_norm": 0.17732569575309753, "learning_rate": 9.611448774886924e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080445, "epoch": 0.02182355017811868, "step": 170}, {"loss": 0.62211475, "acc": 0.81763601, "grad_norm": 0.3583473563194275, "learning_rate": 9.578866633275288e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081173, "epoch": 0.022465419301004524, "step": 175}, {"loss": 0.63143706, "acc": 0.81451321, "grad_norm": 0.19369152188301086, "learning_rate": 9.545032675245813e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081877, "epoch": 0.023107288423890367, "step": 180}, {"loss": 0.6451148, "acc": 0.809447, "grad_norm": 0.16049319505691528, "learning_rate": 9.509956150664796e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082533, "epoch": 0.02374915754677621, "step": 185}, {"loss": 0.65715637, "acc": 0.80372143, "grad_norm": 0.19566483795642853, "learning_rate": 9.473646649103818e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083203, "epoch": 0.024391026669662055, "step": 190}, {"loss": 0.63388405, "acc": 0.81516018, "grad_norm": 0.1836969554424286, "learning_rate": 9.43611409721806e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083851, "epoch": 0.0250328957925479, "step": 195}, {"loss": 0.65765018, "acc": 0.80683355, "grad_norm": 0.15840834379196167, "learning_rate": 9.397368756032445e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.084362, "epoch": 0.025674764915433742, "step": 200}, {"eval_loss": 0.6316511034965515, "eval_acc": 0.8154263931167957, "eval_runtime": 194.3299, "eval_samples_per_second": 6.474, "eval_steps_per_second": 6.474, "epoch": 0.025674764915433742, "step": 200}, {"loss": 0.64739652, "acc": 0.81476297, "grad_norm": 0.18683095276355743, "learning_rate": 9.357421218136386e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078515, "epoch": 0.026316634038319586, "step": 205}, {"loss": 0.65772038, "acc": 0.80957623, "grad_norm": 0.16226844489574432, "learning_rate": 9.316282404787871e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079027, "epoch": 0.02695850316120543, "step": 210}, {"loss": 0.63748703, "acc": 0.81580648, "grad_norm": 0.16426005959510803, "learning_rate": 9.273963562927695e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079584, "epoch": 0.027600372284091273, "step": 215}, {"loss": 0.66415677, "acc": 0.80812073, "grad_norm": 0.1749752312898636, "learning_rate": 9.230476262104677e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080111, "epoch": 0.028242241406977116, "step": 220}, {"loss": 0.62169385, "acc": 0.81957884, "grad_norm": 0.15272143483161926, "learning_rate": 9.185832391312644e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080603, "epoch": 0.02888411052986296, "step": 225}, {"loss": 0.6528583, "acc": 0.80860453, "grad_norm": 0.1689305603504181, "learning_rate": 9.140044155740101e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081113, "epoch": 0.029525979652748804, "step": 230}, {"loss": 0.62348075, "acc": 0.81558657, "grad_norm": 0.20389845967292786, "learning_rate": 9.093124073433463e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081633, "epoch": 0.030167848775634647, "step": 235}, {"loss": 0.54310794, "acc": 0.83771782, "grad_norm": 0.1833639293909073, "learning_rate": 9.045084971874738e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082163, "epoch": 0.03080971789852049, "step": 240}, {"loss": 0.65011134, "acc": 0.81091404, "grad_norm": 0.1823006570339203, "learning_rate": 8.995939984474624e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082662, "epoch": 0.03145158702140634, "step": 245}, {"loss": 0.61326828, "acc": 0.8202961, "grad_norm": 0.19047267735004425, "learning_rate": 8.945702546981969e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.083111, "epoch": 0.03209345614429218, "step": 250}, {"eval_loss": 0.6222989559173584, "eval_acc": 0.8174640226702884, "eval_runtime": 194.2619, "eval_samples_per_second": 6.476, "eval_steps_per_second": 6.476, "epoch": 0.03209345614429218, "step": 250}, {"loss": 0.65217943, "acc": 0.81616802, "grad_norm": 0.19024300575256348, "learning_rate": 8.894386393810563e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078534, "epoch": 0.032735325267178025, "step": 255}, {"loss": 0.65409112, "acc": 0.81027069, "grad_norm": 0.19169311225414276, "learning_rate": 8.842005554284296e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078979, "epoch": 0.03337719439006387, "step": 260}, {"loss": 0.67106547, "acc": 0.80319004, "grad_norm": 0.20081347227096558, "learning_rate": 8.788574348801675e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079517, "epoch": 0.03401906351294971, "step": 265}, {"loss": 0.57896609, "acc": 0.82499094, "grad_norm": 0.16266761720180511, "learning_rate": 8.73410738492077e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079959, "epoch": 0.034660932635835556, "step": 270}, {"loss": 0.56308613, "acc": 0.83434772, "grad_norm": 0.19760368764400482, "learning_rate": 8.678619553365659e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080441, "epoch": 0.0353028017587214, "step": 275}, {"loss": 0.62751951, "acc": 0.81103878, "grad_norm": 0.20421290397644043, "learning_rate": 8.622126023955446e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080888, "epoch": 0.035944670881607244, "step": 280}, {"loss": 0.67880988, "acc": 0.80577688, "grad_norm": 0.18944613635540009, "learning_rate": 8.564642241456986e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081351, "epoch": 0.03658654000449309, "step": 285}, {"loss": 0.63270054, "acc": 0.81629257, "grad_norm": 0.16580034792423248, "learning_rate": 8.506183921362443e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081754, "epoch": 0.03722840912737893, "step": 290}, {"loss": 0.63396297, "acc": 0.81265612, "grad_norm": 0.20476555824279785, "learning_rate": 8.44676704559283e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082163, "epoch": 0.037870278250264774, "step": 295}, {"loss": 0.63431234, "acc": 0.81665688, "grad_norm": 0.1685812920331955, "learning_rate": 8.386407858128706e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082563, "epoch": 0.03851214737315061, "step": 300}, {"eval_loss": 0.6213402152061462, "eval_acc": 0.8180910416791721, "eval_runtime": 194.9277, "eval_samples_per_second": 6.454, "eval_steps_per_second": 6.454, "epoch": 0.03851214737315061, "step": 300}, {"loss": 0.65134788, "acc": 0.81313, "grad_norm": 0.19343021512031555, "learning_rate": 8.32512286056924e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078839, "epoch": 0.039154016496036455, "step": 305}, {"loss": 0.66552057, "acc": 0.80900688, "grad_norm": 0.20626357197761536, "learning_rate": 8.262928807620843e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07924, "epoch": 0.0397958856189223, "step": 310}, {"loss": 0.6285687, "acc": 0.81944618, "grad_norm": 0.22261416912078857, "learning_rate": 8.199842702516583e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079651, "epoch": 0.04043775474180814, "step": 315}, {"loss": 0.61407933, "acc": 0.82105675, "grad_norm": 0.17977821826934814, "learning_rate": 8.135881792367686e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080053, "epoch": 0.041079623864693986, "step": 320}, {"loss": 0.63154807, "acc": 0.81391029, "grad_norm": 0.1734636276960373, "learning_rate": 8.07106356344834e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080427, "epoch": 0.04172149298757983, "step": 325}, {"loss": 0.67294674, "acc": 0.80443487, "grad_norm": 0.20138931274414062, "learning_rate": 8.005405736415126e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08081, "epoch": 0.04236336211046567, "step": 330}, {"loss": 0.62769508, "acc": 0.8138341, "grad_norm": 0.2296956181526184, "learning_rate": 7.938926261462366e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081179, "epoch": 0.04300523123335152, "step": 335}, {"loss": 0.65062008, "acc": 0.81060715, "grad_norm": 0.18877319991588593, "learning_rate": 7.871643313414718e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081555, "epoch": 0.04364710035623736, "step": 340}, {"loss": 0.65066905, "acc": 0.80925789, "grad_norm": 0.20824845135211945, "learning_rate": 7.803575286758364e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081899, "epoch": 0.044288969479123204, "step": 345}, {"loss": 0.64833279, "acc": 0.80743494, "grad_norm": 0.1929645985364914, "learning_rate": 7.734740790612136e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.082229, "epoch": 0.04493083860200905, "step": 350}, {"eval_loss": 0.6184135675430298, "eval_acc": 0.818597113383227, "eval_runtime": 195.2572, "eval_samples_per_second": 6.443, "eval_steps_per_second": 6.443, "epoch": 0.04493083860200905, "step": 350}, {"loss": 0.63578596, "acc": 0.81946774, "grad_norm": 0.185298889875412, "learning_rate": 7.66515864363997e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078909, "epoch": 0.04557270772489489, "step": 355}, {"loss": 0.59197049, "acc": 0.82359991, "grad_norm": 0.16975072026252747, "learning_rate": 7.594847868906076e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079228, "epoch": 0.046214576847780735, "step": 360}, {"loss": 0.58269887, "acc": 0.82826347, "grad_norm": 0.19332191348075867, "learning_rate": 7.52382768867422e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079527, "epoch": 0.04685644597066658, "step": 365}, {"loss": 0.62563605, "acc": 0.81692057, "grad_norm": 0.1801847517490387, "learning_rate": 7.452117519152542e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079855, "epoch": 0.04749831509355242, "step": 370}, {"loss": 0.62537222, "acc": 0.81458244, "grad_norm": 0.2671217620372772, "learning_rate": 7.379736965185368e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080167, "epoch": 0.048140184216438266, "step": 375}, {"loss": 0.6464529, "acc": 0.80892944, "grad_norm": 0.20377114415168762, "learning_rate": 7.30670581489344e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080535, "epoch": 0.04878205333932411, "step": 380}, {"loss": 0.64175944, "acc": 0.81387253, "grad_norm": 0.21851402521133423, "learning_rate": 7.233044034264034e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080866, "epoch": 0.04942392246220995, "step": 385}, {"loss": 0.65399485, "acc": 0.81104851, "grad_norm": 0.17920850217342377, "learning_rate": 7.158771761692464e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081177, "epoch": 0.0500657915850958, "step": 390}, {"loss": 0.65062542, "acc": 0.81167917, "grad_norm": 0.21850617229938507, "learning_rate": 7.083909302476453e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081491, "epoch": 0.05070766070798164, "step": 395}, {"loss": 0.62041502, "acc": 0.82351618, "grad_norm": 0.1936645656824112, "learning_rate": 7.008477123264848e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081765, "epoch": 0.051349529830867484, "step": 400}, {"eval_loss": 0.6147059202194214, "eval_acc": 0.8192219173956314, "eval_runtime": 194.2328, "eval_samples_per_second": 6.477, "eval_steps_per_second": 6.477, "epoch": 0.051349529830867484, "step": 400}, {"loss": 0.63979912, "acc": 0.81023674, "grad_norm": 0.1859249472618103, "learning_rate": 6.932495846462261e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.078921, "epoch": 0.05199139895375333, "step": 405}, {"loss": 0.63082585, "acc": 0.81422606, "grad_norm": 0.18879809975624084, "learning_rate": 6.855986244591104e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079225, "epoch": 0.05263326807663917, "step": 410}, {"loss": 0.60244231, "acc": 0.82355537, "grad_norm": 0.1991114318370819, "learning_rate": 6.778969234612584e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079522, "epoch": 0.053275137199525015, "step": 415}, {"loss": 0.68041868, "acc": 0.80394392, "grad_norm": 0.18245312571525574, "learning_rate": 6.701465872208216e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079822, "epoch": 0.05391700632241086, "step": 420}, {"loss": 0.58148174, "acc": 0.82535486, "grad_norm": 0.18471555411815643, "learning_rate": 6.623497346023418e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080165, "epoch": 0.0545588754452967, "step": 425}, {"loss": 0.64324603, "acc": 0.8145462, "grad_norm": 0.21886418759822845, "learning_rate": 6.545084971874738e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080479, "epoch": 0.055200744568182546, "step": 430}, {"loss": 0.64245248, "acc": 0.80875597, "grad_norm": 0.2046084851026535, "learning_rate": 6.466250186922325e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080772, "epoch": 0.05584261369106839, "step": 435}, {"loss": 0.63060322, "acc": 0.81591587, "grad_norm": 0.1934758424758911, "learning_rate": 6.387014543809223e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081046, "epoch": 0.05648448281395423, "step": 440}, {"loss": 0.64218235, "acc": 0.81191225, "grad_norm": 0.2059066742658615, "learning_rate": 6.307399704769099e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081334, "epoch": 0.05712635193684008, "step": 445}, {"loss": 0.64007626, "acc": 0.81284475, "grad_norm": 0.18999861180782318, "learning_rate": 6.227427435703997e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081619, "epoch": 0.05776822105972592, "step": 450}, {"eval_loss": 0.6134685277938843, "eval_acc": 0.8195972020245513, "eval_runtime": 194.9348, "eval_samples_per_second": 6.453, "eval_steps_per_second": 6.453, "epoch": 0.05776822105972592, "step": 450}, {"loss": 0.63169065, "acc": 0.81439934, "grad_norm": 0.20194242894649506, "learning_rate": 6.147119600233758e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07909, "epoch": 0.058410090182611764, "step": 455}, {"loss": 0.65331206, "acc": 0.80925694, "grad_norm": 0.22199371457099915, "learning_rate": 6.066498153718735e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079394, "epoch": 0.05905195930549761, "step": 460}, {"loss": 0.62136326, "acc": 0.81743002, "grad_norm": 0.1933964639902115, "learning_rate": 5.985585137257401e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079664, "epoch": 0.05969382842838345, "step": 465}, {"loss": 0.58844328, "acc": 0.82081652, "grad_norm": 0.19113869965076447, "learning_rate": 5.90440267166055e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079903, "epoch": 0.060335697551269295, "step": 470}, {"loss": 0.6088398, "acc": 0.82189302, "grad_norm": 0.21947172284126282, "learning_rate": 5.8229729514036705e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080178, "epoch": 0.06097756667415514, "step": 475}, {"loss": 0.62442837, "acc": 0.81938705, "grad_norm": 0.19398923218250275, "learning_rate": 5.74131823855921e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080433, "epoch": 0.06161943579704098, "step": 480}, {"loss": 0.57895641, "acc": 0.82784338, "grad_norm": 0.17412325739860535, "learning_rate": 5.6594608567103456e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080668, "epoch": 0.062261304919926826, "step": 485}, {"loss": 0.61787653, "acc": 0.82182274, "grad_norm": 0.2373647540807724, "learning_rate": 5.577423184847932e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080927, "epoch": 0.06290317404281268, "step": 490}, {"loss": 0.57188206, "acc": 0.82861795, "grad_norm": 0.18874205648899078, "learning_rate": 5.495227651252315e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081151, "epoch": 0.06354504316569852, "step": 495}, {"loss": 0.67568989, "acc": 0.80789671, "grad_norm": 0.1971614509820938, "learning_rate": 5.4128967273616625e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081405, "epoch": 0.06418691228858436, "step": 500}, {"eval_loss": 0.6154261827468872, "eval_acc": 0.8191289863904123, "eval_runtime": 194.8211, "eval_samples_per_second": 6.457, "eval_steps_per_second": 6.457, "epoch": 0.06418691228858436, "step": 500}, {"loss": 0.64408102, "acc": 0.80737734, "grad_norm": 0.2034166306257248, "learning_rate": 5.330452921628497e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079157, "epoch": 0.06482878141147021, "step": 505}, {"loss": 0.55616164, "acc": 0.83580818, "grad_norm": 0.1943274289369583, "learning_rate": 5.247918773366112e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079418, "epoch": 0.06547065053435605, "step": 510}, {"loss": 0.63107128, "acc": 0.81569843, "grad_norm": 0.21546119451522827, "learning_rate": 5.165316846586541e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079676, "epoch": 0.0661125196572419, "step": 515}, {"loss": 0.60510926, "acc": 0.82521887, "grad_norm": 0.18064647912979126, "learning_rate": 5.0826697238317935e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079928, "epoch": 0.06675438878012774, "step": 520}, {"loss": 0.65878468, "acc": 0.8060174, "grad_norm": 0.2181115299463272, "learning_rate": 5e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080188, "epoch": 0.06739625790301358, "step": 525}, {"loss": 0.61963496, "acc": 0.81847181, "grad_norm": 0.19227808713912964, "learning_rate": 4.917330276168208e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080404, "epoch": 0.06803812702589943, "step": 530}, {"loss": 0.6185873, "acc": 0.81498117, "grad_norm": 0.22034384310245514, "learning_rate": 4.834683153413459e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080637, "epoch": 0.06867999614878527, "step": 535}, {"loss": 0.6963346, "acc": 0.80154915, "grad_norm": 0.19249100983142853, "learning_rate": 4.7520812266338885e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080856, "epoch": 0.06932186527167111, "step": 540}, {"loss": 0.6188817, "acc": 0.81683502, "grad_norm": 0.1994090974330902, "learning_rate": 4.669547078371504e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081075, "epoch": 0.06996373439455696, "step": 545}, {"loss": 0.59354177, "acc": 0.82736206, "grad_norm": 0.18659113347530365, "learning_rate": 4.5871032726383386e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081266, "epoch": 0.0706056035174428, "step": 550}, {"eval_loss": 0.6139300465583801, "eval_acc": 0.8192911509362449, "eval_runtime": 200.9073, "eval_samples_per_second": 6.262, "eval_steps_per_second": 6.262, "epoch": 0.0706056035174428, "step": 550}, {"loss": 0.63172441, "acc": 0.81306267, "grad_norm": 0.17537347972393036, "learning_rate": 4.504772348747687e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079145, "epoch": 0.07124747264032864, "step": 555}, {"loss": 0.58555121, "acc": 0.82534027, "grad_norm": 0.21789848804473877, "learning_rate": 4.4225768151520694e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079394, "epoch": 0.07188934176321449, "step": 560}, {"loss": 0.59516869, "acc": 0.82140818, "grad_norm": 0.19700835645198822, "learning_rate": 4.3405391432896555e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079597, "epoch": 0.07253121088610033, "step": 565}, {"loss": 0.60017176, "acc": 0.81845322, "grad_norm": 0.1818612515926361, "learning_rate": 4.2586817614407895e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079791, "epoch": 0.07317308000898617, "step": 570}, {"loss": 0.59121842, "acc": 0.82169409, "grad_norm": 0.2091558277606964, "learning_rate": 4.17702704859633e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080013, "epoch": 0.07381494913187202, "step": 575}, {"loss": 0.64874387, "acc": 0.81168118, "grad_norm": 0.20149122178554535, "learning_rate": 4.095597328339452e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080249, "epoch": 0.07445681825475786, "step": 580}, {"loss": 0.63141985, "acc": 0.82017975, "grad_norm": 0.21395570039749146, "learning_rate": 4.0144148627425993e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080445, "epoch": 0.0750986873776437, "step": 585}, {"loss": 0.59338393, "acc": 0.8225503, "grad_norm": 0.21270450949668884, "learning_rate": 3.933501846281267e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080661, "epoch": 0.07574055650052955, "step": 590}, {"loss": 0.65440679, "acc": 0.80733299, "grad_norm": 0.21861939132213593, "learning_rate": 3.852880399766243e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080898, "epoch": 0.07638242562341538, "step": 595}, {"loss": 0.61422372, "acc": 0.81755505, "grad_norm": 0.1930130422115326, "learning_rate": 3.772572564296005e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.081091, "epoch": 0.07702429474630122, "step": 600}, {"eval_loss": 0.6109773516654968, "eval_acc": 0.8198276458076612, "eval_runtime": 195.2232, "eval_samples_per_second": 6.444, "eval_steps_per_second": 6.444, "epoch": 0.07702429474630122, "step": 600}, {"loss": 0.6057888, "acc": 0.82081652, "grad_norm": 0.20753733813762665, "learning_rate": 3.6926002952309016e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07921, "epoch": 0.07766616386918707, "step": 605}, {"loss": 0.61725841, "acc": 0.82343655, "grad_norm": 0.1979513019323349, "learning_rate": 3.612985456190778e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079401, "epoch": 0.07830803299207291, "step": 610}, {"loss": 0.62781944, "acc": 0.81410999, "grad_norm": 0.20070388913154602, "learning_rate": 3.533749813077677e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079569, "epoch": 0.07894990211495875, "step": 615}, {"loss": 0.62505813, "acc": 0.81817207, "grad_norm": 0.2327299267053604, "learning_rate": 3.4549150281252636e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079788, "epoch": 0.0795917712378446, "step": 620}, {"loss": 0.60028605, "acc": 0.82294455, "grad_norm": 0.18113943934440613, "learning_rate": 3.3765026539765834e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079975, "epoch": 0.08023364036073044, "step": 625}, {"loss": 0.61079011, "acc": 0.82047234, "grad_norm": 0.20408566296100616, "learning_rate": 3.298534127791785e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080162, "epoch": 0.08087550948361628, "step": 630}, {"loss": 0.57911015, "acc": 0.82677517, "grad_norm": 0.2132798135280609, "learning_rate": 3.221030765387417e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08036, "epoch": 0.08151737860650213, "step": 635}, {"loss": 0.60286283, "acc": 0.81979742, "grad_norm": 0.20325441658496857, "learning_rate": 3.144013755408895e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080558, "epoch": 0.08215924772938797, "step": 640}, {"loss": 0.58266845, "acc": 0.83071327, "grad_norm": 0.20148617029190063, "learning_rate": 3.0675041535377405e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080764, "epoch": 0.08280111685227382, "step": 645}, {"loss": 0.55458455, "acc": 0.83186378, "grad_norm": 0.19807127118110657, "learning_rate": 2.991522876735154e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080948, "epoch": 0.08344298597515966, "step": 650}, {"eval_loss": 0.6076882481575012, "eval_acc": 0.8209896385738762, "eval_runtime": 194.4544, "eval_samples_per_second": 6.469, "eval_steps_per_second": 6.469, "epoch": 0.08344298597515966, "step": 650}, {"loss": 0.61260557, "acc": 0.82214499, "grad_norm": 0.18806923925876617, "learning_rate": 2.916090697523549e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079195, "epoch": 0.0840848550980455, "step": 655}, {"loss": 0.59967513, "acc": 0.82406235, "grad_norm": 0.19712701439857483, "learning_rate": 2.8412282383075363e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079403, "epoch": 0.08472672422093135, "step": 660}, {"loss": 0.64144659, "acc": 0.80978308, "grad_norm": 0.19845040142536163, "learning_rate": 2.766955965735968e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079587, "epoch": 0.08536859334381719, "step": 665}, {"loss": 0.62947636, "acc": 0.81445723, "grad_norm": 0.21892952919006348, "learning_rate": 2.693294185106562e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079776, "epoch": 0.08601046246670303, "step": 670}, {"loss": 0.58508019, "acc": 0.82742786, "grad_norm": 0.21680107712745667, "learning_rate": 2.6202630348146324e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07997, "epoch": 0.08665233158958888, "step": 675}, {"loss": 0.60457458, "acc": 0.82206249, "grad_norm": 0.19368013739585876, "learning_rate": 2.547882480847461e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080131, "epoch": 0.08729420071247472, "step": 680}, {"loss": 0.61911306, "acc": 0.8187645, "grad_norm": 0.21237029135227203, "learning_rate": 2.476172311325783e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080301, "epoch": 0.08793606983536056, "step": 685}, {"loss": 0.63167734, "acc": 0.81704865, "grad_norm": 0.22553302347660065, "learning_rate": 2.405152131093926e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080481, "epoch": 0.08857793895824641, "step": 690}, {"loss": 0.63321238, "acc": 0.81163187, "grad_norm": 0.21230626106262207, "learning_rate": 2.3348413563600325e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080651, "epoch": 0.08921980808113225, "step": 695}, {"loss": 0.61235924, "acc": 0.81947212, "grad_norm": 0.23210006952285767, "learning_rate": 2.2652592093878666e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08085, "epoch": 0.0898616772040181, "step": 700}, {"eval_loss": 0.6076461672782898, "eval_acc": 0.8203855599214145, "eval_runtime": 194.4087, "eval_samples_per_second": 6.471, "eval_steps_per_second": 6.471, "epoch": 0.0898616772040181, "step": 700}, {"loss": 0.63990374, "acc": 0.81527042, "grad_norm": 0.20815226435661316, "learning_rate": 2.196424713241637e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079227, "epoch": 0.09050354632690394, "step": 705}, {"loss": 0.59049015, "acc": 0.82444172, "grad_norm": 0.21324452757835388, "learning_rate": 2.128356686585282e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079404, "epoch": 0.09114541544978978, "step": 710}, {"loss": 0.60989962, "acc": 0.81617746, "grad_norm": 0.19047819077968597, "learning_rate": 2.061073738537635e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079576, "epoch": 0.09178728457267563, "step": 715}, {"loss": 0.67080445, "acc": 0.80728264, "grad_norm": 0.2062956988811493, "learning_rate": 1.9945942635848748e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079742, "epoch": 0.09242915369556147, "step": 720}, {"loss": 0.61908646, "acc": 0.81671677, "grad_norm": 0.19861043989658356, "learning_rate": 1.928936436551661e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079905, "epoch": 0.09307102281844731, "step": 725}, {"loss": 0.66370716, "acc": 0.81090012, "grad_norm": 0.19133475422859192, "learning_rate": 1.8641182076323148e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08006, "epoch": 0.09371289194133316, "step": 730}, {"loss": 0.66476107, "acc": 0.81192856, "grad_norm": 0.22429423034191132, "learning_rate": 1.800157297483417e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080239, "epoch": 0.094354761064219, "step": 735}, {"loss": 0.58692684, "acc": 0.82513466, "grad_norm": 0.21653637290000916, "learning_rate": 1.7370711923791567e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080402, "epoch": 0.09499663018710484, "step": 740}, {"loss": 0.57462683, "acc": 0.82555256, "grad_norm": 0.17780368030071259, "learning_rate": 1.6748771394307585e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080553, "epoch": 0.09563849930999069, "step": 745}, {"loss": 0.61962047, "acc": 0.81813164, "grad_norm": 0.2015465795993805, "learning_rate": 1.6135921418712956e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080707, "epoch": 0.09628036843287653, "step": 750}, {"eval_loss": 0.6083427667617798, "eval_acc": 0.8204207990619473, "eval_runtime": 194.7163, "eval_samples_per_second": 6.461, "eval_steps_per_second": 6.461, "epoch": 0.09628036843287653, "step": 750}, {"loss": 0.61750922, "acc": 0.82061501, "grad_norm": 0.2477208524942398, "learning_rate": 1.553232954407171e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079226, "epoch": 0.09692223755576237, "step": 755}, {"loss": 0.61280818, "acc": 0.81846237, "grad_norm": 0.22278401255607605, "learning_rate": 1.4938160786375572e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079391, "epoch": 0.09756410667864822, "step": 760}, {"loss": 0.63006077, "acc": 0.81434851, "grad_norm": 0.22640761733055115, "learning_rate": 1.435357758543015e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079552, "epoch": 0.09820597580153406, "step": 765}, {"loss": 0.63865561, "acc": 0.81086941, "grad_norm": 0.20250476896762848, "learning_rate": 1.3778739760445552e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079713, "epoch": 0.0988478449244199, "step": 770}, {"loss": 0.63764729, "acc": 0.81333466, "grad_norm": 0.21983562409877777, "learning_rate": 1.3213804466343421e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079857, "epoch": 0.09948971404730575, "step": 775}, {"loss": 0.62097745, "acc": 0.81033506, "grad_norm": 0.21427662670612335, "learning_rate": 1.2658926150792322e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080004, "epoch": 0.1001315831701916, "step": 780}, {"loss": 0.60655851, "acc": 0.82130699, "grad_norm": 0.20593635737895966, "learning_rate": 1.2114256511983274e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080173, "epoch": 0.10077345229307744, "step": 785}, {"loss": 0.61125717, "acc": 0.82261295, "grad_norm": 0.2052464336156845, "learning_rate": 1.157994445715706e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080342, "epoch": 0.10141532141596328, "step": 790}, {"loss": 0.59510598, "acc": 0.82531328, "grad_norm": 0.17600791156291962, "learning_rate": 1.1056136061894384e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.08049, "epoch": 0.10205719053884912, "step": 795}, {"loss": 0.63478656, "acc": 0.81779881, "grad_norm": 0.2141779363155365, "learning_rate": 1.0542974530180327e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080624, "epoch": 0.10269905966173497, "step": 800}, {"eval_loss": 0.6077002882957458, "eval_acc": 0.8207697400203976, "eval_runtime": 194.8773, "eval_samples_per_second": 6.455, "eval_steps_per_second": 6.455, "epoch": 0.10269905966173497, "step": 800}, {"loss": 0.66100531, "acc": 0.80902939, "grad_norm": 0.2090810388326645, "learning_rate": 1.0040600155253765e-05, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079226, "epoch": 0.10334092878462081, "step": 805}, {"loss": 0.63930345, "acc": 0.81437035, "grad_norm": 0.22697587311267853, "learning_rate": 9.549150281252633e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079387, "epoch": 0.10398279790750665, "step": 810}, {"loss": 0.63128233, "acc": 0.81263914, "grad_norm": 0.21495579183101654, "learning_rate": 9.068759265665384e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079538, "epoch": 0.1046246670303925, "step": 815}, {"loss": 0.66762576, "acc": 0.80606184, "grad_norm": 0.24026648700237274, "learning_rate": 8.599558442598998e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07969, "epoch": 0.10526653615327834, "step": 820}, {"loss": 0.56980219, "acc": 0.83144102, "grad_norm": 0.2179374396800995, "learning_rate": 8.141676086873572e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079849, "epoch": 0.10590840527616419, "step": 825}, {"loss": 0.61694736, "acc": 0.81910725, "grad_norm": 0.19496454298496246, "learning_rate": 7.695237378953223e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07997, "epoch": 0.10655027439905003, "step": 830}, {"loss": 0.64870877, "acc": 0.81330662, "grad_norm": 0.23187701404094696, "learning_rate": 7.260364370723044e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080126, "epoch": 0.10719214352193587, "step": 835}, {"loss": 0.61115222, "acc": 0.81870842, "grad_norm": 0.20400239527225494, "learning_rate": 6.837175952121306e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080258, "epoch": 0.10783401264482172, "step": 840}, {"loss": 0.61838484, "acc": 0.82128296, "grad_norm": 0.24608130753040314, "learning_rate": 6.425787818636131e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080422, "epoch": 0.10847588176770756, "step": 845}, {"loss": 0.67037339, "acc": 0.8118104, "grad_norm": 0.21192343533039093, "learning_rate": 6.026312439675552e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080553, "epoch": 0.1091177508905934, "step": 850}, {"eval_loss": 0.606462836265564, "eval_acc": 0.8208858520874116, "eval_runtime": 194.9575, "eval_samples_per_second": 6.453, "eval_steps_per_second": 6.453, "epoch": 0.1091177508905934, "step": 850}, {"loss": 0.63853312, "acc": 0.81058187, "grad_norm": 0.2256067544221878, "learning_rate": 5.6388590278194096e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079236, "epoch": 0.10975962001347925, "step": 855}, {"loss": 0.6172534, "acc": 0.8174571, "grad_norm": 0.21500875055789948, "learning_rate": 5.263533508961827e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079369, "epoch": 0.11040148913636509, "step": 860}, {"loss": 0.65724411, "acc": 0.8093504, "grad_norm": 0.23700734972953796, "learning_rate": 4.900438493352055e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07952, "epoch": 0.11104335825925093, "step": 865}, {"loss": 0.61837373, "acc": 0.81735506, "grad_norm": 0.21098878979682922, "learning_rate": 4.549673247541875e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079659, "epoch": 0.11168522738213678, "step": 870}, {"loss": 0.61365747, "acc": 0.81503067, "grad_norm": 0.20609669387340546, "learning_rate": 4.2113336672471245e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079794, "epoch": 0.11232709650502262, "step": 875}, {"loss": 0.66433964, "acc": 0.80629053, "grad_norm": 0.2180800437927246, "learning_rate": 3.885512251130763e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079933, "epoch": 0.11296896562790847, "step": 880}, {"loss": 0.5967988, "acc": 0.82552185, "grad_norm": 0.2074093371629715, "learning_rate": 3.5722980755146517e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080078, "epoch": 0.11361083475079431, "step": 885}, {"loss": 0.66238441, "acc": 0.81032143, "grad_norm": 0.232750803232193, "learning_rate": 3.271776770026963e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080218, "epoch": 0.11425270387368015, "step": 890}, {"loss": 0.6185041, "acc": 0.8156251, "grad_norm": 0.24590888619422913, "learning_rate": 2.9840304941919415e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080356, "epoch": 0.114894572996566, "step": 895}, {"loss": 0.61333613, "acc": 0.81570625, "grad_norm": 0.2058228850364685, "learning_rate": 2.7091379149682685e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080474, "epoch": 0.11553644211945184, "step": 900}, {"eval_loss": 0.6085067391395569, "eval_acc": 0.8202886005724797, "eval_runtime": 194.5686, "eval_samples_per_second": 6.466, "eval_steps_per_second": 6.466, "epoch": 0.11553644211945184, "step": 900}, {"loss": 0.64109416, "acc": 0.81097269, "grad_norm": 0.23131993412971497, "learning_rate": 2.4471741852423237e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079218, "epoch": 0.11617831124233768, "step": 905}, {"loss": 0.59271107, "acc": 0.82361622, "grad_norm": 0.18522906303405762, "learning_rate": 2.1982109232821178e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079368, "epoch": 0.11682018036522353, "step": 910}, {"loss": 0.65264983, "acc": 0.81258793, "grad_norm": 0.21756961941719055, "learning_rate": 1.962316193157593e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.07951, "epoch": 0.11746204948810937, "step": 915}, {"loss": 0.59875569, "acc": 0.82611704, "grad_norm": 0.20278231799602509, "learning_rate": 1.7395544861325718e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079655, "epoch": 0.11810391861099521, "step": 920}, {"loss": 0.62275109, "acc": 0.82435198, "grad_norm": 0.21583449840545654, "learning_rate": 1.5299867030334814e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079795, "epoch": 0.11874578773388106, "step": 925}, {"loss": 0.61020494, "acc": 0.81717892, "grad_norm": 0.22039002180099487, "learning_rate": 1.333670137599713e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079939, "epoch": 0.1193876568567669, "step": 930}, {"loss": 0.63481708, "acc": 0.80936031, "grad_norm": 0.21585673093795776, "learning_rate": 1.1506584608200367e-06, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080073, "epoch": 0.12002952597965275, "step": 935}, {"loss": 0.62871428, "acc": 0.81828098, "grad_norm": 0.22403886914253235, "learning_rate": 9.810017062595322e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080211, "epoch": 0.12067139510253859, "step": 940}, {"loss": 0.59829245, "acc": 0.82708139, "grad_norm": 0.22789925336837769, "learning_rate": 8.247462563808817e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080336, "epoch": 0.12131326422542443, "step": 945}, {"loss": 0.629322, "acc": 0.81116629, "grad_norm": 0.22641904652118683, "learning_rate": 6.819348298638839e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080481, "epoch": 0.12195513334831028, "step": 950}, {"eval_loss": 0.6082066297531128, "eval_acc": 0.8201861908583086, "eval_runtime": 194.2718, "eval_samples_per_second": 6.475, "eval_steps_per_second": 6.475, "epoch": 0.12195513334831028, "step": 950}, {"loss": 0.65304608, "acc": 0.81035719, "grad_norm": 0.21176832914352417, "learning_rate": 5.526064699265753e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079321, "epoch": 0.12259700247119612, "step": 955}, {"loss": 0.65838566, "acc": 0.80980167, "grad_norm": 0.23720386624336243, "learning_rate": 4.367965336512403e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079457, "epoch": 0.12323887159408196, "step": 960}, {"loss": 0.64156389, "acc": 0.81608143, "grad_norm": 0.19302093982696533, "learning_rate": 3.3453668231809286e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079569, "epoch": 0.12388074071696781, "step": 965}, {"loss": 0.63968878, "acc": 0.81429224, "grad_norm": 0.20239369571208954, "learning_rate": 2.458548727494292e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079694, "epoch": 0.12452260983985365, "step": 970}, {"loss": 0.65152073, "acc": 0.80978498, "grad_norm": 0.20085211098194122, "learning_rate": 1.7077534966650766e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079826, "epoch": 0.1251644789627395, "step": 975}, {"loss": 0.59241028, "acc": 0.82283268, "grad_norm": 0.23421017825603485, "learning_rate": 1.0931863906127327e-07, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.079952, "epoch": 0.12580634808562535, "step": 980}, {"loss": 0.64031863, "acc": 0.81115065, "grad_norm": 0.19245800375938416, "learning_rate": 6.150154258476315e-08, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080066, "epoch": 0.12644821720851118, "step": 985}, {"loss": 0.63289447, "acc": 0.81750393, "grad_norm": 0.21410977840423584, "learning_rate": 2.7337132953697554e-08, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080194, "epoch": 0.12709008633139704, "step": 990}, {"loss": 0.67404447, "acc": 0.80839672, "grad_norm": 0.24657242000102997, "learning_rate": 6.834750376549792e-09, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080318, "epoch": 0.12773195545428287, "step": 995}, {"loss": 0.58532543, "acc": 0.82744455, "grad_norm": 0.20574873685836792, "learning_rate": 0.0, "memory(GiB)": 12.9, "train_speed(iter/s)": 0.080433, "epoch": 0.12837382457716873, "step": 1000}, {"eval_loss": 0.6072012186050415, "eval_acc": 0.8205681371523807, "eval_runtime": 194.0316, "eval_samples_per_second": 6.483, "eval_steps_per_second": 6.483, "epoch": 0.12837382457716873, "step": 1000}, {"train_runtime": 12626.7242, "train_samples_per_second": 1.267, "train_steps_per_second": 0.079, "total_flos": 3.855587826431877e+17, "train_loss": 0.635814554810524, "epoch": 0.12837382457716873, "step": 1000}], "model_info": "PeftModelForCausalLM: 4159.3108M Params (12.6894M Trainable [0.3051%]), 0.0006M Buffers.", "dataset_info": {}, "train_time": {"train_runtime": 12626.7242, "n_train_samples": 124636, "train_samples_per_second": 9.870810356339295}} diff --git a/phi3_5-vision-instruct/v6-20241130-010713/runs/events.out.tfevents.1732900047.labGPU210.19287.0 b/phi3_5-vision-instruct/v6-20241130-010713/runs/events.out.tfevents.1732900047.labGPU210.19287.0 new file mode 100644 index 0000000000000000000000000000000000000000..6b59eee92ac595cfe009fe62d2d34c89838b1696 --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/runs/events.out.tfevents.1732900047.labGPU210.19287.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c88a0c449854cd81781eaaab18bd297f0fe73e028426ad20976ffc97c3aeac6 +size 93224 diff --git a/phi3_5-vision-instruct/v6-20241130-010713/sft_args.json b/phi3_5-vision-instruct/v6-20241130-010713/sft_args.json new file mode 100644 index 0000000000000000000000000000000000000000..88f4cf48769faec01ae68b0ea99e4e98c08a1e8d --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/sft_args.json @@ -0,0 +1,246 @@ +{ + "model_type": "phi3_5-vision-instruct", + "model_id_or_path": "/home/pzcmoe/home/zhc/llama/models/Phi-3.5-vision-instruct", + "model_revision": "main", + "full_determinism": false, + "sft_type": "lora", + "freeze_parameters": [], + "freeze_vit": false, + "freeze_parameters_ratio": 0.0, + "additional_trainable_parameters": [], + "tuner_backend": "peft", + "template_type": "phi3-vl", + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "add_output_dir_suffix": true, + "ddp_backend": null, + "ddp_find_unused_parameters": null, + "ddp_broadcast_buffers": null, + "ddp_timeout": 1800, + "seed": 42, + "resume_from_checkpoint": null, + "resume_only_model": false, + "ignore_data_skip": false, + "dtype": "bf16", + "packing": false, + "train_backend": "transformers", + "tp": 1, + "pp": 1, + "min_lr": null, + "sequence_parallel": false, + "model_kwargs": {}, + "loss_name": null, + "dataset": [ + "llamafactory/OpenO1-SFT" + ], + "val_dataset": [], + "dataset_seed": 42, + "dataset_test_ratio": 0.01, + "use_loss_scale": false, + "loss_scale_config_path": "/home/pzcmoe/home/zhc/llama/swift/swift/llm/agent/default_loss_scale_config.json", + "system": null, + "tools_prompt": "react_en", + "max_length": 2048, + "truncation_strategy": "delete", + "check_dataset_strategy": "none", + "streaming": false, + "streaming_val_size": 0, + "streaming_buffer_size": 16384, + "model_name": [ + null, + null + ], + "model_author": [ + null, + null + ], + "quant_method": null, + "quantization_bit": 0, + "hqq_axis": 0, + "hqq_dynamic_config_path": null, + "bnb_4bit_comp_dtype": "bf16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "rescale_image": -1, + "target_modules": "^(model.layers|model.vision_embed_tokens.img_projection)(?!.*(lm_head|output|emb|wte|shared)).*", + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias_trainable": "none", + "lora_dtype": null, + "lora_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "init_lora_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "rope_scaling": null, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "ia3_feedforward_modules": [], + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "neftune_noise_alpha": null, + "neftune_backend": "transformers", + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "use_liger": false, + "gradient_checkpointing": true, + "vit_use_gc": true, + "deepspeed": null, + "batch_size": 1, + "eval_batch_size": 1, + "auto_find_batch_size": false, + "num_train_epochs": 1, + "max_steps": 1000, + "optim": "adamw_torch", + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "gradient_accumulation_steps": 16, + "max_grad_norm": 1, + "predict_with_generate": false, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "eval_steps": 50, + "save_steps": 50, + "save_only_model": false, + "save_total_limit": null, + "logging_steps": 5, + "acc_steps": 1, + "dataloader_num_workers": 1, + "dataloader_pin_memory": true, + "dataloader_drop_last": false, + "push_to_hub": false, + "hub_model_id": null, + "hub_token": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "test_oom_error": false, + "disable_tqdm": false, + "lazy_tokenize": true, + "preprocess_num_proc": 1, + "use_flash_attn": null, + "ignore_args_error": false, + "check_model_is_latest": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "report_to": [ + "tensorboard" + ], + "acc_strategy": "token", + "save_on_each_node": false, + "evaluation_strategy": "steps", + "save_strategy": "steps", + "save_safetensors": true, + "gpu_memory_fraction": null, + "include_num_input_tokens_seen": false, + "local_repo_path": null, + "custom_register_path": null, + "custom_dataset_info": null, + "device_map_config": null, + "device_max_memory": [], + "max_new_tokens": 2048, + "do_sample": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "fsdp": "", + "fsdp_config": null, + "sequence_parallel_size": 1, + "model_layer_cls_name": null, + "metric_warmup_step": 0, + "fsdp_num": 1, + "per_device_train_batch_size": null, + "per_device_eval_batch_size": null, + "eval_strategy": null, + "self_cognition_sample": 0, + "train_dataset_mix_ratio": 0.0, + "train_dataset_mix_ds": [ + "ms-bench" + ], + "train_dataset_sample": -1, + "val_dataset_sample": null, + "safe_serialization": null, + "only_save_model": null, + "neftune_alpha": null, + "deepspeed_config_path": null, + "model_cache_dir": null, + "lora_dropout_p": null, + "lora_target_modules": [], + "lora_target_regex": null, + "lora_modules_to_save": [], + "boft_target_modules": [], + "boft_modules_to_save": [], + "vera_target_modules": [], + "vera_modules_to_save": [], + "ia3_target_modules": [], + "ia3_modules_to_save": [], + "custom_train_dataset_path": [], + "custom_val_dataset_path": [], + "device_map_config_path": null, + "push_hub_strategy": null, + "use_self_cognition": false, + "is_multimodal": true, + "is_vision": true, + "lora_use_embedding": false, + "lora_use_all": false, + "lora_m2s_use_embedding": false, + "lora_m2s_use_ln": false, + "torch_dtype": "torch.bfloat16", + "fp16": false, + "bf16": true, + "rank": -1, + "local_rank": -1, + "world_size": 1, + "local_world_size": 1, + "bnb_4bit_compute_dtype": "torch.bfloat16", + "load_in_4bit": false, + "load_in_8bit": false, + "train_sampler_random": true, + "train_type": "sft", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=1000, lr_scheduler_type=, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs', logging_strategy=, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=, save_steps=50, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" +} \ No newline at end of file diff --git a/phi3_5-vision-instruct/v6-20241130-010713/training_args.json b/phi3_5-vision-instruct/v6-20241130-010713/training_args.json new file mode 100644 index 0000000000000000000000000000000000000000..d3c15fabd434d4804ae360bc05c94d3531b099ac --- /dev/null +++ b/phi3_5-vision-instruct/v6-20241130-010713/training_args.json @@ -0,0 +1,155 @@ +{ + "output_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "overwrite_output_dir": false, + "do_train": false, + "do_eval": true, + "do_predict": false, + "eval_strategy": "steps", + "prediction_loss_only": false, + "per_device_train_batch_size": 1, + "per_device_eval_batch_size": 1, + "per_gpu_train_batch_size": null, + "per_gpu_eval_batch_size": null, + "gradient_accumulation_steps": 16, + "eval_accumulation_steps": null, + "eval_delay": 0, + "torch_empty_cache_steps": null, + "learning_rate": 0.0001, + "weight_decay": 0.1, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "max_grad_norm": 1, + "num_train_epochs": 1, + "max_steps": 1000, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": {}, + "warmup_ratio": 0.05, + "warmup_steps": 0, + "log_level": "passive", + "log_level_replica": "warning", + "log_on_each_node": true, + "logging_dir": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713/runs", + "logging_strategy": "steps", + "logging_first_step": true, + "logging_steps": 5, + "logging_nan_inf_filter": true, + "save_strategy": "steps", + "save_steps": 50, + "save_total_limit": null, + "save_safetensors": true, + "save_on_each_node": false, + "save_only_model": false, + "restore_callback_states_from_checkpoint": false, + "no_cuda": false, + "use_cpu": false, + "use_mps_device": false, + "seed": 42, + "data_seed": 42, + "jit_mode_eval": false, + "use_ipex": false, + "bf16": true, + "fp16": false, + "fp16_opt_level": "O1", + "half_precision_backend": "auto", + "bf16_full_eval": false, + "fp16_full_eval": false, + "tf32": null, + "local_rank": 0, + "ddp_backend": null, + "tpu_num_cores": null, + "tpu_metrics_debug": false, + "debug": [], + "dataloader_drop_last": false, + "eval_steps": 50, + "dataloader_num_workers": 1, + "dataloader_prefetch_factor": null, + "past_index": -1, + "run_name": "/home/pzcmoe/home/zhc/llama/output/phi3_5-vision-instruct/v6-20241130-010713", + "disable_tqdm": false, + "remove_unused_columns": false, + "label_names": null, + "load_best_model_at_end": false, + "metric_for_best_model": "loss", + "greater_is_better": false, + "ignore_data_skip": false, + "fsdp": [], + "fsdp_min_num_params": 0, + "fsdp_config": { + "min_num_params": 0, + "xla": false, + "xla_fsdp_v2": false, + "xla_fsdp_grad_ckpt": false + }, + "fsdp_transformer_layer_cls_to_wrap": null, + "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)", + "deepspeed": null, + "label_smoothing_factor": 0.0, + "optim": "adamw_torch", + "optim_args": null, + "adafactor": false, + "group_by_length": false, + "length_column_name": "length", + "report_to": [ + "tensorboard" + ], + "ddp_find_unused_parameters": null, + "ddp_bucket_cap_mb": null, + "ddp_broadcast_buffers": null, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": false, + "skip_memory_metrics": true, + "use_legacy_prediction_loop": false, + "push_to_hub": false, + "resume_from_checkpoint": null, + "hub_model_id": null, + "hub_strategy": "every_save", + "hub_token": null, + "hub_private_repo": false, + "hub_always_push": false, + "gradient_checkpointing": true, + "gradient_checkpointing_kwargs": null, + "include_inputs_for_metrics": false, + "include_for_metrics": [], + "eval_do_concat_batches": true, + "fp16_backend": "auto", + "evaluation_strategy": null, + "push_to_hub_model_id": null, + "push_to_hub_organization": null, + "push_to_hub_token": null, + "mp_parameters": "", + "auto_find_batch_size": false, + "full_determinism": false, + "torchdynamo": null, + "ray_scope": "last", + "ddp_timeout": 1800, + "torch_compile": false, + "torch_compile_backend": null, + "torch_compile_mode": null, + "dispatch_batches": null, + "split_batches": null, + "include_tokens_per_second": false, + "include_num_input_tokens_seen": false, + "neftune_noise_alpha": null, + "optim_target_modules": null, + "batch_eval_metrics": false, + "eval_on_start": false, + "use_liger_kernel": false, + "eval_use_gather_object": false, + "average_tokens_across_devices": false, + "sortish_sampler": false, + "predict_with_generate": false, + "generation_max_length": null, + "generation_num_beams": null, + "generation_config": "GenerationConfig {\n \"bos_token_id\": 1,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000\n}\n", + "acc_strategy": "token", + "loss_name": null, + "additional_saved_files": [], + "train_sampler_random": true, + "metric_warmup_step": 0, + "train_dataset_sample": -1, + "distributed_state": "Distributed environment: NO\nNum processes: 1\nProcess index: 0\nLocal process index: 0\nDevice: cuda\n", + "_n_gpu": 1, + "__cached__setup_devices": "device(type='cuda', index=0)", + "deepspeed_plugin": null +} \ No newline at end of file