Training in progress, step 120

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba15576476b741f5d2c780b3510a6d84c2431ba91617313d892077caf538da5
+size 6299896

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}

config.json

@@ -0,0 +1,143 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
+    "AutoTokenizer": "Xenova/gpt-4o"
+  },
+  "bos_token_id": 199999,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "vocab_size": 200064
+}

debug.log

@@ -0,0 +1,476 @@
+[2026-01-24 12:51:56,817] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:6937] baseline 0.000GB ()
+[2026-01-24 12:51:56,820] [INFO] [axolotl.cli.config.load_cfg:259] [PID:6937] config:
+{
+  "activation_offloading": false,
+  "adapter": "lora",
+  "axolotl_config_path": "using_axolotl/lora.yml",
+  "base_model": "microsoft/Phi-4-mini-instruct",
+  "base_model_config": "microsoft/Phi-4-mini-instruct",
+  "batch_size": 8,
+  "bf16": true,
+  "capabilities": {
+    "bf16": true,
+    "compute_capability": "sm_86",
+    "fp8": false,
+    "n_gpu": 1,
+    "n_node": 1
+  },
+  "chat_template": "tokenizer_default",
+  "context_parallel_size": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_prefetch_factor": 256,
+  "dataset_num_proc": 9,
+  "datasets": [
+    {
+      "message_property_mappings": {
+        "content": "content",
+        "role": "role"
+      },
+      "path": "DannyAI/African-History-QA-Dataset",
+      "split": "train",
+      "trust_remote_code": false,
+      "type": "alpaca_chat.load_qa"
+    }
+  ],
+  "ddp": false,
+  "device": "cuda:0",
+  "dion_rank_fraction": 1.0,
+  "dion_rank_multiple_of": 1,
+  "env_capabilities": {
+    "torch_version": "2.9.1"
+  },
+  "eval_batch_size": 2,
+  "eval_causal_lm_metrics": [
+    "sacrebleu",
+    "comet",
+    "ter",
+    "chrf"
+  ],
+  "eval_max_new_tokens": 128,
+  "eval_sample_packing": false,
+  "eval_steps": 100,
+  "eval_strategy": "steps",
+  "eval_table_size": 0,
+  "experimental_skip_move_to_device": true,
+  "fp16": false,
+  "gradient_accumulation_steps": 4,
+  "gradient_checkpointing": false,
+  "hub_model_id": "DannyAI/phi4_lora_axolotl",
+  "include_tkps": true,
+  "is_falcon_derived_model": false,
+  "is_llama_derived_model": false,
+  "is_mistral_derived_model": false,
+  "learning_rate": 2e-05,
+  "lisa_layers_attribute": "model.layers",
+  "load_best_model_at_end": false,
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "local_rank": 0,
+  "logging_steps": 5,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_r": 8,
+  "lora_target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "loraplus_lr_embedding": 1e-06,
+  "lr_scheduler": "cosine",
+  "mean_resizing_embeddings": false,
+  "micro_batch_size": 2,
+  "model_config_type": "phi3",
+  "num_epochs": 10.0,
+  "optimizer": "adamw_torch",
+  "otel_metrics_host": "localhost",
+  "otel_metrics_port": 8000,
+  "output_dir": "./phi4_african_history_lora_out",
+  "pad_to_sequence_len": true,
+  "pretrain_multipack_attn": true,
+  "profiler_steps_start": 0,
+  "qlora_sharded_model_loading": false,
+  "ray_num_workers": 1,
+  "remove_unused_columns": false,
+  "resources_per_worker": {
+    "GPU": 1
+  },
+  "sample_packing": true,
+  "sample_packing_bin_size": 200,
+  "sample_packing_group_size": 100000,
+  "save_only_model": false,
+  "save_safetensors": true,
+  "save_steps": 200,
+  "save_strategy": "steps",
+  "sequence_len": 2048,
+  "shuffle_before_merging_datasets": false,
+  "shuffle_merged_datasets": true,
+  "skip_prepare_dataset": false,
+  "streaming_multipack_buffer_size": 10000,
+  "strict": false,
+  "tensor_parallel_size": 1,
+  "test_datasets": [
+    {
+      "message_property_mappings": {
+        "content": "content",
+        "role": "role"
+      },
+      "path": "DannyAI/African-History-QA-Dataset",
+      "split": "validation",
+      "trust_remote_code": false,
+      "type": "alpaca_chat.load_qa"
+    }
+  ],
+  "tiled_mlp_use_original_mlp": true,
+  "tokenizer_config": "microsoft/Phi-4-mini-instruct",
+  "tokenizer_save_jinja_files": true,
+  "tokenizer_type": "AutoTokenizer",
+  "torch_dtype": "torch.bfloat16",
+  "train_on_inputs": false,
+  "trl": {
+    "log_completions": false,
+    "mask_truncated_completions": false,
+    "ref_model_mixup_alpha": 0.9,
+    "ref_model_sync_steps": 64,
+    "scale_rewards": true,
+    "sync_ref_model": false,
+    "use_vllm": false,
+    "vllm_server_host": "0.0.0.0",
+    "vllm_server_port": 8000
+  },
+  "type_of_model": "AutoModelForCausalLM",
+  "use_otel_metrics": false,
+  "use_ray": false,
+  "use_wandb": true,
+  "val_set_size": 0.0,
+  "vllm": {
+    "device": "auto",
+    "dtype": "auto",
+    "gpu_memory_utilization": 0.9,
+    "host": "0.0.0.0",
+    "port": 8000
+  },
+  "wandb_name": "phi4_lora_axolotl",
+  "wandb_project": "phi4_african_history",
+  "warmup_steps": 10,
+  "weight_decay": 0.0,
+  "world_size": 1
+}
+[2026-01-24 12:51:58,452] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:6937] EOS: 199999 / <|endoftext|>
+[2026-01-24 12:51:58,452] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:6937] BOS: 199999 / <|endoftext|>
+[2026-01-24 12:51:58,453] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:6937] PAD: 199999 / <|endoftext|>
+[2026-01-24 12:51:58,453] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:6937] UNK: 199999 / <|endoftext|>
+[2026-01-24 12:51:58,453] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:481] [PID:6937] Unable to find prepared dataset in last_run_prepared/89363fb9438bda5d225c172d067e1ebf
+[2026-01-24 12:51:58,453] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:6937] Loading raw datasets...
+[2026-01-24 12:51:58,453] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:6937] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
+[2026-01-24 12:52:01,502] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:6937] Loading dataset: DannyAI/African-History-QA-Dataset with base_type: alpaca_chat.load_qa and prompt_style: None
+[2026-01-24 12:52:01,722] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:224] [PID:6937] min_input_len: 52
+[2026-01-24 12:52:01,722] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:226] [PID:6937] max_input_len: 179
+
+
+
+
+[2026-01-24 12:52:03,950] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:481] [PID:6937] Unable to find prepared dataset in last_run_prepared/1affaed26259409613b775fd6050f3a2
+[2026-01-24 12:52:03,951] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:6937] Loading raw datasets...
+[2026-01-24 12:52:03,951] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:6937] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
+[2026-01-24 12:52:05,236] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:6937] Loading dataset: DannyAI/African-History-QA-Dataset with base_type: alpaca_chat.load_qa and prompt_style: None
+[2026-01-24 12:52:05,446] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:224] [PID:6937] min_input_len: 54
+[2026-01-24 12:52:05,446] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:226] [PID:6937] max_input_len: 169
+
+
+
+
+[2026-01-24 12:52:07,313] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:417] [PID:6937] total_num_tokens: 205_770
+[2026-01-24 12:52:07,348] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:435] [PID:6937] `total_supervised_tokens: 94_469`
+[2026-01-24 12:52:07,377] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:6937] Using single process for pack_parallel, running sequentially.
+[2026-01-24 12:52:08,322] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:6937] Using single process for pack_parallel, running sequentially.
+[2026-01-24 12:52:08,510] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.18906092643737793
+[2026-01-24 12:52:08,511] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:6937] Using single process for pack_parallel, running sequentially.
+[2026-01-24 12:52:08,705] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.19425106048583984
+[2026-01-24 12:52:08,705] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:6937] Using single process for pack_parallel, running sequentially.
+[2026-01-24 12:52:08,914] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.20883750915527344
+[2026-01-24 12:52:08,914] [DEBUG] [axolotl.utils.samplers.multipack.pack_parallel:177] [PID:6937] Using single process for pack_parallel, running sequentially.
+[2026-01-24 12:52:09,117] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.20302033424377441
+[2026-01-24 12:52:09,156] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:6937] gather_len_batches: [51]
+[2026-01-24 12:52:09,156] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:494] [PID:6937] data_loader_len: 12
+[2026-01-24 12:52:09,156] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:510] [PID:6937] sample_packing_eff_est across ranks: [0.9850356158088235]
+[2026-01-24 12:52:09,156] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:522] [PID:6937] sample_packing_eff_est: 0.99
+[2026-01-24 12:52:09,156] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:533] [PID:6937] total_num_steps: 120
+[2026-01-24 12:52:09,157] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:6937] Maximum number of steps set at 120
+[2026-01-24 12:52:09,212] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:6937] loading tokenizer... microsoft/Phi-4-mini-instruct
+[2026-01-24 12:52:10,586] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:285] [PID:6937] EOS: 199999 / <|endoftext|>
+[2026-01-24 12:52:10,586] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:286] [PID:6937] BOS: 199999 / <|endoftext|>
+[2026-01-24 12:52:10,586] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:287] [PID:6937] PAD: 199999 / <|endoftext|>
+[2026-01-24 12:52:10,586] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:288] [PID:6937] UNK: 199999 / <|endoftext|>
+[2026-01-24 12:52:10,586] [DEBUG] [axolotl.train.setup_model_and_tokenizer:82] [PID:6937] Loading model
+[2026-01-24 12:52:10,782] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:6937] Patched Trainer.evaluation_loop with nanmean loss calculation
+[2026-01-24 12:52:10,788] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:6937] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
+[2026-01-24 12:52:10,789] [INFO] [axolotl.loaders.patch_manager._apply_multipack_patches:345] [PID:6937] Applying multipack dataloader patch for sample packing...
+
+[2026-01-24 12:52:16,277] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:347] [PID:6937] Converting modules to torch.bfloat16
+[2026-01-24 12:52:17,178] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:6937] Memory usage after model load 0.000GB ()
+trainable params: 1,572,864 || all params: 3,837,594,624 || trainable%: 0.0410
+[2026-01-24 12:52:17,232] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:6937] after adapters 0.000GB ()
+[2026-01-24 12:52:47,260] [INFO] [axolotl.train.save_initial_configs:413] [PID:6937] Pre-saving adapter config to ./phi4_african_history_lora_out...
+[2026-01-24 12:52:47,261] [INFO] [axolotl.train.save_initial_configs:417] [PID:6937] Pre-saving tokenizer to ./phi4_african_history_lora_out...
+[2026-01-24 12:52:47,558] [INFO] [axolotl.train.save_initial_configs:422] [PID:6937] Pre-saving model config to ./phi4_african_history_lora_out...
+[2026-01-24 12:52:47,563] [INFO] [axolotl.train.execute_training:212] [PID:6937] Starting trainer...
+[2026-01-24 12:52:49,594] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.7298610210418701
+[2026-01-24 12:52:50,250] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.6557362079620361
+[2026-01-24 12:52:50,759] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.5084567070007324
+[2026-01-24 12:52:51,268] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:6937] generate_batches time: 0.5085635185241699
+[2026-01-24 12:52:51,268] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:6937] gather_len_batches: [51]
+wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc.
+wandb: Currently logged in as: dannyai (dannyai-danny-the-analyst) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
+wandb: ⢿ Waiting for wandb.init()...
+
+
+
+wandb: Run data is saved locally in /workspace/wandb/run-20260124_125251-ehuutbte
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run phi4_lora_axolotl
+wandb: ⭐️ View project at https://wandb.ai/dannyai-danny-the-analyst/phi4_african_history
+wandb: 🚀 View run at https://wandb.ai/dannyai-danny-the-analyst/phi4_african_history/runs/ehuutbte
+wandb: Detected [huggingface_hub.inference] in use.
+wandb: Use W&B Weave for improved LLM call tracing. Install Weave with `pip install weave` then add `import weave` to the top of your script.
+wandb: For more information, check out the docs at: https://weave-docs.wandb.ai/
+wandb: WARNING Saving files without folders. If you want to preserve subdirectories pass base_path to wandb.save, i.e. wandb.save("/mnt/folder/file.h5", base_path="/mnt")
+wandb: WARNING Symlinked 1 file into the W&B run directory; call wandb.save again to sync new files.
+[2026-01-24 12:52:54,066] [INFO] [axolotl.utils.callbacks.on_train_begin:757] [PID:6937] The Axolotl config has been saved to the WandB run under files.
+
  0%|                                            | 0/120 [00:00<?, ?it/s][2026-01-24 12:52:54,083] [INFO] [axolotl.core.trainers.base.evaluate:400] [PID:6937] Running evaluation step...
+
+
  0%|                                            | 0/100 [00:00<?, ?it/s]
+
  2%|▋                                   | 2/100 [00:00<00:08, 11.63it/s]
+
  4%|█▍                                  | 4/100 [00:01<00:32,  2.97it/s]
+
  5%|█▊                                  | 5/100 [00:01<00:37,  2.50it/s]
+
  6%|██▏                                 | 6/100 [00:02<00:40,  2.32it/s]
+
  7%|██▌                                 | 7/100 [00:02<00:42,  2.20it/s]
+
  8%|██▉                                 | 8/100 [00:03<00:43,  2.12it/s]
+
  9%|███▏                                | 9/100 [00:03<00:45,  2.01it/s]
+
 10%|███▌                               | 10/100 [00:04<00:44,  2.00it/s]
+
 11%|███▊                               | 11/100 [00:04<00:44,  1.99it/s]
+
 12%|████▏                              | 12/100 [00:05<00:44,  1.98it/s]
+
 13%|████▌                              | 13/100 [00:05<00:45,  1.92it/s]
+
 14%|████▉                              | 14/100 [00:06<00:44,  1.94it/s]
+
 15%|█████▎                             | 15/100 [00:06<00:43,  1.94it/s]
+
 16%|█████▌                             | 16/100 [00:07<00:43,  1.95it/s]
+
 17%|█████▉                             | 17/100 [00:07<00:43,  1.91it/s]
+
 18%|██████▎                            | 18/100 [00:08<00:42,  1.93it/s]
+
 19%|██████▋                            | 19/100 [00:09<00:41,  1.94it/s]
+
 20%|███████                            | 20/100 [00:09<00:41,  1.95it/s]
+
 21%|███████▎                           | 21/100 [00:10<00:41,  1.91it/s]
+
 22%|███████▋                           | 22/100 [00:10<00:40,  1.93it/s]
+
 23%|████████                           | 23/100 [00:11<00:39,  1.94it/s]
+
 24%|████████▍                          | 24/100 [00:11<00:39,  1.95it/s]
+
 25%|████████▊                          | 25/100 [00:12<00:39,  1.90it/s]
+
 26%|█████████                          | 26/100 [00:12<00:38,  1.93it/s]
+
 27%|█████████▍                         | 27/100 [00:13<00:37,  1.94it/s]
+
 28%|█████████▊                         | 28/100 [00:13<00:37,  1.94it/s]
+
 29%|██████████▏                        | 29/100 [00:14<00:37,  1.90it/s]
+
 30%|██████████▌                        | 30/100 [00:14<00:36,  1.92it/s]
+
 31%|██████████▊                        | 31/100 [00:15<00:35,  1.93it/s]
+
 32%|███████████▏                       | 32/100 [00:15<00:35,  1.94it/s]
+
 33%|███████████▌                       | 33/100 [00:16<00:35,  1.90it/s]
+
 34%|███████████▉                       | 34/100 [00:16<00:34,  1.92it/s]
+
 35%|████████████▎                      | 35/100 [00:17<00:33,  1.93it/s]
+
 36%|████████████▌                      | 36/100 [00:17<00:33,  1.94it/s]
+
 37%|████████████▉                      | 37/100 [00:18<00:33,  1.90it/s]
+
 38%|█████████████▎                     | 38/100 [00:18<00:32,  1.92it/s]
+
 39%|█████████████▋                     | 39/100 [00:19<00:31,  1.93it/s]
+
 40%|██████████████                     | 40/100 [00:19<00:30,  1.94it/s]
+
 41%|██████████████▎                    | 41/100 [00:20<00:31,  1.90it/s]
+
 42%|██████████████▋                    | 42/100 [00:20<00:30,  1.92it/s]
+
 43%|███████████████                    | 43/100 [00:21<00:29,  1.93it/s]
+
 44%|███████████████▍                   | 44/100 [00:21<00:28,  1.94it/s]
+
 45%|███████████████▊                   | 45/100 [00:22<00:28,  1.90it/s]
+
 46%|████████████████                   | 46/100 [00:23<00:28,  1.92it/s]
+
 47%|████████████████▍                  | 47/100 [00:23<00:27,  1.93it/s]
+
 48%|████████████████▊                  | 48/100 [00:24<00:26,  1.94it/s]
+
 49%|█████████████████▏                 | 49/100 [00:24<00:26,  1.90it/s]
+
 50%|█████████████████▌                 | 50/100 [00:25<00:26,  1.92it/s]
+
 51%|█████████████████▊                 | 51/100 [00:25<00:25,  1.93it/s]
+
 52%|██████████████████▏                | 52/100 [00:26<00:24,  1.94it/s]
+
 53%|██████████████████▌                | 53/100 [00:26<00:24,  1.90it/s]
+
 54%|██████████████████▉                | 54/100 [00:27<00:23,  1.92it/s]
+
 55%|███████████████████▎               | 55/100 [00:27<00:23,  1.93it/s]
+
 56%|███████████████████▌               | 56/100 [00:28<00:22,  1.93it/s]
+
 57%|███████████████████▉               | 57/100 [00:28<00:22,  1.90it/s]
+
 58%|████████████████████▎              | 58/100 [00:29<00:21,  1.92it/s]
+
 59%|████████████████████▋              | 59/100 [00:29<00:21,  1.92it/s]
+
 60%|█████████████████████              | 60/100 [00:30<00:20,  1.93it/s]
+
 61%|█████████████████████▎             | 61/100 [00:30<00:20,  1.89it/s]
+
 62%|█████████████████████▋             | 62/100 [00:31<00:19,  1.91it/s]
+
 63%|██████████████████████             | 63/100 [00:31<00:19,  1.92it/s]
+
 64%|██████████████████████▍            | 64/100 [00:32<00:18,  1.93it/s]
+
 65%|██████████████████████▊            | 65/100 [00:32<00:18,  1.89it/s]
+
 66%|███████████████████████            | 66/100 [00:33<00:17,  1.91it/s]
+
 67%|███████████████████████▍           | 67/100 [00:34<00:17,  1.92it/s]
+
 68%|███████████████████████▊           | 68/100 [00:34<00:16,  1.93it/s]
+
 69%|████████████████████████▏          | 69/100 [00:35<00:16,  1.89it/s]
+
 70%|████████████████████████▌          | 70/100 [00:35<00:15,  1.91it/s]
+
 71%|████████████████████████▊          | 71/100 [00:36<00:15,  1.92it/s]
+
 72%|█████████████████████████▏         | 72/100 [00:36<00:14,  1.93it/s]
+
 73%|█████████████████████████▌         | 73/100 [00:37<00:14,  1.89it/s]
+
 74%|█████████████████████████▉         | 74/100 [00:37<00:13,  1.91it/s]
+
 75%|██████████████████████████▎        | 75/100 [00:38<00:13,  1.92it/s]
+
 76%|██████████████████████████▌        | 76/100 [00:38<00:12,  1.93it/s]
+
 77%|██████████████████████████▉        | 77/100 [00:39<00:12,  1.89it/s]
+
 78%|███████████████████████████▎       | 78/100 [00:39<00:11,  1.91it/s]
+
 79%|██████████████��████████████▋       | 79/100 [00:40<00:10,  1.92it/s]
+
 80%|████████████████████████████       | 80/100 [00:40<00:10,  1.92it/s]
+
 81%|████████████████████████████▎      | 81/100 [00:41<00:10,  1.88it/s]
+
 82%|████████████████████████████▋      | 82/100 [00:41<00:09,  1.91it/s]
+
 83%|█████████████████████████████      | 83/100 [00:42<00:08,  1.92it/s]
+
 84%|█████████████████████████████▍     | 84/100 [00:42<00:08,  1.92it/s]
+
 85%|█████████████████████████████▊     | 85/100 [00:43<00:07,  1.88it/s]
+
 86%|██████████████████████████████     | 86/100 [00:43<00:07,  1.90it/s]
+
 87%|██████████████████████████████▍    | 87/100 [00:44<00:06,  1.91it/s]
+
 88%|██████████████████████████████▊    | 88/100 [00:44<00:06,  1.92it/s]
+
 89%|███████████████████████████████▏   | 89/100 [00:45<00:05,  1.88it/s]
+
 90%|███████████████████████████████▌   | 90/100 [00:46<00:05,  1.90it/s]
+
 91%|███████████████████████████████▊   | 91/100 [00:46<00:04,  1.91it/s]
+
 92%|████████████████████████████████▏  | 92/100 [00:47<00:04,  1.92it/s]
+
 93%|████████████████████████████████▌  | 93/100 [00:47<00:03,  1.88it/s]
+
 94%|████████████████████████████████▉  | 94/100 [00:48<00:03,  1.90it/s]
+
 95%|█████████████████████████████████▎ | 95/100 [00:48<00:02,  1.91it/s]
+
 96%|█████████████████████████████████▌ | 96/100 [00:49<00:02,  1.92it/s]
+
 97%|█████████████████████████████████▉ | 97/100 [00:49<00:01,  1.88it/s]
+
 98%|██████████████████████████████████▎| 98/100 [00:50<00:01,  1.90it/s]
+
 99%|██████████████████████████████████▋| 99/100 [00:50<00:00,  1.91it/s]
+
                                                                         
+
                                                                         
+
  0%|                                            | 0/120 [00:53<?, ?it/s]
+
+
                                                                         
  1%|▎                                 | 1/120 [01:03<2:06:12, 63.63s/it]
  2%|▌                                 | 2/120 [01:11<1:01:02, 31.04s/it]
  2%|▉                                   | 3/120 [01:20<40:13, 20.63s/it]
  3%|█▏                                  | 4/120 [01:28<30:26, 15.74s/it]
  4%|█▌                                  | 5/120 [01:36<24:59, 13.04s/it]
                                                                         
+
  4%|█▌                                  | 5/120 [01:36<24:59, 13.04s/it]
  5%|█▊                                  | 6/120 [01:44<21:41, 11.41s/it]
  6%|██                                  | 7/120 [01:53<19:33, 10.38s/it]
  7%|██▍                                 | 8/120 [02:01<18:06,  9.70s/it]
  8%|██▋                                 | 9/120 [02:09<17:06,  9.25s/it]
  8%| | 10/120 [02:17<16:23,  8                                          
                               
+
  8%| | 10/120 [02:17<16:23,  8
  9%|█████▌                                                       | 11/120 [02:26<15:51,  8.73s/it]
 10%|████████████▍                                                                                                               | 12/120 [02:34<15:26,  8.58s/it]
 11%|█████████████▍                                                                                                              | 13/120 [02:40<14:02,  7.87s/it]
 12%|████                               | 14/120 [02:50<15:11,  8.60s/it]                                                                                         
 12%|███████▋                                                     | 15/120 [02:59<14:52,  8.50s/it]
                                                                                                   
+
 12%|███████▋                                                     | 15/120 [02:59<14:52,  8.50s/it]
 13%|████████▏                                                    | 16/120 [03:07<14:37,  8.44s/it]
 14%|████████▋                                                    | 17/120 [03:15<14:24,  8.39s/it]
 15%|█████████▏                                                   | 18/120 [03:23<14:12,  8.35s/it]
 16%|█████████▋                                                   | 19/120 [03:32<14:01,  8.34s/it]
 17%|██████████▏                                                  | 20/120 [03:40<13:51,  8.32s/it]
                                                                                                   
+
 17%|██████████▏                                                  | 20/120 [03:40<13:51,  8.32s/it]
 18%|██████████▋                                                  | 21/120 [03:48<13:42,  8.30s/it]
 18%|██████▍                            | 22/120 [03:57<13:33,  8.30s/it]                          
 19%|██████▋                            | 23/120 [04:05<13:24,  8.29s/it]
 20%|███████                            | 24/120 [04:13<13:15,  8.29s/it]
 21%|███████▎                           | 25/120 [04:21<13:07,  8.29s/it]
                                                                         
+
 21%|███████▎                           | 25/120 [04:21<13:07,  8.29s/it]
 22%|███████▌                           | 26/120 [04:28<12:02,  7.69s/it]
 22%|███████▉                           | 27/120 [04:39<13:27,  8.68s/it]
 23%|████████▏                          | 28/120 [04:47<13:07,  8.56s/it]
 24%|████████▍                          | 29/120 [04:54<12:26,  8.20s/it]
 25%|████████▊                          | 30/120 [05:03<12:19,  8.22s/it]
                                                                         
+
 25%|████████▊                          | 30/120 [05:03<12:19,  8.22s/it]
 26%|█████████                          | 31/120 [05:11<12:12,  8.23s/it]
 27%|█████████▎                         | 32/120 [05:19<12:05,  8.24s/it]
 28%|█████████▋                         | 33/120 [05:27<11:57,  8.25s/it]
 28%|█████████▉                         | 34/120 [05:36<11:50,  8.26s/it]
 29%|██████████▏                        | 35/120 [05:44<11:41,  8.26s/it]
                                                                         
+
 29%|██████████▏                        | 35/120 [05:44<11:41,  8.26s/it]
 30%|██████████▌                        | 36/120 [05:52<11:33,  8.26s/it]
 31%|██████████▊                        | 37/120 [06:01<11:25,  8.26s/it]
 32%|███████████                        | 38/120 [06:09<11:17,  8.26s/it]
 32%|███████████▍                       | 39/120 [06:15<10:20,  7.66s/it]
 33%|███████████▋                       | 40/120 [06:25<11:15,  8.44s/it]
                                                                         
+
 33%|███████████▋                       | 40/120 [06:25<11:15,  8.44s/it]
 34%|███████████▉                       | 41/120 [06:34<11:03,  8.39s/it]
 35%|████████████▎                      | 42/120 [06:42<10:52,  8.36s/it]
 36%|████████████▌                      | 43/120 [06:50<10:42,  8.34s/it]
 37%|████████████▊                      | 44/120 [06:58<10:32,  8.32s/it]
 38%|█████████████▏                     | 45/120 [07:07<10:22,  8.31s/it]
                                                                         
+
 38%|█████████████▏                     | 45/120 [07:07<10:22,  8.31s/it]
 38%|█████████████▍                     | 46/120 [07:15<10:13,  8.30s/it]
 39%|█████████████▋                     | 47/120 [07:23<10:04,  8.29s/it]
 40%|██████████████                     | 48/120 [07:32<09:56,  8.28s/it]
 41%|██████████████▎                    | 49/120 [07:39<09:27,  8.00s/it]
 42%|██████████████▌                    | 50/120 [07:47<09:25,  8.07s/it]
                                                                         
+
 42%|██████████████▌                    | 50/120 [07:47<09:25,  8.07s/it]
 42%|██████████████▉                    | 51/120 [07:55<09:20,  8.13s/it]
 43%|███████████████▏                   | 52/120 [08:02<08:34,  7.57s/it]
 44%|███████████████▍                   | 53/120 [08:12<09:17,  8.33s/it]
 45%|███████████████▊                   | 54/120 [08:20<09:08,  8.31s/it]
 46%|████████████████                   | 55/120 [08:28<08:59,  8.30s/it]
                                                                         
+
 46%|████████████████                   | 55/120 [08:28<08:59,  8.30s/it]
 47%|████████████████▎                  | 56/120 [08:37<08:50,  8.29s/it]
 48%|████████████████▋                  | 57/120 [08:45<08:41,  8.28s/it]
 48%|████████████████▉                  | 58/120 [08:53<08:33,  8.28s/it]
 49%|█████████████████▏                 | 59/120 [09:01<08:24,  8.27s/it]
 50%|█████████████████▌                 | 60/120 [09:10<08:16,  8.27s/it]
                                                                         
+
 50%|█████████████████▌                 | 60/120 [09:10<08:16,  8.27s/it]
 51%|█████████████████▊                 | 61/120 [09:18<08:08,  8.27s/it]
 52%|██████████████████                 | 62/120 [09:26<07:59,  8.27s/it]
 52%|██████████████████▍                | 63/120 [09:34<07:51,  8.27s/it]
 53%|██████████████████▋                | 64/120 [09:43<07:42,  8.27s/it]
 54%|██████████████████▉                | 65/120 [09:49<07:01,  7.66s/it]
                                                                         
+
 54%|██████████████████▉                | 65/120 [09:49<07:01,  7.66s/it]
 55%|███████████████████▎               | 66/120 [09:59<07:34,  8.42s/it]
 56%|███████████████████▌               | 67/120 [10:07<07:23,  8.38s/it]
 57%|███████████████████▊               | 68/120 [10:16<07:13,  8.34s/it]
 57%|████████████████████▏              | 69/120 [10:24<07:04,  8.32s/it]
 58%|████████████████████▍              | 70/120 [10:32<06:55,  8.30s/it]
                                                                         
+
 58%|████████████████████▍              | 70/120 [10:32<06:55,  8.30s/it]
 59%|████████████████████▋              | 71/120 [10:40<06:46,  8.30s/it]
 60%|█████████████████████              | 72/120 [10:49<06:37,  8.29s/it]
 61%|█████████████████████▎             | 73/120 [10:57<06:29,  8.28s/it]
 62%|█████████████████████▌             | 74/120 [11:04<06:07,  8.00s/it]
 62%|█████████████████████▉             | 75/120 [11:13<06:03,  8.08s/it]
                                                                         
+
 62%|█████████████████████▉             | 75/120 [11:13<06:03,  8.08s/it]
 63%|██████████████████████▏            | 76/120 [11:21<05:58,  8.14s/it]
 64%|██████████████████████▍            | 77/120 [11:29<05:51,  8.18s/it]
 65%|██████████████████████▊            | 78/120 [11:35<05:19,  7.60s/it]
 66%|███████████████████████            | 79/120 [11:46<05:44,  8.40s/it]
 67%|███████████████████████▎           | 80/120 [11:54<05:34,  8.36s/it]
                                                                         
+
 67%|███████████████████████▎           | 80/120 [11:54<05:34,  8.36s/it]
 68%|███████████████████████▋           | 81/120 [12:02<05:24,  8.33s/it]
 68%|███████████████████████▉           | 82/120 [12:10<05:15,  8.31s/it]
 69%|████████████████████████▏          | 83/120 [12:19<05:07,  8.30s/it]
 70%|████████████████████████▌          | 84/120 [12:27<04:58,  8.29s/it]
 71%|████████████████████████▊          | 85/120 [12:35<04:49,  8.28s/it]
                                                                         
+
 71%|████████████████████████▊          | 85/120 [12:35<04:49,  8.28s/it]
 72%|█████████████████████████          | 86/120 [12:43<04:41,  8.27s/it]
 72%|█████████████████████████▍         | 87/120 [12:52<04:32,  8.27s/it]
 73%|█████████████████████████▋         | 88/120 [12:59<04:15,  7.99s/it]
 74%|█████████████████████████▉         | 89/120 [13:07<04:10,  8.07s/it]
 75%|██████████████████████████▎        | 90/120 [13:16<04:03,  8.13s/it]
                                                                         
+
 75%|██████████████████████████▎        | 90/120 [13:16<04:03,  8.13s/it]
 76%|██████████████████████████▌        | 91/120 [13:22<03:39,  7.57s/it]
 77%|██████████████████████████▊        | 92/120 [13:32<03:54,  8.36s/it]
 78%|███████████████████████████▏       | 93/120 [13:39<03:37,  8.05s/it]
 78%|███████████████████████████▍       | 94/120 [13:48<03:30,  8.11s/it]
 79%|███████████████████████████▋       | 95/120 [13:56<03:23,  8.15s/it]
                                                                         
+
 79%|███████████████████████████▋       | 95/120 [13:56<03:23,  8.15s/it]
 80%|████████████████████████████       | 96/120 [14:04<03:16,  8.18s/it]
 81%|████████████████████████████▎      | 97/120 [14:12<03:08,  8.20s/it]
 82%|████████████████████████████▌      | 98/120 [14:21<03:00,  8.22s/it]
 82%|████████████████████████████▉      | 99/120 [14:29<02:52,  8.23s/it]
 83%|████████████████████████████▎     | 100/120 [14:36<02:39,  7.96s/it]
                                                                         
+
 83%|████████████████████████████▎     | 100/120 [14:36<02:39,  7.96s/it][2026-01-24 13:07:30,848] [INFO] [axolotl.core.trainers.base.evaluate:400] [PID:6937] Running evaluation step...
+
+
  0%|                                            | 0/100 [00:00<?, ?it/s]
+
  2%|▋                                   | 2/100 [00:00<00:25,  3.84it/s]
+
  3%|█                                   | 3/100 [00:01<00:35,  2.70it/s]
+
  4%|█▍                                  | 4/100 [00:01<00:41,  2.33it/s]
+
  5%|█▊                                  | 5/100 [00:02<00:54,  1.74it/s]
+
  6%|██▏                                 | 6/100 [00:02<00:52,  1.79it/s]
+
  7%|██▌                                 | 7/100 [00:03<00:50,  1.83it/s]
+
  8%|██▉                                 | 8/100 [00:03<00:49,  1.85it/s]
+
  9%|███▏                                | 9/100 [00:04<00:49,  1.83it/s]
+
 10%|███▌                               | 10/100 [00:05<00:48,  1.86it/s]
+
 11%|███▊                               | 11/100 [00:05<00:47,  1.87it/s]
+
 12%|████▏                              | 12/100 [00:06<00:46,  1.89it/s]
+
 13%|████▌                              | 13/100 [00:06<00:46,  1.85it/s]
+
 14%|████▉                              | 14/100 [00:07<00:45,  1.87it/s]
+
 15%|█████▎                             | 15/100 [00:07<00:45,  1.88it/s]
+
 16%|█████▌                             | 16/100 [00:08<00:44,  1.89it/s]
+
 17%|█████▉                             | 17/100 [00:08<00:44,  1.86it/s]
+
 18%|██████▎                            | 18/100 [00:09<00:43,  1.88it/s]
+
 19%|██████▋                            | 19/100 [00:09<00:42,  1.89it/s]
+
 20%|███████                            | 20/100 [00:10<00:42,  1.89it/s]
+
 21%|███████▎                           | 21/100 [00:10<00:42,  1.86it/s]
+
 22%|███████▋                           | 22/100 [00:11<00:41,  1.88it/s]
+
 23%|████████                           | 23/100 [00:11<00:40,  1.89it/s]
+
 24%|████████▍                          | 24/100 [00:12<00:40,  1.90it/s]
+
 25%|████████▊                          | 25/100 [00:13<00:40,  1.86it/s]
+
 26%|█████████                          | 26/100 [00:13<00:39,  1.88it/s]
+
 27%|█████████▍                         | 27/100 [00:14<00:38,  1.89it/s]
+
 28%|█████████▊                         | 28/100 [00:14<00:37,  1.90it/s]
+
 29%|██████████▏                        | 29/100 [00:15<00:38,  1.86it/s]
+
 30%|██████████▌                        | 30/100 [00:15<00:37,  1.88it/s]
+
 31%|██████████▊                        | 31/100 [00:16<00:36,  1.89it/s]
+
 32%|███████████▏                       | 32/100 [00:16<00:35,  1.90it/s]
+
 33%|███████████▌                       | 33/100 [00:17<00:36,  1.86it/s]
+
 34%|███████████▉                       | 34/100 [00:17<00:35,  1.88it/s]
+
 35%|████████████▎                      | 35/100 [00:18<00:34,  1.89it/s]
+
 36%|████████████▌                      | 36/100 [00:18<00:33,  1.90it/s]
+
 37%|████████████▉                      | 37/100 [00:19<00:33,  1.86it/s]
+
 38%|█████████████▎                     | 38/100 [00:19<00:32,  1.88it/s]
+
 39%|█████████████▋                     | 39/100 [00:20<00:32,  1.89it/s]
+
 40%|██████████████                     | 40/100 [00:21<00:31,  1.90it/s]
+
 41%|██████████████▎                    | 41/100 [00:21<00:31,  1.86it/s]
+
 42%|██████████████▋                    | 42/100 [00:22<00:30,  1.88it/s]
+
 43%|███████████████                    | 43/100 [00:22<00:30,  1.89it/s]
+
 44%|███████████████▍                   | 44/100 [00:23<00:29,  1.90it/s]
+
 45%|███████████████▊                   | 45/100 [00:23<00:29,  1.86it/s]
+
 46%|████████████████                   | 46/100 [00:24<00:28,  1.88it/s]
+
 47%|████████████████▍                  | 47/100 [00:24<00:28,  1.89it/s]
+
 48%|████████████████▊                  | 48/100 [00:25<00:27,  1.90it/s]
+
 49%|█████████████████▏                 | 49/100 [00:25<00:27,  1.86it/s]
+
 50%|█████████████████▌                 | 50/100 [00:26<00:26,  1.88it/s]
+
 51%|█████████████████▊                 | 51/100 [00:26<00:25,  1.89it/s]
+
 52%|██████████████████▏                | 52/100 [00:27<00:25,  1.89it/s]
+
 53%|██████████████████▌                | 53/100 [00:27<00:25,  1.86it/s]
+
 54%|██████████████████▉                | 54/100 [00:28<00:24,  1.88it/s]
+
 55%|███████████████████▎               | 55/100 [00:28<00:23,  1.89it/s]
+
 56%|███████████████████▌               | 56/100 [00:29<00:23,  1.89it/s]
+
 57%|███████████████████▉               | 57/100 [00:30<00:23,  1.86it/s]
+
 58%|████████████████████▎              | 58/100 [00:30<00:22,  1.88it/s]
+
 59%|████████████████████▋              | 59/100 [00:31<00:21,  1.89it/s]
+
 60%|█████████████████████              | 60/100 [00:31<00:21,  1.89it/s]
+
 61%|█████████████████████▎             | 61/100 [00:32<00:20,  1.86it/s]
+
 62%|█████████████████████▋             | 62/100 [00:32<00:20,  1.88it/s]
+
 63%|██████████████████████             | 63/100 [00:33<00:19,  1.89it/s]
+
 64%|██████████████████████▍            | 64/100 [00:33<00:18,  1.90it/s]
+
 65%|██████████████████████▊            | 65/100 [00:34<00:18,  1.86it/s]
+
 66%|███████████████████████            | 66/100 [00:34<00:18,  1.88it/s]
+
 67%|███████████████████████▍           | 67/100 [00:35<00:17,  1.89it/s]
+
 68%|███████████████████████▊           | 68/100 [00:35<00:16,  1.90it/s]
+
 69%|████████████████████████▏          | 69/100 [00:36<00:16,  1.86it/s]
+
 70%|████████████████████████▌          | 70/100 [00:36<00:15,  1.88it/s]
+
 71%|████████████████████████▊          | 71/100 [00:37<00:15,  1.89it/s]
+
 72%|█████████████████████████▏         | 72/100 [00:38<00:14,  1.90it/s]
+
 73%|█████████████████████████▌         | 73/100 [00:38<00:14,  1.86it/s]
+
 74%|█████████████████████████▉         | 74/100 [00:39<00:13,  1.88it/s]
+
 75%|██████████████████████████▎        | 75/100 [00:39<00:13,  1.89it/s]
+
 76%|██████████████████████████▌        | 76/100 [00:40<00:12,  1.89it/s]
+
 77%|██████████████████████████▉        | 77/100 [00:40<00:12,  1.86it/s]
+
 78%|███████████████████████████▎       | 78/100 [00:41<00:11,  1.88it/s]
+
 79%|███████████████████████████▋       | 79/100 [00:41<00:11,  1.89it/s]
+
 80%|████████████████████████████       | 80/100 [00:42<00:10,  1.89it/s]
+
 81%|████████████████████████████▎      | 81/100 [00:42<00:10,  1.86it/s]
+
 82%|████████████████████████████▋      | 82/100 [00:43<00:09,  1.88it/s]
+
 83%|█████████████████████████████      | 83/100 [00:43<00:08,  1.89it/s]
+
 84%|█████████████████████████████▍     | 84/100 [00:44<00:08,  1.90it/s]
+
 85%|█████████████████████████████▊     | 85/100 [00:44<00:08,  1.86it/s]
+
 86%|██████████████████████████████     | 86/100 [00:45<00:07,  1.88it/s]
+
 87%|██████████████████████████████▍    | 87/100 [00:46<00:06,  1.89it/s]
+
 88%|██████████████████████████████▊    | 88/100 [00:46<00:06,  1.90it/s]
+
 89%|███████████████████████████████▏   | 89/100 [00:47<00:05,  1.86it/s]
+
 90%|███████████████████████████████▌   | 90/100 [00:47<00:05,  1.88it/s]
+
 91%|███████████████████████████████▊   | 91/100 [00:48<00:04,  1.89it/s]
+
 92%|████████████████████████████████▏  | 92/100 [00:48<00:04,  1.90it/s]
+
 93%|████████████████████████████████▌  | 93/100 [00:49<00:03,  1.86it/s]
+
 94%|████████████████████████████████▉  | 94/100 [00:49<00:03,  1.88it/s]
+
 95%|█████████████████████████████████▎ | 95/100 [00:50<00:02,  1.89it/s]
+
 96%|█████████████████████████████████▌ | 96/100 [00:50<00:02,  1.90it/s]
+
 97%|█████████████████████████████████▉ | 97/100 [00:51<00:01,  1.86it/s]
+
 98%|██████████████████████████████████▎| 98/100 [00:51<00:01,  1.88it/s]
+
 99%|██████████████████████████████████▋| 99/100 [00:52<00:00,  1.89it/s]
+
                                                                         
+
                                                                         
+
 83%|████████████████████████████▎     | 100/120 [15:30<02:39,  7.96s/it]
+
+
                                                                         
 84%|████████████████████████████▌     | 101/120 [15:39<07:42, 24.33s/it]
 85%|████████████████████████████▉     | 102/120 [15:47<05:51, 19.51s/it]
 86%|█████████████████████████████▏    | 103/120 [15:55<04:34, 16.14s/it]
 87%|█████████████████████████████▍    | 104/120 [16:02<03:30, 13.17s/it]
 88%|█████████████████████████████▊    | 105/120 [16:12<03:04, 12.32s/it]
                                                                         
+
 88%|█████████████████████████████▊    | 105/120 [16:12<03:04, 12.32s/it]
 88%|██████████████████████████████    | 106/120 [16:20<02:35, 11.11s/it]
 89%|██████████████████████████████▎   | 107/120 [16:28<02:13, 10.26s/it]
 90%|██████████████████████████████▌   | 108/120 [16:37<01:55,  9.66s/it]
 91%|██████████████████████████████▉   | 109/120 [16:45<01:41,  9.25s/it]
 92%|███████████████████████████████▏  | 110/120 [16:53<01:29,  8.96s/it]
                                                                         
+
 92%|███████████████████████████████▏  | 110/120 [16:53<01:29,  8.96s/it]
 92%|███████████████████████████████▍  | 111/120 [17:02<01:18,  8.75s/it]
 93%|███████████████████████████████▋  | 112/120 [17:10<01:08,  8.60s/it]
 94%|████████████████████████████████  | 113/120 [17:18<00:59,  8.50s/it]
 95%|████████████████████████████████▎ | 114/120 [17:26<00:50,  8.43s/it]
 96%|████████████████████████████████▌ | 115/120 [17:35<00:41,  8.38s/it]
                                                                         
+
 96%|████████████████████████████████▌ | 115/120 [17:35<00:41,  8.38s/it]
 97%|████████████████████████████████▊ | 116/120 [17:43<00:33,  8.34s/it]
 98%|█████████████████████████████████▏| 117/120 [17:49<00:23,  7.72s/it]
 98%|█████████████████████████████████▍| 118/120 [17:59<00:16,  8.47s/it]
 99%|█████████████████████████████████▋| 119/120 [18:08<00:08,  8.41s/it]
                                                                         
+
+
                                                                         
+

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
+size 15524095

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c63c7f9cbcde7e7d09bc87889471974cc0f6f0a055096966e9ecffca626e8b2
+size 7761