Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 stage1_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 stage2_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+stageforobj_7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

stageforobj_7b/README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_7b_stage1_obj
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft_7b_stage1_obj
+
+This model is a fine-tuned version of [saves/qwen2.5_3d/full/sft_7b_stage1_abl_lr](https://huggingface.co/saves/qwen2.5_3d/full/sft_7b_stage1_abl_lr) on the objaverse_lvis and the scannet datasets.
+It achieves the following results on the evaluation set:
+- Loss: 3.2045
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.4.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

stageforobj_7b/added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</pointcloud>": 151669,
+  "</tool_call>": 151658,
+  "<layer_sep>": 151667,
+  "<point_patch>": 151666,
+  "<pointcloud>": 151665,
+  "<row_sep>": 151668,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

stageforobj_7b/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9976470588235293,
+    "eval_loss": 3.2044739723205566,
+    "eval_runtime": 10.7704,
+    "eval_samples_per_second": 265.729,
+    "eval_steps_per_second": 8.356,
+    "total_flos": 24084090519552.0,
+    "train_loss": 3.110305127107872,
+    "train_runtime": 1505.75,
+    "train_samples_per_second": 72.226,
+    "train_steps_per_second": 0.282
+}

stageforobj_7b/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "point_patch_size": 512,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151670
+}

stageforobj_7b/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9976470588235293,
+    "eval_loss": 3.2044739723205566,
+    "eval_runtime": 10.7704,
+    "eval_samples_per_second": 265.729,
+    "eval_steps_per_second": 8.356
+}

stageforobj_7b/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.51.3"
+}

stageforobj_7b/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b2a36175400a37ef67f8e80b9ad8c65402b3911f5e4dcb899fbe5b9f7fceb7
+size 4874836584

stageforobj_7b/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa207f3d2465388cad40b96f779f878edadbe7bce0dcd7876190de18700e677
+size 4932751008

stageforobj_7b/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401e43b605f3396f5204854a4b19b420e45037022f581b18262d96e0a755062c
+size 4330865200

stageforobj_7b/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1763a0d490e79b83bb75119276365fbdec4803d561e60435781a14c4e421b188
+size 1087170688

stageforobj_7b/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15225584640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

stageforobj_7b/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

stageforobj_7b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0753d5702df82d1b95a420b85e1d0087f2694c4698707a8c69ae45fc22da41f5
+size 11422839

stageforobj_7b/tokenizer_config.json

@@ -0,0 +1,249 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<pointcloud>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<point_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<layer_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<row_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</pointcloud>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

stageforobj_7b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9976470588235293,
+    "total_flos": 24084090519552.0,
+    "train_loss": 3.110305127107872,
+    "train_runtime": 1505.75,
+    "train_samples_per_second": 72.226,
+    "train_steps_per_second": 0.282
+}

stageforobj_7b/trainer_log.jsonl

@@ -0,0 +1,43 @@
+{"current_steps": 10, "total_steps": 424, "loss": 4.5309, "lr": 2.0930232558139536e-06, "epoch": 0.047058823529411764, "percentage": 2.36, "elapsed_time": "0:00:39", "remaining_time": "0:27:24"}
+{"current_steps": 20, "total_steps": 424, "loss": 4.6651, "lr": 4.418604651162791e-06, "epoch": 0.09411764705882353, "percentage": 4.72, "elapsed_time": "0:01:14", "remaining_time": "0:24:57"}
+{"current_steps": 30, "total_steps": 424, "loss": 4.1549, "lr": 6.744186046511628e-06, "epoch": 0.1411764705882353, "percentage": 7.08, "elapsed_time": "0:01:48", "remaining_time": "0:23:40"}
+{"current_steps": 40, "total_steps": 424, "loss": 4.2405, "lr": 9.069767441860465e-06, "epoch": 0.18823529411764706, "percentage": 9.43, "elapsed_time": "0:02:22", "remaining_time": "0:22:43"}
+{"current_steps": 50, "total_steps": 424, "loss": 4.1437, "lr": 9.993882081071307e-06, "epoch": 0.23529411764705882, "percentage": 11.79, "elapsed_time": "0:02:56", "remaining_time": "0:21:57"}
+{"current_steps": 60, "total_steps": 424, "loss": 3.8467, "lr": 9.956549003010122e-06, "epoch": 0.2823529411764706, "percentage": 14.15, "elapsed_time": "0:03:30", "remaining_time": "0:21:14"}
+{"current_steps": 70, "total_steps": 424, "loss": 3.7309, "lr": 9.885535069181163e-06, "epoch": 0.32941176470588235, "percentage": 16.51, "elapsed_time": "0:04:03", "remaining_time": "0:20:33"}
+{"current_steps": 80, "total_steps": 424, "loss": 3.8004, "lr": 9.781322835100639e-06, "epoch": 0.3764705882352941, "percentage": 18.87, "elapsed_time": "0:04:37", "remaining_time": "0:19:54"}
+{"current_steps": 90, "total_steps": 424, "loss": 3.67, "lr": 9.644620446138078e-06, "epoch": 0.4235294117647059, "percentage": 21.23, "elapsed_time": "0:05:11", "remaining_time": "0:19:17"}
+{"current_steps": 100, "total_steps": 424, "loss": 3.5809, "lr": 9.476356825510613e-06, "epoch": 0.47058823529411764, "percentage": 23.58, "elapsed_time": "0:05:45", "remaining_time": "0:18:40"}
+{"current_steps": 110, "total_steps": 424, "loss": 3.5833, "lr": 9.27767536204258e-06, "epoch": 0.5176470588235295, "percentage": 25.94, "elapsed_time": "0:06:19", "remaining_time": "0:18:03"}
+{"current_steps": 120, "total_steps": 424, "loss": 3.4652, "lr": 9.049926140583487e-06, "epoch": 0.5647058823529412, "percentage": 28.3, "elapsed_time": "0:06:53", "remaining_time": "0:17:27"}
+{"current_steps": 130, "total_steps": 424, "loss": 3.5311, "lr": 8.794656767880394e-06, "epoch": 0.611764705882353, "percentage": 30.66, "elapsed_time": "0:07:27", "remaining_time": "0:16:51"}
+{"current_steps": 140, "total_steps": 424, "loss": 3.4362, "lr": 8.513601856244951e-06, "epoch": 0.6588235294117647, "percentage": 33.02, "elapsed_time": "0:08:01", "remaining_time": "0:16:16"}
+{"current_steps": 150, "total_steps": 424, "loss": 3.3697, "lr": 8.208671236475945e-06, "epoch": 0.7058823529411765, "percentage": 35.38, "elapsed_time": "0:08:35", "remaining_time": "0:15:41"}
+{"current_steps": 160, "total_steps": 424, "loss": 3.4514, "lr": 7.881936980133118e-06, "epoch": 0.7529411764705882, "percentage": 37.74, "elapsed_time": "0:09:09", "remaining_time": "0:15:06"}
+{"current_steps": 170, "total_steps": 424, "loss": 3.415, "lr": 7.5356193193488655e-06, "epoch": 0.8, "percentage": 40.09, "elapsed_time": "0:09:43", "remaining_time": "0:14:31"}
+{"current_steps": 180, "total_steps": 424, "loss": 3.416, "lr": 7.172071559855792e-06, "epoch": 0.8470588235294118, "percentage": 42.45, "elapsed_time": "0:10:16", "remaining_time": "0:13:56"}
+{"current_steps": 190, "total_steps": 424, "loss": 3.3697, "lr": 6.793764089749473e-06, "epoch": 0.8941176470588236, "percentage": 44.81, "elapsed_time": "0:10:50", "remaining_time": "0:13:21"}
+{"current_steps": 200, "total_steps": 424, "loss": 3.3808, "lr": 6.403267592650466e-06, "epoch": 0.9411764705882353, "percentage": 47.17, "elapsed_time": "0:11:24", "remaining_time": "0:12:46"}
+{"current_steps": 210, "total_steps": 424, "loss": 3.3248, "lr": 6.003235579335851e-06, "epoch": 0.9882352941176471, "percentage": 49.53, "elapsed_time": "0:11:58", "remaining_time": "0:12:12"}
+{"current_steps": 220, "total_steps": 424, "loss": 2.9907, "lr": 5.596386356541779e-06, "epoch": 1.0376470588235294, "percentage": 51.89, "elapsed_time": "0:12:33", "remaining_time": "0:11:38"}
+{"current_steps": 230, "total_steps": 424, "loss": 2.5643, "lr": 5.185484555463026e-06, "epoch": 1.0847058823529412, "percentage": 54.25, "elapsed_time": "0:13:06", "remaining_time": "0:11:03"}
+{"current_steps": 240, "total_steps": 424, "loss": 2.5068, "lr": 4.773322345467525e-06, "epoch": 1.131764705882353, "percentage": 56.6, "elapsed_time": "0:13:40", "remaining_time": "0:10:29"}
+{"current_steps": 250, "total_steps": 424, "loss": 2.5273, "lr": 4.362700460682861e-06, "epoch": 1.1788235294117646, "percentage": 58.96, "elapsed_time": "0:14:14", "remaining_time": "0:09:54"}
+{"current_steps": 260, "total_steps": 424, "loss": 2.5001, "lr": 3.956409168383325e-06, "epoch": 1.2258823529411764, "percentage": 61.32, "elapsed_time": "0:14:47", "remaining_time": "0:09:20"}
+{"current_steps": 270, "total_steps": 424, "loss": 2.5026, "lr": 3.5572093085015683e-06, "epoch": 1.2729411764705882, "percentage": 63.68, "elapsed_time": "0:15:21", "remaining_time": "0:08:45"}
+{"current_steps": 280, "total_steps": 424, "loss": 2.527, "lr": 3.167813533105598e-06, "epoch": 1.32, "percentage": 66.04, "elapsed_time": "0:15:55", "remaining_time": "0:08:11"}
+{"current_steps": 290, "total_steps": 424, "loss": 2.4914, "lr": 2.790867873323067e-06, "epoch": 1.3670588235294119, "percentage": 68.4, "elapsed_time": "0:16:29", "remaining_time": "0:07:37"}
+{"current_steps": 300, "total_steps": 424, "loss": 2.4706, "lr": 2.4289337589697e-06, "epoch": 1.4141176470588235, "percentage": 70.75, "elapsed_time": "0:17:03", "remaining_time": "0:07:02"}
+{"current_steps": 310, "total_steps": 424, "loss": 2.5091, "lr": 2.0844706130625146e-06, "epoch": 1.4611764705882353, "percentage": 73.11, "elapsed_time": "0:17:37", "remaining_time": "0:06:28"}
+{"current_steps": 320, "total_steps": 424, "loss": 2.4765, "lr": 1.7598191394919738e-06, "epoch": 1.5082352941176471, "percentage": 75.47, "elapsed_time": "0:18:10", "remaining_time": "0:05:54"}
+{"current_steps": 330, "total_steps": 424, "loss": 2.5081, "lr": 1.4571854174170847e-06, "epoch": 1.5552941176470587, "percentage": 77.83, "elapsed_time": "0:18:44", "remaining_time": "0:05:20"}
+{"current_steps": 340, "total_steps": 424, "loss": 2.4196, "lr": 1.1786259104655562e-06, "epoch": 1.6023529411764705, "percentage": 80.19, "elapsed_time": "0:19:18", "remaining_time": "0:04:46"}
+{"current_steps": 350, "total_steps": 424, "loss": 2.4922, "lr": 9.260334926048787e-07, "epoch": 1.6494117647058824, "percentage": 82.55, "elapsed_time": "0:19:51", "remaining_time": "0:04:11"}
+{"current_steps": 360, "total_steps": 424, "loss": 2.497, "lr": 7.011245856416016e-07, "epoch": 1.696470588235294, "percentage": 84.91, "elapsed_time": "0:20:25", "remaining_time": "0:03:37"}
+{"current_steps": 370, "total_steps": 424, "loss": 2.5347, "lr": 5.054274957524075e-07, "epoch": 1.743529411764706, "percentage": 87.26, "elapsed_time": "0:20:58", "remaining_time": "0:03:03"}
+{"current_steps": 380, "total_steps": 424, "loss": 2.5013, "lr": 3.402720283028277e-07, "epoch": 1.7905882352941176, "percentage": 89.62, "elapsed_time": "0:21:32", "remaining_time": "0:02:29"}
+{"current_steps": 390, "total_steps": 424, "loss": 2.4669, "lr": 2.0678045152324798e-07, "epoch": 1.8376470588235294, "percentage": 91.98, "elapsed_time": "0:22:06", "remaining_time": "0:01:55"}
+{"current_steps": 400, "total_steps": 424, "loss": 2.4493, "lr": 1.0585987044602009e-07, "epoch": 1.8847058823529412, "percentage": 94.34, "elapsed_time": "0:22:39", "remaining_time": "0:01:21"}
+{"current_steps": 410, "total_steps": 424, "loss": 2.4777, "lr": 3.819606292448541e-08, "epoch": 1.9317647058823528, "percentage": 96.7, "elapsed_time": "0:23:13", "remaining_time": "0:00:47"}
+{"current_steps": 420, "total_steps": 424, "loss": 2.4466, "lr": 4.248819619533384e-09, "epoch": 1.9788235294117649, "percentage": 99.06, "elapsed_time": "0:23:46", "remaining_time": "0:00:13"}
+{"current_steps": 424, "total_steps": 424, "epoch": 1.9976470588235293, "percentage": 100.0, "elapsed_time": "0:24:39", "remaining_time": "0:00:00"}

stageforobj_7b/trainer_state.json

@@ -0,0 +1,346 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9976470588235293,
+  "eval_steps": 1000,
+  "global_step": 424,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047058823529411764,
+      "grad_norm": 8.788684230920598,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 4.5309,
+      "step": 10
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 6.998727390050895,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 4.6651,
+      "step": 20
+    },
+    {
+      "epoch": 0.1411764705882353,
+      "grad_norm": 6.515681208989748,
+      "learning_rate": 6.744186046511628e-06,
+      "loss": 4.1549,
+      "step": 30
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 7.605880411600852,
+      "learning_rate": 9.069767441860465e-06,
+      "loss": 4.2405,
+      "step": 40
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 7.177988115005756,
+      "learning_rate": 9.993882081071307e-06,
+      "loss": 4.1437,
+      "step": 50
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 5.4652025894786345,
+      "learning_rate": 9.956549003010122e-06,
+      "loss": 3.8467,
+      "step": 60
+    },
+    {
+      "epoch": 0.32941176470588235,
+      "grad_norm": 4.8629872323573125,
+      "learning_rate": 9.885535069181163e-06,
+      "loss": 3.7309,
+      "step": 70
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 5.365982162427207,
+      "learning_rate": 9.781322835100639e-06,
+      "loss": 3.8004,
+      "step": 80
+    },
+    {
+      "epoch": 0.4235294117647059,
+      "grad_norm": 5.060180355669811,
+      "learning_rate": 9.644620446138078e-06,
+      "loss": 3.67,
+      "step": 90
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 5.226709815725197,
+      "learning_rate": 9.476356825510613e-06,
+      "loss": 3.5809,
+      "step": 100
+    },
+    {
+      "epoch": 0.5176470588235295,
+      "grad_norm": 4.694406891661751,
+      "learning_rate": 9.27767536204258e-06,
+      "loss": 3.5833,
+      "step": 110
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 4.654517351848249,
+      "learning_rate": 9.049926140583487e-06,
+      "loss": 3.4652,
+      "step": 120
+    },
+    {
+      "epoch": 0.611764705882353,
+      "grad_norm": 4.480886367596858,
+      "learning_rate": 8.794656767880394e-06,
+      "loss": 3.5311,
+      "step": 130
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 4.046920884054983,
+      "learning_rate": 8.513601856244951e-06,
+      "loss": 3.4362,
+      "step": 140
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 4.15095515539088,
+      "learning_rate": 8.208671236475945e-06,
+      "loss": 3.3697,
+      "step": 150
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 4.5030764145707876,
+      "learning_rate": 7.881936980133118e-06,
+      "loss": 3.4514,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.410443566139292,
+      "learning_rate": 7.5356193193488655e-06,
+      "loss": 3.415,
+      "step": 170
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 4.534330257179155,
+      "learning_rate": 7.172071559855792e-06,
+      "loss": 3.416,
+      "step": 180
+    },
+    {
+      "epoch": 0.8941176470588236,
+      "grad_norm": 4.351932423342719,
+      "learning_rate": 6.793764089749473e-06,
+      "loss": 3.3697,
+      "step": 190
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 4.718872538122695,
+      "learning_rate": 6.403267592650466e-06,
+      "loss": 3.3808,
+      "step": 200
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "grad_norm": 4.426150842075073,
+      "learning_rate": 6.003235579335851e-06,
+      "loss": 3.3248,
+      "step": 210
+    },
+    {
+      "epoch": 1.0376470588235294,
+      "grad_norm": 4.217309936309565,
+      "learning_rate": 5.596386356541779e-06,
+      "loss": 2.9907,
+      "step": 220
+    },
+    {
+      "epoch": 1.0847058823529412,
+      "grad_norm": 4.722636153559949,
+      "learning_rate": 5.185484555463026e-06,
+      "loss": 2.5643,
+      "step": 230
+    },
+    {
+      "epoch": 1.131764705882353,
+      "grad_norm": 3.7876367957845325,
+      "learning_rate": 4.773322345467525e-06,
+      "loss": 2.5068,
+      "step": 240
+    },
+    {
+      "epoch": 1.1788235294117646,
+      "grad_norm": 4.346780355107672,
+      "learning_rate": 4.362700460682861e-06,
+      "loss": 2.5273,
+      "step": 250
+    },
+    {
+      "epoch": 1.2258823529411764,
+      "grad_norm": 4.25856037122792,
+      "learning_rate": 3.956409168383325e-06,
+      "loss": 2.5001,
+      "step": 260
+    },
+    {
+      "epoch": 1.2729411764705882,
+      "grad_norm": 4.327903224436647,
+      "learning_rate": 3.5572093085015683e-06,
+      "loss": 2.5026,
+      "step": 270
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 4.206792961189683,
+      "learning_rate": 3.167813533105598e-06,
+      "loss": 2.527,
+      "step": 280
+    },
+    {
+      "epoch": 1.3670588235294119,
+      "grad_norm": 4.316800527546698,
+      "learning_rate": 2.790867873323067e-06,
+      "loss": 2.4914,
+      "step": 290
+    },
+    {
+      "epoch": 1.4141176470588235,
+      "grad_norm": 4.328573695674155,
+      "learning_rate": 2.4289337589697e-06,
+      "loss": 2.4706,
+      "step": 300
+    },
+    {
+      "epoch": 1.4611764705882353,
+      "grad_norm": 3.7826564411000017,
+      "learning_rate": 2.0844706130625146e-06,
+      "loss": 2.5091,
+      "step": 310
+    },
+    {
+      "epoch": 1.5082352941176471,
+      "grad_norm": 4.285506912188139,
+      "learning_rate": 1.7598191394919738e-06,
+      "loss": 2.4765,
+      "step": 320
+    },
+    {
+      "epoch": 1.5552941176470587,
+      "grad_norm": 4.356664186823199,
+      "learning_rate": 1.4571854174170847e-06,
+      "loss": 2.5081,
+      "step": 330
+    },
+    {
+      "epoch": 1.6023529411764705,
+      "grad_norm": 4.02145373581367,
+      "learning_rate": 1.1786259104655562e-06,
+      "loss": 2.4196,
+      "step": 340
+    },
+    {
+      "epoch": 1.6494117647058824,
+      "grad_norm": 4.439109292958898,
+      "learning_rate": 9.260334926048787e-07,
+      "loss": 2.4922,
+      "step": 350
+    },
+    {
+      "epoch": 1.696470588235294,
+      "grad_norm": 3.930078039800694,
+      "learning_rate": 7.011245856416016e-07,
+      "loss": 2.497,
+      "step": 360
+    },
+    {
+      "epoch": 1.743529411764706,
+      "grad_norm": 4.474647254392334,
+      "learning_rate": 5.054274957524075e-07,
+      "loss": 2.5347,
+      "step": 370
+    },
+    {
+      "epoch": 1.7905882352941176,
+      "grad_norm": 4.866544609218042,
+      "learning_rate": 3.402720283028277e-07,
+      "loss": 2.5013,
+      "step": 380
+    },
+    {
+      "epoch": 1.8376470588235294,
+      "grad_norm": 4.6153993454634845,
+      "learning_rate": 2.0678045152324798e-07,
+      "loss": 2.4669,
+      "step": 390
+    },
+    {
+      "epoch": 1.8847058823529412,
+      "grad_norm": 4.035106904147479,
+      "learning_rate": 1.0585987044602009e-07,
+      "loss": 2.4493,
+      "step": 400
+    },
+    {
+      "epoch": 1.9317647058823528,
+      "grad_norm": 4.213708711277714,
+      "learning_rate": 3.819606292448541e-08,
+      "loss": 2.4777,
+      "step": 410
+    },
+    {
+      "epoch": 1.9788235294117649,
+      "grad_norm": 4.6354893872633465,
+      "learning_rate": 4.248819619533384e-09,
+      "loss": 2.4466,
+      "step": 420
+    },
+    {
+      "epoch": 1.9976470588235293,
+      "step": 424,
+      "total_flos": 24084090519552.0,
+      "train_loss": 3.110305127107872,
+      "train_runtime": 1505.75,
+      "train_samples_per_second": 72.226,
+      "train_steps_per_second": 0.282
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3000,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 24084090519552.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

stageforobj_7b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef87349117ce846afb17da775ccdc2435d297469e5bb757eff9ee53346128f9
+size 7544