Upload folder using huggingface_hub

.gitattributes

@@ -52,3 +52,4 @@ qwen2-osplan-119/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-gob-plan-119/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llama3-ob-plan-120-ckt-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llama3-ob-plan-120-ckt-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2-os-121/README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2-os-121
+  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. -->
+
+# qwen2-os-121
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct) on the osgenesis_sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3870
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.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: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1123        | 2.2427 | 500  | 0.3916          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen2-os-121/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<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
+}

qwen2-os-121/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.38697758316993713,
+    "eval_runtime": 21.0213,
+    "eval_samples_per_second": 17.839,
+    "eval_steps_per_second": 2.236,
+    "total_flos": 81298172149760.0,
+    "train_loss": 0.2715019001910861,
+    "train_runtime": 8763.6204,
+    "train_samples_per_second": 2.437,
+    "train_steps_per_second": 0.076
+}

qwen2-os-121/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2-os-121/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2-os-121/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.38697758316993713,
+    "eval_runtime": 21.0213,
+    "eval_samples_per_second": 17.839,
+    "eval_steps_per_second": 2.236
+}

qwen2-os-121/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

qwen2-os-121/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9aabf689b4213ec4c4b7c0f78176b3129fea8fbfe0fd5b8ee2d5e147247a3c7
+size 4877660776

qwen2-os-121/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3105824620eda4db1fe685737bb88e5e6b76880b012808e92949997428c7c13
+size 4932751008

qwen2-os-121/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420a4844b89db8543eb3847b6d535fe75a9eb78e2ff06f37bc5234fb3f862676
+size 4330865200

qwen2-os-121/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5093b59e8c1a358beeb5e83d5332c741d55233c53b3ff6724acc5fd58ac0501f
+size 1089994880

qwen2-os-121/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "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"
+  }
+}

qwen2-os-121/runs/Jan21_17-04-07_hgx003/events.out.tfevents.1768986401.hgx003.2686687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2964c8ae86d3cbf62ab7aaf44a2d5ab922e317c9c635f0bcff1833a51f0c9945
+size 20706

qwen2-os-121/runs/Jan21_17-04-07_hgx003/events.out.tfevents.1768995215.hgx003.2686687.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29569e6e0deb5dd9353629005dc1b9eb45e7c5913a93f42afcf4c9feb0c8840c
+size 359

qwen2-os-121/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
+  }
+}

qwen2-os-121/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

qwen2-os-121/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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,
+  "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
+}

qwen2-os-121/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 81298172149760.0,
+    "train_loss": 0.2715019001910861,
+    "train_runtime": 8763.6204,
+    "train_samples_per_second": 2.437,
+    "train_steps_per_second": 0.076
+}

qwen2-os-121/trainer_log.jsonl

@@ -0,0 +1,68 @@
+{"current_steps": 10, "total_steps": 669, "loss": 0.917, "lr": 1.3432835820895524e-06, "epoch": 0.0449438202247191, "percentage": 1.49, "elapsed_time": "0:04:37", "remaining_time": "5:05:16"}
+{"current_steps": 20, "total_steps": 669, "loss": 0.6672, "lr": 2.835820895522388e-06, "epoch": 0.0898876404494382, "percentage": 2.99, "elapsed_time": "0:07:47", "remaining_time": "4:12:50"}
+{"current_steps": 30, "total_steps": 669, "loss": 0.5808, "lr": 4.3283582089552236e-06, "epoch": 0.1348314606741573, "percentage": 4.48, "elapsed_time": "0:09:55", "remaining_time": "3:31:31"}
+{"current_steps": 40, "total_steps": 669, "loss": 0.4926, "lr": 5.820895522388061e-06, "epoch": 0.1797752808988764, "percentage": 5.98, "elapsed_time": "0:12:02", "remaining_time": "3:09:21"}
+{"current_steps": 50, "total_steps": 669, "loss": 0.4439, "lr": 7.313432835820896e-06, "epoch": 0.2247191011235955, "percentage": 7.47, "elapsed_time": "0:14:10", "remaining_time": "2:55:25"}
+{"current_steps": 60, "total_steps": 669, "loss": 0.4527, "lr": 8.805970149253732e-06, "epoch": 0.2696629213483146, "percentage": 8.97, "elapsed_time": "0:16:17", "remaining_time": "2:45:18"}
+{"current_steps": 70, "total_steps": 669, "loss": 0.4631, "lr": 9.999727665400876e-06, "epoch": 0.3146067415730337, "percentage": 10.46, "elapsed_time": "0:18:27", "remaining_time": "2:37:53"}
+{"current_steps": 80, "total_steps": 669, "loss": 0.4538, "lr": 9.990199069047216e-06, "epoch": 0.3595505617977528, "percentage": 11.96, "elapsed_time": "0:20:29", "remaining_time": "2:30:50"}
+{"current_steps": 90, "total_steps": 669, "loss": 0.4265, "lr": 9.967083394667763e-06, "epoch": 0.4044943820224719, "percentage": 13.45, "elapsed_time": "0:22:35", "remaining_time": "2:25:17"}
+{"current_steps": 100, "total_steps": 669, "loss": 0.4133, "lr": 9.93044358052752e-06, "epoch": 0.449438202247191, "percentage": 14.95, "elapsed_time": "0:24:49", "remaining_time": "2:21:13"}
+{"current_steps": 110, "total_steps": 669, "loss": 0.4326, "lr": 9.880379387779637e-06, "epoch": 0.4943820224719101, "percentage": 16.44, "elapsed_time": "0:27:03", "remaining_time": "2:17:29"}
+{"current_steps": 120, "total_steps": 669, "loss": 0.4387, "lr": 9.817027128840462e-06, "epoch": 0.5393258426966292, "percentage": 17.94, "elapsed_time": "0:29:13", "remaining_time": "2:13:42"}
+{"current_steps": 130, "total_steps": 669, "loss": 0.4069, "lr": 9.740559296244543e-06, "epoch": 0.5842696629213483, "percentage": 19.43, "elapsed_time": "0:31:18", "remaining_time": "2:09:49"}
+{"current_steps": 140, "total_steps": 669, "loss": 0.4315, "lr": 9.651184092990109e-06, "epoch": 0.6292134831460674, "percentage": 20.93, "elapsed_time": "0:33:23", "remaining_time": "2:06:10"}
+{"current_steps": 150, "total_steps": 669, "loss": 0.4056, "lr": 9.5491448656538e-06, "epoch": 0.6741573033707865, "percentage": 22.42, "elapsed_time": "0:35:29", "remaining_time": "2:02:47"}
+{"current_steps": 160, "total_steps": 669, "loss": 0.4098, "lr": 9.434719441818106e-06, "epoch": 0.7191011235955056, "percentage": 23.92, "elapsed_time": "0:37:35", "remaining_time": "1:59:34"}
+{"current_steps": 170, "total_steps": 669, "loss": 0.3986, "lr": 9.308219373615574e-06, "epoch": 0.7640449438202247, "percentage": 25.41, "elapsed_time": "0:39:40", "remaining_time": "1:56:26"}
+{"current_steps": 180, "total_steps": 669, "loss": 0.4021, "lr": 9.16998908944939e-06, "epoch": 0.8089887640449438, "percentage": 26.91, "elapsed_time": "0:41:43", "remaining_time": "1:53:20"}
+{"current_steps": 190, "total_steps": 669, "loss": 0.3702, "lr": 9.020404956200016e-06, "epoch": 0.8539325842696629, "percentage": 28.4, "elapsed_time": "0:43:50", "remaining_time": "1:50:32"}
+{"current_steps": 200, "total_steps": 669, "loss": 0.4055, "lr": 8.85987425447124e-06, "epoch": 0.898876404494382, "percentage": 29.9, "elapsed_time": "0:45:55", "remaining_time": "1:47:40"}
+{"current_steps": 210, "total_steps": 669, "loss": 0.3959, "lr": 8.688834069665819e-06, "epoch": 0.9438202247191011, "percentage": 31.39, "elapsed_time": "0:47:58", "remaining_time": "1:44:52"}
+{"current_steps": 220, "total_steps": 669, "loss": 0.3838, "lr": 8.50775010191001e-06, "epoch": 0.9887640449438202, "percentage": 32.88, "elapsed_time": "0:50:05", "remaining_time": "1:42:13"}
+{"current_steps": 230, "total_steps": 669, "loss": 0.3031, "lr": 8.317115398067289e-06, "epoch": 1.0314606741573034, "percentage": 34.38, "elapsed_time": "0:52:06", "remaining_time": "1:39:28"}
+{"current_steps": 240, "total_steps": 669, "loss": 0.2631, "lr": 8.117449009293668e-06, "epoch": 1.0764044943820226, "percentage": 35.87, "elapsed_time": "0:54:13", "remaining_time": "1:36:55"}
+{"current_steps": 250, "total_steps": 669, "loss": 0.2559, "lr": 7.909294577789765e-06, "epoch": 1.1213483146067416, "percentage": 37.37, "elapsed_time": "0:56:18", "remaining_time": "1:34:21"}
+{"current_steps": 260, "total_steps": 669, "loss": 0.2561, "lr": 7.693218856597515e-06, "epoch": 1.1662921348314608, "percentage": 38.86, "elapsed_time": "0:58:23", "remaining_time": "1:31:51"}
+{"current_steps": 270, "total_steps": 669, "loss": 0.259, "lr": 7.469810166471802e-06, "epoch": 1.2112359550561798, "percentage": 40.36, "elapsed_time": "1:00:27", "remaining_time": "1:29:20"}
+{"current_steps": 280, "total_steps": 669, "loss": 0.2587, "lr": 7.239676794028526e-06, "epoch": 1.256179775280899, "percentage": 41.85, "elapsed_time": "1:02:37", "remaining_time": "1:27:00"}
+{"current_steps": 290, "total_steps": 669, "loss": 0.2537, "lr": 7.003445335530572e-06, "epoch": 1.301123595505618, "percentage": 43.35, "elapsed_time": "1:04:47", "remaining_time": "1:24:40"}
+{"current_steps": 300, "total_steps": 669, "loss": 0.2638, "lr": 6.761758990821143e-06, "epoch": 1.346067415730337, "percentage": 44.84, "elapsed_time": "1:06:57", "remaining_time": "1:22:21"}
+{"current_steps": 310, "total_steps": 669, "loss": 0.2438, "lr": 6.515275812049644e-06, "epoch": 1.3910112359550562, "percentage": 46.34, "elapsed_time": "1:09:06", "remaining_time": "1:20:01"}
+{"current_steps": 320, "total_steps": 669, "loss": 0.2565, "lr": 6.264666911958404e-06, "epoch": 1.4359550561797754, "percentage": 47.83, "elapsed_time": "1:11:12", "remaining_time": "1:17:40"}
+{"current_steps": 330, "total_steps": 669, "loss": 0.2433, "lr": 6.0106146366086514e-06, "epoch": 1.4808988764044944, "percentage": 49.33, "elapsed_time": "1:13:16", "remaining_time": "1:15:16"}
+{"current_steps": 340, "total_steps": 669, "loss": 0.2383, "lr": 5.753810707520918e-06, "epoch": 1.5258426966292133, "percentage": 50.82, "elapsed_time": "1:15:24", "remaining_time": "1:12:57"}
+{"current_steps": 350, "total_steps": 669, "loss": 0.2712, "lr": 5.494954338288404e-06, "epoch": 1.5707865168539326, "percentage": 52.32, "elapsed_time": "1:17:28", "remaining_time": "1:10:37"}
+{"current_steps": 360, "total_steps": 669, "loss": 0.2342, "lr": 5.234750330791268e-06, "epoch": 1.6157303370786518, "percentage": 53.81, "elapsed_time": "1:19:35", "remaining_time": "1:08:19"}
+{"current_steps": 370, "total_steps": 669, "loss": 0.2483, "lr": 4.973907156195405e-06, "epoch": 1.6606741573033708, "percentage": 55.31, "elapsed_time": "1:21:43", "remaining_time": "1:06:02"}
+{"current_steps": 380, "total_steps": 669, "loss": 0.2453, "lr": 4.713135025960652e-06, "epoch": 1.7056179775280897, "percentage": 56.8, "elapsed_time": "1:23:49", "remaining_time": "1:03:44"}
+{"current_steps": 390, "total_steps": 669, "loss": 0.2353, "lr": 4.4531439581106295e-06, "epoch": 1.750561797752809, "percentage": 58.3, "elapsed_time": "1:25:53", "remaining_time": "1:01:26"}
+{"current_steps": 400, "total_steps": 669, "loss": 0.2397, "lr": 4.194641844029227e-06, "epoch": 1.7955056179775282, "percentage": 59.79, "elapsed_time": "1:27:59", "remaining_time": "0:59:10"}
+{"current_steps": 410, "total_steps": 669, "loss": 0.2218, "lr": 3.938332521047434e-06, "epoch": 1.8404494382022472, "percentage": 61.29, "elapsed_time": "1:30:13", "remaining_time": "0:56:59"}
+{"current_steps": 420, "total_steps": 669, "loss": 0.2407, "lr": 3.6849138560683305e-06, "epoch": 1.8853932584269661, "percentage": 62.78, "elapsed_time": "1:32:24", "remaining_time": "0:54:46"}
+{"current_steps": 430, "total_steps": 669, "loss": 0.2388, "lr": 3.435075845448105e-06, "epoch": 1.9303370786516854, "percentage": 64.28, "elapsed_time": "1:34:28", "remaining_time": "0:52:30"}
+{"current_steps": 440, "total_steps": 669, "loss": 0.2348, "lr": 3.189498736306584e-06, "epoch": 1.9752808988764046, "percentage": 65.77, "elapsed_time": "1:36:35", "remaining_time": "0:50:16"}
+{"current_steps": 450, "total_steps": 669, "loss": 0.1991, "lr": 2.948851174382565e-06, "epoch": 2.0179775280898875, "percentage": 67.26, "elapsed_time": "1:38:36", "remaining_time": "0:47:59"}
+{"current_steps": 460, "total_steps": 669, "loss": 0.1076, "lr": 2.7137883834768076e-06, "epoch": 2.0629213483146067, "percentage": 68.76, "elapsed_time": "1:40:39", "remaining_time": "0:45:44"}
+{"current_steps": 470, "total_steps": 669, "loss": 0.1055, "lr": 2.4849503814396624e-06, "epoch": 2.107865168539326, "percentage": 70.25, "elapsed_time": "1:42:49", "remaining_time": "0:43:32"}
+{"current_steps": 480, "total_steps": 669, "loss": 0.1051, "lr": 2.2629602375607373e-06, "epoch": 2.152808988764045, "percentage": 71.75, "elapsed_time": "1:45:02", "remaining_time": "0:41:21"}
+{"current_steps": 490, "total_steps": 669, "loss": 0.1087, "lr": 2.048422376105299e-06, "epoch": 2.197752808988764, "percentage": 73.24, "elapsed_time": "1:47:05", "remaining_time": "0:39:07"}
+{"current_steps": 500, "total_steps": 669, "loss": 0.1123, "lr": 1.8419209306164653e-06, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "1:49:16", "remaining_time": "0:36:56"}
+{"current_steps": 500, "total_steps": 669, "eval_loss": 0.39164599776268005, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "1:49:37", "remaining_time": "0:37:03"}
+{"current_steps": 510, "total_steps": 669, "loss": 0.1114, "lr": 1.6440181534640277e-06, "epoch": 2.2876404494382023, "percentage": 76.23, "elapsed_time": "1:52:02", "remaining_time": "0:34:55"}
+{"current_steps": 520, "total_steps": 669, "loss": 0.1106, "lr": 1.4552528849702852e-06, "epoch": 2.3325842696629215, "percentage": 77.73, "elapsed_time": "1:54:11", "remaining_time": "0:32:43"}
+{"current_steps": 530, "total_steps": 669, "loss": 0.1001, "lr": 1.2761390862810907e-06, "epoch": 2.3775280898876403, "percentage": 79.22, "elapsed_time": "1:56:23", "remaining_time": "0:30:31"}
+{"current_steps": 540, "total_steps": 669, "loss": 0.1078, "lr": 1.107164439976764e-06, "epoch": 2.4224719101123595, "percentage": 80.72, "elapsed_time": "1:58:29", "remaining_time": "0:28:18"}
+{"current_steps": 550, "total_steps": 669, "loss": 0.0981, "lr": 9.487890222330137e-07, "epoch": 2.4674157303370787, "percentage": 82.21, "elapsed_time": "2:00:39", "remaining_time": "0:26:06"}
+{"current_steps": 560, "total_steps": 669, "loss": 0.099, "lr": 8.014440501472909e-07, "epoch": 2.512359550561798, "percentage": 83.71, "elapsed_time": "2:02:46", "remaining_time": "0:23:53"}
+{"current_steps": 570, "total_steps": 669, "loss": 0.1082, "lr": 6.655307076412637e-07, "epoch": 2.5573033707865167, "percentage": 85.2, "elapsed_time": "2:04:52", "remaining_time": "0:21:41"}
+{"current_steps": 580, "total_steps": 669, "loss": 0.105, "lr": 5.414190531362162e-07, "epoch": 2.602247191011236, "percentage": 86.7, "elapsed_time": "2:06:59", "remaining_time": "0:19:29"}
+{"current_steps": 590, "total_steps": 669, "loss": 0.1024, "lr": 4.29447011975474e-07, "epoch": 2.647191011235955, "percentage": 88.19, "elapsed_time": "2:09:05", "remaining_time": "0:17:17"}
+{"current_steps": 600, "total_steps": 669, "loss": 0.1054, "lr": 3.299194563372604e-07, "epoch": 2.692134831460674, "percentage": 89.69, "elapsed_time": "2:11:10", "remaining_time": "0:15:05"}
+{"current_steps": 610, "total_steps": 669, "loss": 0.0948, "lr": 2.431073751431529e-07, "epoch": 2.737078651685393, "percentage": 91.18, "elapsed_time": "2:13:13", "remaining_time": "0:12:53"}
+{"current_steps": 620, "total_steps": 669, "loss": 0.1027, "lr": 1.6924713622225975e-07, "epoch": 2.7820224719101123, "percentage": 92.68, "elapsed_time": "2:15:19", "remaining_time": "0:10:41"}
+{"current_steps": 630, "total_steps": 669, "loss": 0.0962, "lr": 1.0853984274007246e-07, "epoch": 2.8269662921348315, "percentage": 94.17, "elapsed_time": "2:17:25", "remaining_time": "0:08:30"}
+{"current_steps": 640, "total_steps": 669, "loss": 0.1036, "lr": 6.115078564427946e-08, "epoch": 2.8719101123595507, "percentage": 95.67, "elapsed_time": "2:19:37", "remaining_time": "0:06:19"}
+{"current_steps": 650, "total_steps": 669, "loss": 0.0964, "lr": 2.7208993618390578e-08, "epoch": 2.9168539325842695, "percentage": 97.16, "elapsed_time": "2:21:42", "remaining_time": "0:04:08"}
+{"current_steps": 660, "total_steps": 669, "loss": 0.1032, "lr": 6.806881768539053e-09, "epoch": 2.9617977528089887, "percentage": 98.65, "elapsed_time": "2:23:50", "remaining_time": "0:01:57"}
+{"current_steps": 669, "total_steps": 669, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:26:03", "remaining_time": "0:00:00"}

qwen2-os-121/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 669,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 13.065853118896484,
+      "learning_rate": 1.3432835820895524e-06,
+      "loss": 0.917,
+      "step": 10
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 19.221128463745117,
+      "learning_rate": 2.835820895522388e-06,
+      "loss": 0.6672,
+      "step": 20
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 4.594083786010742,
+      "learning_rate": 4.3283582089552236e-06,
+      "loss": 0.5808,
+      "step": 30
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 4.076601505279541,
+      "learning_rate": 5.820895522388061e-06,
+      "loss": 0.4926,
+      "step": 40
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 3.3338639736175537,
+      "learning_rate": 7.313432835820896e-06,
+      "loss": 0.4439,
+      "step": 50
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 4.051526069641113,
+      "learning_rate": 8.805970149253732e-06,
+      "loss": 0.4527,
+      "step": 60
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": 3.7653603553771973,
+      "learning_rate": 9.999727665400876e-06,
+      "loss": 0.4631,
+      "step": 70
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 3.8603553771972656,
+      "learning_rate": 9.990199069047216e-06,
+      "loss": 0.4538,
+      "step": 80
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 3.166360378265381,
+      "learning_rate": 9.967083394667763e-06,
+      "loss": 0.4265,
+      "step": 90
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 2.982255697250366,
+      "learning_rate": 9.93044358052752e-06,
+      "loss": 0.4133,
+      "step": 100
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 2.9556069374084473,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.4326,
+      "step": 110
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 3.1054093837738037,
+      "learning_rate": 9.817027128840462e-06,
+      "loss": 0.4387,
+      "step": 120
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 2.889918804168701,
+      "learning_rate": 9.740559296244543e-06,
+      "loss": 0.4069,
+      "step": 130
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 2.890075206756592,
+      "learning_rate": 9.651184092990109e-06,
+      "loss": 0.4315,
+      "step": 140
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 3.2339141368865967,
+      "learning_rate": 9.5491448656538e-06,
+      "loss": 0.4056,
+      "step": 150
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 2.964042901992798,
+      "learning_rate": 9.434719441818106e-06,
+      "loss": 0.4098,
+      "step": 160
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 2.6165759563446045,
+      "learning_rate": 9.308219373615574e-06,
+      "loss": 0.3986,
+      "step": 170
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 2.560549020767212,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.4021,
+      "step": 180
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 2.7782649993896484,
+      "learning_rate": 9.020404956200016e-06,
+      "loss": 0.3702,
+      "step": 190
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 2.6154396533966064,
+      "learning_rate": 8.85987425447124e-06,
+      "loss": 0.4055,
+      "step": 200
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 2.7704086303710938,
+      "learning_rate": 8.688834069665819e-06,
+      "loss": 0.3959,
+      "step": 210
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 2.554821252822876,
+      "learning_rate": 8.50775010191001e-06,
+      "loss": 0.3838,
+      "step": 220
+    },
+    {
+      "epoch": 1.0314606741573034,
+      "grad_norm": 2.3032705783843994,
+      "learning_rate": 8.317115398067289e-06,
+      "loss": 0.3031,
+      "step": 230
+    },
+    {
+      "epoch": 1.0764044943820226,
+      "grad_norm": 1.8269344568252563,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.2631,
+      "step": 240
+    },
+    {
+      "epoch": 1.1213483146067416,
+      "grad_norm": 2.5574216842651367,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.2559,
+      "step": 250
+    },
+    {
+      "epoch": 1.1662921348314608,
+      "grad_norm": 2.505126953125,
+      "learning_rate": 7.693218856597515e-06,
+      "loss": 0.2561,
+      "step": 260
+    },
+    {
+      "epoch": 1.2112359550561798,
+      "grad_norm": 2.4236679077148438,
+      "learning_rate": 7.469810166471802e-06,
+      "loss": 0.259,
+      "step": 270
+    },
+    {
+      "epoch": 1.256179775280899,
+      "grad_norm": 2.1280295848846436,
+      "learning_rate": 7.239676794028526e-06,
+      "loss": 0.2587,
+      "step": 280
+    },
+    {
+      "epoch": 1.301123595505618,
+      "grad_norm": 2.421351432800293,
+      "learning_rate": 7.003445335530572e-06,
+      "loss": 0.2537,
+      "step": 290
+    },
+    {
+      "epoch": 1.346067415730337,
+      "grad_norm": 2.053130865097046,
+      "learning_rate": 6.761758990821143e-06,
+      "loss": 0.2638,
+      "step": 300
+    },
+    {
+      "epoch": 1.3910112359550562,
+      "grad_norm": 2.744643211364746,
+      "learning_rate": 6.515275812049644e-06,
+      "loss": 0.2438,
+      "step": 310
+    },
+    {
+      "epoch": 1.4359550561797754,
+      "grad_norm": 2.027100086212158,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.2565,
+      "step": 320
+    },
+    {
+      "epoch": 1.4808988764044944,
+      "grad_norm": 2.3016886711120605,
+      "learning_rate": 6.0106146366086514e-06,
+      "loss": 0.2433,
+      "step": 330
+    },
+    {
+      "epoch": 1.5258426966292133,
+      "grad_norm": 2.508007049560547,
+      "learning_rate": 5.753810707520918e-06,
+      "loss": 0.2383,
+      "step": 340
+    },
+    {
+      "epoch": 1.5707865168539326,
+      "grad_norm": 2.2673184871673584,
+      "learning_rate": 5.494954338288404e-06,
+      "loss": 0.2712,
+      "step": 350
+    },
+    {
+      "epoch": 1.6157303370786518,
+      "grad_norm": 2.4957592487335205,
+      "learning_rate": 5.234750330791268e-06,
+      "loss": 0.2342,
+      "step": 360
+    },
+    {
+      "epoch": 1.6606741573033708,
+      "grad_norm": 2.1853106021881104,
+      "learning_rate": 4.973907156195405e-06,
+      "loss": 0.2483,
+      "step": 370
+    },
+    {
+      "epoch": 1.7056179775280897,
+      "grad_norm": 1.8735578060150146,
+      "learning_rate": 4.713135025960652e-06,
+      "loss": 0.2453,
+      "step": 380
+    },
+    {
+      "epoch": 1.750561797752809,
+      "grad_norm": 2.260606288909912,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.2353,
+      "step": 390
+    },
+    {
+      "epoch": 1.7955056179775282,
+      "grad_norm": 2.2341856956481934,
+      "learning_rate": 4.194641844029227e-06,
+      "loss": 0.2397,
+      "step": 400
+    },
+    {
+      "epoch": 1.8404494382022472,
+      "grad_norm": 1.9118940830230713,
+      "learning_rate": 3.938332521047434e-06,
+      "loss": 0.2218,
+      "step": 410
+    },
+    {
+      "epoch": 1.8853932584269661,
+      "grad_norm": 2.3548195362091064,
+      "learning_rate": 3.6849138560683305e-06,
+      "loss": 0.2407,
+      "step": 420
+    },
+    {
+      "epoch": 1.9303370786516854,
+      "grad_norm": 2.4646918773651123,
+      "learning_rate": 3.435075845448105e-06,
+      "loss": 0.2388,
+      "step": 430
+    },
+    {
+      "epoch": 1.9752808988764046,
+      "grad_norm": 2.05568790435791,
+      "learning_rate": 3.189498736306584e-06,
+      "loss": 0.2348,
+      "step": 440
+    },
+    {
+      "epoch": 2.0179775280898875,
+      "grad_norm": 1.6222045421600342,
+      "learning_rate": 2.948851174382565e-06,
+      "loss": 0.1991,
+      "step": 450
+    },
+    {
+      "epoch": 2.0629213483146067,
+      "grad_norm": 2.2049689292907715,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.1076,
+      "step": 460
+    },
+    {
+      "epoch": 2.107865168539326,
+      "grad_norm": 1.6832406520843506,
+      "learning_rate": 2.4849503814396624e-06,
+      "loss": 0.1055,
+      "step": 470
+    },
+    {
+      "epoch": 2.152808988764045,
+      "grad_norm": 1.5062949657440186,
+      "learning_rate": 2.2629602375607373e-06,
+      "loss": 0.1051,
+      "step": 480
+    },
+    {
+      "epoch": 2.197752808988764,
+      "grad_norm": 1.708046793937683,
+      "learning_rate": 2.048422376105299e-06,
+      "loss": 0.1087,
+      "step": 490
+    },
+    {
+      "epoch": 2.242696629213483,
+      "grad_norm": 1.863958477973938,
+      "learning_rate": 1.8419209306164653e-06,
+      "loss": 0.1123,
+      "step": 500
+    },
+    {
+      "epoch": 2.242696629213483,
+      "eval_loss": 0.39164599776268005,
+      "eval_runtime": 21.0828,
+      "eval_samples_per_second": 17.787,
+      "eval_steps_per_second": 2.229,
+      "step": 500
+    },
+    {
+      "epoch": 2.2876404494382023,
+      "grad_norm": 1.9434905052185059,
+      "learning_rate": 1.6440181534640277e-06,
+      "loss": 0.1114,
+      "step": 510
+    },
+    {
+      "epoch": 2.3325842696629215,
+      "grad_norm": 1.9378854036331177,
+      "learning_rate": 1.4552528849702852e-06,
+      "loss": 0.1106,
+      "step": 520
+    },
+    {
+      "epoch": 2.3775280898876403,
+      "grad_norm": 1.6431339979171753,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.1001,
+      "step": 530
+    },
+    {
+      "epoch": 2.4224719101123595,
+      "grad_norm": 1.9648070335388184,
+      "learning_rate": 1.107164439976764e-06,
+      "loss": 0.1078,
+      "step": 540
+    },
+    {
+      "epoch": 2.4674157303370787,
+      "grad_norm": 1.8690208196640015,
+      "learning_rate": 9.487890222330137e-07,
+      "loss": 0.0981,
+      "step": 550
+    },
+    {
+      "epoch": 2.512359550561798,
+      "grad_norm": 1.8798915147781372,
+      "learning_rate": 8.014440501472909e-07,
+      "loss": 0.099,
+      "step": 560
+    },
+    {
+      "epoch": 2.5573033707865167,
+      "grad_norm": 1.7974302768707275,
+      "learning_rate": 6.655307076412637e-07,
+      "loss": 0.1082,
+      "step": 570
+    },
+    {
+      "epoch": 2.602247191011236,
+      "grad_norm": 2.128044366836548,
+      "learning_rate": 5.414190531362162e-07,
+      "loss": 0.105,
+      "step": 580
+    },
+    {
+      "epoch": 2.647191011235955,
+      "grad_norm": 1.9329229593276978,
+      "learning_rate": 4.29447011975474e-07,
+      "loss": 0.1024,
+      "step": 590
+    },
+    {
+      "epoch": 2.692134831460674,
+      "grad_norm": 2.111759662628174,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.1054,
+      "step": 600
+    },
+    {
+      "epoch": 2.737078651685393,
+      "grad_norm": 1.865928292274475,
+      "learning_rate": 2.431073751431529e-07,
+      "loss": 0.0948,
+      "step": 610
+    },
+    {
+      "epoch": 2.7820224719101123,
+      "grad_norm": 1.9106682538986206,
+      "learning_rate": 1.6924713622225975e-07,
+      "loss": 0.1027,
+      "step": 620
+    },
+    {
+      "epoch": 2.8269662921348315,
+      "grad_norm": 1.7859702110290527,
+      "learning_rate": 1.0853984274007246e-07,
+      "loss": 0.0962,
+      "step": 630
+    },
+    {
+      "epoch": 2.8719101123595507,
+      "grad_norm": 1.9934887886047363,
+      "learning_rate": 6.115078564427946e-08,
+      "loss": 0.1036,
+      "step": 640
+    },
+    {
+      "epoch": 2.9168539325842695,
+      "grad_norm": 2.19028902053833,
+      "learning_rate": 2.7208993618390578e-08,
+      "loss": 0.0964,
+      "step": 650
+    },
+    {
+      "epoch": 2.9617977528089887,
+      "grad_norm": 1.8574639558792114,
+      "learning_rate": 6.806881768539053e-09,
+      "loss": 0.1032,
+      "step": 660
+    },
+    {
+      "epoch": 3.0,
+      "step": 669,
+      "total_flos": 81298172149760.0,
+      "train_loss": 0.2715019001910861,
+      "train_runtime": 8763.6204,
+      "train_samples_per_second": 2.437,
+      "train_steps_per_second": 0.076
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 81298172149760.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2-os-121/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950450631402afa849fd7262f88ec0c22bd2eec48058c23138ff4068edaa8776
+size 8337