Upload folder using huggingface_hub

.gitattributes

@@ -46,3 +46,4 @@ webrl-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 atomic_expert/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 test_admin/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-gob-plan-115/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2-os-limit118/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2-os-limit118/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: qwen2-oslimit118-1epoch
+  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-oslimit118-1epoch
+
+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 os-limit-118 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1683
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen2-os-limit118/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-limit118/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.1683357208967209,
+    "eval_runtime": 84.5468,
+    "eval_samples_per_second": 7.653,
+    "eval_steps_per_second": 1.916,
+    "total_flos": 16529390043136.0,
+    "train_loss": 0.3663143482837048,
+    "train_runtime": 9513.5528,
+    "train_samples_per_second": 0.611,
+    "train_steps_per_second": 0.077
+}

qwen2-os-limit118/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-limit118/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-limit118/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.1683357208967209,
+    "eval_runtime": 84.5468,
+    "eval_samples_per_second": 7.653,
+    "eval_steps_per_second": 1.916
+}

qwen2-os-limit118/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-limit118/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f104977a1a29b8acb5aefcfdaeb3bd617d4db362bb9c929c93047cc0bfd1e8e
+size 4877660776

qwen2-os-limit118/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde4ed6da60371e99d1f79017125527601a5624a0453415a11b5b247be180700
+size 4932751008

qwen2-os-limit118/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6307f7bdc0a081c7599951ddcf912f97632f2f7693fbe8ed24d80afd7358b665
+size 4330865200

qwen2-os-limit118/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c948c8eec0c25528af08c88f7542e6c21f81033e5c518713fc558d6b3a044e72
+size 1089994880

qwen2-os-limit118/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-limit118/runs/Jan18_20-47-47_hgx001/events.out.tfevents.1768740587.hgx001.877435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484c25ef755b27e9d1f0aa29c1022883b59c84c752d31626c1afa82ceaff9903
+size 21726

qwen2-os-limit118/runs/Jan18_20-47-47_hgx001/events.out.tfevents.1768750214.hgx001.877435.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891748fbcc68335ed1ed83e9d5e11eee54af14c81fec081c44d8158e24d8ee94
+size 359

qwen2-os-limit118/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-limit118/tokenizer.json

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

qwen2-os-limit118/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-limit118/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 16529390043136.0,
+    "train_loss": 0.3663143482837048,
+    "train_runtime": 9513.5528,
+    "train_samples_per_second": 0.611,
+    "train_steps_per_second": 0.077
+}

qwen2-os-limit118/trainer_log.jsonl

@@ -0,0 +1,73 @@
+{"current_steps": 10, "total_steps": 728, "loss": 1.3667, "lr": 1.2328767123287671e-05, "epoch": 0.013745704467353952, "percentage": 1.37, "elapsed_time": "0:02:21", "remaining_time": "2:48:47"}
+{"current_steps": 20, "total_steps": 728, "loss": 0.4837, "lr": 2.6027397260273973e-05, "epoch": 0.027491408934707903, "percentage": 2.75, "elapsed_time": "0:04:31", "remaining_time": "2:39:59"}
+{"current_steps": 30, "total_steps": 728, "loss": 0.4664, "lr": 3.9726027397260274e-05, "epoch": 0.041237113402061855, "percentage": 4.12, "elapsed_time": "0:06:40", "remaining_time": "2:35:09"}
+{"current_steps": 40, "total_steps": 728, "loss": 0.5088, "lr": 5.342465753424658e-05, "epoch": 0.054982817869415807, "percentage": 5.49, "elapsed_time": "0:08:55", "remaining_time": "2:33:24"}
+{"current_steps": 50, "total_steps": 728, "loss": 0.5292, "lr": 6.712328767123288e-05, "epoch": 0.06872852233676977, "percentage": 6.87, "elapsed_time": "0:11:02", "remaining_time": "2:29:47"}
+{"current_steps": 60, "total_steps": 728, "loss": 0.584, "lr": 8.082191780821919e-05, "epoch": 0.08247422680412371, "percentage": 8.24, "elapsed_time": "0:13:09", "remaining_time": "2:26:30"}
+{"current_steps": 70, "total_steps": 728, "loss": 0.6036, "lr": 9.452054794520548e-05, "epoch": 0.09621993127147767, "percentage": 9.62, "elapsed_time": "0:15:22", "remaining_time": "2:24:34"}
+{"current_steps": 80, "total_steps": 728, "loss": 0.6505, "lr": 9.997929717161141e-05, "epoch": 0.10996563573883161, "percentage": 10.99, "elapsed_time": "0:17:33", "remaining_time": "2:22:15"}
+{"current_steps": 90, "total_steps": 728, "loss": 0.6062, "lr": 9.985284196797884e-05, "epoch": 0.12371134020618557, "percentage": 12.36, "elapsed_time": "0:19:44", "remaining_time": "2:19:53"}
+{"current_steps": 100, "total_steps": 728, "loss": 0.6471, "lr": 9.96117236302637e-05, "epoch": 0.13745704467353953, "percentage": 13.74, "elapsed_time": "0:21:54", "remaining_time": "2:17:37"}
+{"current_steps": 110, "total_steps": 728, "loss": 0.6362, "lr": 9.925649673836947e-05, "epoch": 0.15120274914089346, "percentage": 15.11, "elapsed_time": "0:24:05", "remaining_time": "2:15:19"}
+{"current_steps": 120, "total_steps": 728, "loss": 0.5844, "lr": 9.878797832553093e-05, "epoch": 0.16494845360824742, "percentage": 16.48, "elapsed_time": "0:26:17", "remaining_time": "2:13:10"}
+{"current_steps": 130, "total_steps": 728, "loss": 0.6195, "lr": 9.820724599911147e-05, "epoch": 0.17869415807560138, "percentage": 17.86, "elapsed_time": "0:28:28", "remaining_time": "2:11:00"}
+{"current_steps": 140, "total_steps": 728, "loss": 0.5456, "lr": 9.751563546207167e-05, "epoch": 0.19243986254295534, "percentage": 19.23, "elapsed_time": "0:30:38", "remaining_time": "2:08:43"}
+{"current_steps": 150, "total_steps": 728, "loss": 0.5491, "lr": 9.67147374408097e-05, "epoch": 0.20618556701030927, "percentage": 20.6, "elapsed_time": "0:32:50", "remaining_time": "2:06:34"}
+{"current_steps": 160, "total_steps": 728, "loss": 0.6303, "lr": 9.580639402643957e-05, "epoch": 0.21993127147766323, "percentage": 21.98, "elapsed_time": "0:35:02", "remaining_time": "2:04:24"}
+{"current_steps": 170, "total_steps": 728, "loss": 0.5832, "lr": 9.479269443792261e-05, "epoch": 0.23367697594501718, "percentage": 23.35, "elapsed_time": "0:37:13", "remaining_time": "2:02:10"}
+{"current_steps": 180, "total_steps": 728, "loss": 0.4891, "lr": 9.367597021679686e-05, "epoch": 0.24742268041237114, "percentage": 24.73, "elapsed_time": "0:39:26", "remaining_time": "2:00:04"}
+{"current_steps": 190, "total_steps": 728, "loss": 0.5258, "lr": 9.245878986455683e-05, "epoch": 0.2611683848797251, "percentage": 26.1, "elapsed_time": "0:41:38", "remaining_time": "1:57:53"}
+{"current_steps": 200, "total_steps": 728, "loss": 0.5182, "lr": 9.114395293501774e-05, "epoch": 0.27491408934707906, "percentage": 27.47, "elapsed_time": "0:43:49", "remaining_time": "1:55:40"}
+{"current_steps": 210, "total_steps": 728, "loss": 0.4391, "lr": 8.973448359525206e-05, "epoch": 0.28865979381443296, "percentage": 28.85, "elapsed_time": "0:46:00", "remaining_time": "1:53:29"}
+{"current_steps": 220, "total_steps": 728, "loss": 0.4903, "lr": 8.823362366990833e-05, "epoch": 0.3024054982817869, "percentage": 30.22, "elapsed_time": "0:48:11", "remaining_time": "1:51:17"}
+{"current_steps": 230, "total_steps": 728, "loss": 0.4814, "lr": 8.664482518491053e-05, "epoch": 0.3161512027491409, "percentage": 31.59, "elapsed_time": "0:50:23", "remaining_time": "1:49:06"}
+{"current_steps": 240, "total_steps": 728, "loss": 0.4561, "lr": 8.497174242768791e-05, "epoch": 0.32989690721649484, "percentage": 32.97, "elapsed_time": "0:52:34", "remaining_time": "1:46:53"}
+{"current_steps": 250, "total_steps": 728, "loss": 0.5269, "lr": 8.321822354219677e-05, "epoch": 0.3436426116838488, "percentage": 34.34, "elapsed_time": "0:54:46", "remaining_time": "1:44:43"}
+{"current_steps": 260, "total_steps": 728, "loss": 0.4309, "lr": 8.138830167806602e-05, "epoch": 0.35738831615120276, "percentage": 35.71, "elapsed_time": "0:56:59", "remaining_time": "1:42:34"}
+{"current_steps": 270, "total_steps": 728, "loss": 0.4121, "lr": 7.948618571422379e-05, "epoch": 0.3711340206185567, "percentage": 37.09, "elapsed_time": "0:59:09", "remaining_time": "1:40:21"}
+{"current_steps": 280, "total_steps": 728, "loss": 0.3867, "lr": 7.751625057834107e-05, "epoch": 0.3848797250859107, "percentage": 38.46, "elapsed_time": "1:01:19", "remaining_time": "1:38:07"}
+{"current_steps": 290, "total_steps": 728, "loss": 0.4454, "lr": 7.548302718435783e-05, "epoch": 0.39862542955326463, "percentage": 39.84, "elapsed_time": "1:03:30", "remaining_time": "1:35:54"}
+{"current_steps": 300, "total_steps": 728, "loss": 0.3953, "lr": 7.339119201123577e-05, "epoch": 0.41237113402061853, "percentage": 41.21, "elapsed_time": "1:05:45", "remaining_time": "1:33:48"}
+{"current_steps": 310, "total_steps": 728, "loss": 0.3726, "lr": 7.124555634690684e-05, "epoch": 0.4261168384879725, "percentage": 42.58, "elapsed_time": "1:07:57", "remaining_time": "1:31:37"}
+{"current_steps": 320, "total_steps": 728, "loss": 0.3631, "lr": 6.905105522215683e-05, "epoch": 0.43986254295532645, "percentage": 43.96, "elapsed_time": "1:10:10", "remaining_time": "1:29:28"}
+{"current_steps": 330, "total_steps": 728, "loss": 0.4094, "lr": 6.681273605989643e-05, "epoch": 0.4536082474226804, "percentage": 45.33, "elapsed_time": "1:12:21", "remaining_time": "1:27:15"}
+{"current_steps": 340, "total_steps": 728, "loss": 0.3425, "lr": 6.453574706592676e-05, "epoch": 0.46735395189003437, "percentage": 46.7, "elapsed_time": "1:14:33", "remaining_time": "1:25:04"}
+{"current_steps": 350, "total_steps": 728, "loss": 0.3565, "lr": 6.222532538790107e-05, "epoch": 0.48109965635738833, "percentage": 48.08, "elapsed_time": "1:16:43", "remaining_time": "1:22:51"}
+{"current_steps": 360, "total_steps": 728, "loss": 0.3425, "lr": 5.988678506971725e-05, "epoch": 0.4948453608247423, "percentage": 49.45, "elapsed_time": "1:19:05", "remaining_time": "1:20:51"}
+{"current_steps": 370, "total_steps": 728, "loss": 0.2837, "lr": 5.752550482904674e-05, "epoch": 0.5085910652920962, "percentage": 50.82, "elapsed_time": "1:21:17", "remaining_time": "1:18:39"}
+{"current_steps": 380, "total_steps": 728, "loss": 0.413, "lr": 5.51469156861113e-05, "epoch": 0.5223367697594502, "percentage": 52.2, "elapsed_time": "1:23:29", "remaining_time": "1:16:27"}
+{"current_steps": 390, "total_steps": 728, "loss": 0.3131, "lr": 5.2756488472162636e-05, "epoch": 0.5360824742268041, "percentage": 53.57, "elapsed_time": "1:25:52", "remaining_time": "1:14:25"}
+{"current_steps": 400, "total_steps": 728, "loss": 0.319, "lr": 5.035972124639511e-05, "epoch": 0.5498281786941581, "percentage": 54.95, "elapsed_time": "1:28:02", "remaining_time": "1:12:11"}
+{"current_steps": 410, "total_steps": 728, "loss": 0.3005, "lr": 4.7962126650233445e-05, "epoch": 0.563573883161512, "percentage": 56.32, "elapsed_time": "1:30:12", "remaining_time": "1:09:58"}
+{"current_steps": 420, "total_steps": 728, "loss": 0.2988, "lr": 4.556921922808081e-05, "epoch": 0.5773195876288659, "percentage": 57.69, "elapsed_time": "1:32:24", "remaining_time": "1:07:46"}
+{"current_steps": 430, "total_steps": 728, "loss": 0.2728, "lr": 4.318650274368989e-05, "epoch": 0.5910652920962199, "percentage": 59.07, "elapsed_time": "1:34:36", "remaining_time": "1:05:34"}
+{"current_steps": 440, "total_steps": 728, "loss": 0.2255, "lr": 4.0819457521329995e-05, "epoch": 0.6048109965635738, "percentage": 60.44, "elapsed_time": "1:36:47", "remaining_time": "1:03:21"}
+{"current_steps": 450, "total_steps": 728, "loss": 0.2422, "lr": 3.8473527840865555e-05, "epoch": 0.6185567010309279, "percentage": 61.81, "elapsed_time": "1:38:56", "remaining_time": "1:01:07"}
+{"current_steps": 460, "total_steps": 728, "loss": 0.2398, "lr": 3.615410941573799e-05, "epoch": 0.6323024054982818, "percentage": 63.19, "elapsed_time": "1:41:07", "remaining_time": "0:58:54"}
+{"current_steps": 470, "total_steps": 728, "loss": 0.2259, "lr": 3.386653698265189e-05, "epoch": 0.6460481099656358, "percentage": 64.56, "elapsed_time": "1:43:15", "remaining_time": "0:56:41"}
+{"current_steps": 480, "total_steps": 728, "loss": 0.2402, "lr": 3.161607203150959e-05, "epoch": 0.6597938144329897, "percentage": 65.93, "elapsed_time": "1:45:27", "remaining_time": "0:54:29"}
+{"current_steps": 490, "total_steps": 728, "loss": 0.2172, "lr": 2.9407890703815867e-05, "epoch": 0.6735395189003437, "percentage": 67.31, "elapsed_time": "1:47:38", "remaining_time": "0:52:17"}
+{"current_steps": 500, "total_steps": 728, "loss": 0.2289, "lr": 2.7247071887386545e-05, "epoch": 0.6872852233676976, "percentage": 68.68, "elapsed_time": "1:49:51", "remaining_time": "0:50:05"}
+{"current_steps": 510, "total_steps": 728, "loss": 0.2088, "lr": 2.5138585534743818e-05, "epoch": 0.7010309278350515, "percentage": 70.05, "elapsed_time": "1:52:01", "remaining_time": "0:47:53"}
+{"current_steps": 520, "total_steps": 728, "loss": 0.2001, "lr": 2.3087281232066133e-05, "epoch": 0.7147766323024055, "percentage": 71.43, "elapsed_time": "1:54:08", "remaining_time": "0:45:39"}
+{"current_steps": 530, "total_steps": 728, "loss": 0.1869, "lr": 2.109787704498459e-05, "epoch": 0.7285223367697594, "percentage": 72.8, "elapsed_time": "1:56:13", "remaining_time": "0:43:25"}
+{"current_steps": 540, "total_steps": 728, "loss": 0.1904, "lr": 1.9174948666880803e-05, "epoch": 0.7422680412371134, "percentage": 74.18, "elapsed_time": "1:58:22", "remaining_time": "0:41:12"}
+{"current_steps": 550, "total_steps": 728, "loss": 0.191, "lr": 1.7322918894645522e-05, "epoch": 0.7560137457044673, "percentage": 75.55, "elapsed_time": "2:00:29", "remaining_time": "0:38:59"}
+{"current_steps": 560, "total_steps": 728, "loss": 0.1845, "lr": 1.5546047456103964e-05, "epoch": 0.7697594501718213, "percentage": 76.92, "elapsed_time": "2:02:37", "remaining_time": "0:36:47"}
+{"current_steps": 570, "total_steps": 728, "loss": 0.204, "lr": 1.3848421212505403e-05, "epoch": 0.7835051546391752, "percentage": 78.3, "elapsed_time": "2:04:42", "remaining_time": "0:34:34"}
+{"current_steps": 580, "total_steps": 728, "loss": 0.2088, "lr": 1.223394475861131e-05, "epoch": 0.7972508591065293, "percentage": 79.67, "elapsed_time": "2:06:50", "remaining_time": "0:32:21"}
+{"current_steps": 590, "total_steps": 728, "loss": 0.1979, "lr": 1.0706331442002227e-05, "epoch": 0.8109965635738832, "percentage": 81.04, "elapsed_time": "2:09:00", "remaining_time": "0:30:10"}
+{"current_steps": 600, "total_steps": 728, "loss": 0.1593, "lr": 9.269094822259439e-06, "epoch": 0.8247422680412371, "percentage": 82.42, "elapsed_time": "2:11:08", "remaining_time": "0:27:58"}
+{"current_steps": 610, "total_steps": 728, "loss": 0.1538, "lr": 7.925540589665186e-06, "epoch": 0.8384879725085911, "percentage": 83.79, "elapsed_time": "2:13:16", "remaining_time": "0:25:46"}
+{"current_steps": 620, "total_steps": 728, "loss": 0.1542, "lr": 6.678758962009241e-06, "epoch": 0.852233676975945, "percentage": 85.16, "elapsed_time": "2:15:25", "remaining_time": "0:23:35"}
+{"current_steps": 630, "total_steps": 728, "loss": 0.1789, "lr": 5.531617576988879e-06, "epoch": 0.865979381443299, "percentage": 86.54, "elapsed_time": "2:17:31", "remaining_time": "0:21:23"}
+{"current_steps": 640, "total_steps": 728, "loss": 0.162, "lr": 4.486754896550288e-06, "epoch": 0.8797250859106529, "percentage": 87.91, "elapsed_time": "2:19:36", "remaining_time": "0:19:11"}
+{"current_steps": 650, "total_steps": 728, "loss": 0.1478, "lr": 3.5465741383415686e-06, "epoch": 0.8934707903780069, "percentage": 89.29, "elapsed_time": "2:21:45", "remaining_time": "0:17:00"}
+{"current_steps": 660, "total_steps": 728, "loss": 0.1757, "lr": 2.7132377482351036e-06, "epoch": 0.9072164948453608, "percentage": 90.66, "elapsed_time": "2:23:54", "remaining_time": "0:14:49"}
+{"current_steps": 670, "total_steps": 728, "loss": 0.1558, "lr": 1.9886624266327645e-06, "epoch": 0.9209621993127147, "percentage": 92.03, "elapsed_time": "2:26:00", "remaining_time": "0:12:38"}
+{"current_steps": 680, "total_steps": 728, "loss": 0.1699, "lr": 1.3745147199935748e-06, "epoch": 0.9347079037800687, "percentage": 93.41, "elapsed_time": "2:28:06", "remaining_time": "0:10:27"}
+{"current_steps": 690, "total_steps": 728, "loss": 0.1615, "lr": 8.72207187723445e-07, "epoch": 0.9484536082474226, "percentage": 94.78, "elapsed_time": "2:30:13", "remaining_time": "0:08:16"}
+{"current_steps": 700, "total_steps": 728, "loss": 0.2085, "lr": 4.828951532432458e-07, "epoch": 0.9621993127147767, "percentage": 96.15, "elapsed_time": "2:32:21", "remaining_time": "0:06:05"}
+{"current_steps": 710, "total_steps": 728, "loss": 0.1488, "lr": 2.0747404670796721e-07, "epoch": 0.9759450171821306, "percentage": 97.53, "elapsed_time": "2:34:28", "remaining_time": "0:03:54"}
+{"current_steps": 720, "total_steps": 728, "loss": 0.167, "lr": 4.65773454886298e-08, "epoch": 0.9896907216494846, "percentage": 98.9, "elapsed_time": "2:36:35", "remaining_time": "0:01:44"}
+{"current_steps": 728, "total_steps": 728, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:38:33", "remaining_time": "0:00:00"}

qwen2-os-limit118/trainer_state.json

@@ -0,0 +1,547 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2000,
+  "global_step": 728,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013745704467353952,
+      "grad_norm": 8.309086799621582,
+      "learning_rate": 1.2328767123287671e-05,
+      "loss": 1.3667,
+      "step": 10
+    },
+    {
+      "epoch": 0.027491408934707903,
+      "grad_norm": 5.662752151489258,
+      "learning_rate": 2.6027397260273973e-05,
+      "loss": 0.4837,
+      "step": 20
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 5.212001800537109,
+      "learning_rate": 3.9726027397260274e-05,
+      "loss": 0.4664,
+      "step": 30
+    },
+    {
+      "epoch": 0.054982817869415807,
+      "grad_norm": 5.5099639892578125,
+      "learning_rate": 5.342465753424658e-05,
+      "loss": 0.5088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06872852233676977,
+      "grad_norm": 4.344723224639893,
+      "learning_rate": 6.712328767123288e-05,
+      "loss": 0.5292,
+      "step": 50
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 3.7627005577087402,
+      "learning_rate": 8.082191780821919e-05,
+      "loss": 0.584,
+      "step": 60
+    },
+    {
+      "epoch": 0.09621993127147767,
+      "grad_norm": 9.269454002380371,
+      "learning_rate": 9.452054794520548e-05,
+      "loss": 0.6036,
+      "step": 70
+    },
+    {
+      "epoch": 0.10996563573883161,
+      "grad_norm": 56.21126937866211,
+      "learning_rate": 9.997929717161141e-05,
+      "loss": 0.6505,
+      "step": 80
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 3.858214855194092,
+      "learning_rate": 9.985284196797884e-05,
+      "loss": 0.6062,
+      "step": 90
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 3.209242343902588,
+      "learning_rate": 9.96117236302637e-05,
+      "loss": 0.6471,
+      "step": 100
+    },
+    {
+      "epoch": 0.15120274914089346,
+      "grad_norm": 2.665212869644165,
+      "learning_rate": 9.925649673836947e-05,
+      "loss": 0.6362,
+      "step": 110
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 2.822697877883911,
+      "learning_rate": 9.878797832553093e-05,
+      "loss": 0.5844,
+      "step": 120
+    },
+    {
+      "epoch": 0.17869415807560138,
+      "grad_norm": 3.330354690551758,
+      "learning_rate": 9.820724599911147e-05,
+      "loss": 0.6195,
+      "step": 130
+    },
+    {
+      "epoch": 0.19243986254295534,
+      "grad_norm": 2.6973066329956055,
+      "learning_rate": 9.751563546207167e-05,
+      "loss": 0.5456,
+      "step": 140
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.3305342197418213,
+      "learning_rate": 9.67147374408097e-05,
+      "loss": 0.5491,
+      "step": 150
+    },
+    {
+      "epoch": 0.21993127147766323,
+      "grad_norm": 2.9372878074645996,
+      "learning_rate": 9.580639402643957e-05,
+      "loss": 0.6303,
+      "step": 160
+    },
+    {
+      "epoch": 0.23367697594501718,
+      "grad_norm": 2.954463481903076,
+      "learning_rate": 9.479269443792261e-05,
+      "loss": 0.5832,
+      "step": 170
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 3.9859142303466797,
+      "learning_rate": 9.367597021679686e-05,
+      "loss": 0.4891,
+      "step": 180
+    },
+    {
+      "epoch": 0.2611683848797251,
+      "grad_norm": 4.237502098083496,
+      "learning_rate": 9.245878986455683e-05,
+      "loss": 0.5258,
+      "step": 190
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "grad_norm": 2.210482120513916,
+      "learning_rate": 9.114395293501774e-05,
+      "loss": 0.5182,
+      "step": 200
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 2.6883702278137207,
+      "learning_rate": 8.973448359525206e-05,
+      "loss": 0.4391,
+      "step": 210
+    },
+    {
+      "epoch": 0.3024054982817869,
+      "grad_norm": 2.632126569747925,
+      "learning_rate": 8.823362366990833e-05,
+      "loss": 0.4903,
+      "step": 220
+    },
+    {
+      "epoch": 0.3161512027491409,
+      "grad_norm": 3.1042637825012207,
+      "learning_rate": 8.664482518491053e-05,
+      "loss": 0.4814,
+      "step": 230
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 2.427168846130371,
+      "learning_rate": 8.497174242768791e-05,
+      "loss": 0.4561,
+      "step": 240
+    },
+    {
+      "epoch": 0.3436426116838488,
+      "grad_norm": 2.117550849914551,
+      "learning_rate": 8.321822354219677e-05,
+      "loss": 0.5269,
+      "step": 250
+    },
+    {
+      "epoch": 0.35738831615120276,
+      "grad_norm": 1.9255056381225586,
+      "learning_rate": 8.138830167806602e-05,
+      "loss": 0.4309,
+      "step": 260
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 2.392418622970581,
+      "learning_rate": 7.948618571422379e-05,
+      "loss": 0.4121,
+      "step": 270
+    },
+    {
+      "epoch": 0.3848797250859107,
+      "grad_norm": 1.9980478286743164,
+      "learning_rate": 7.751625057834107e-05,
+      "loss": 0.3867,
+      "step": 280
+    },
+    {
+      "epoch": 0.39862542955326463,
+      "grad_norm": 2.743718147277832,
+      "learning_rate": 7.548302718435783e-05,
+      "loss": 0.4454,
+      "step": 290
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 2.4977786540985107,
+      "learning_rate": 7.339119201123577e-05,
+      "loss": 0.3953,
+      "step": 300
+    },
+    {
+      "epoch": 0.4261168384879725,
+      "grad_norm": 2.0112690925598145,
+      "learning_rate": 7.124555634690684e-05,
+      "loss": 0.3726,
+      "step": 310
+    },
+    {
+      "epoch": 0.43986254295532645,
+      "grad_norm": 1.648325800895691,
+      "learning_rate": 6.905105522215683e-05,
+      "loss": 0.3631,
+      "step": 320
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 2.006272077560425,
+      "learning_rate": 6.681273605989643e-05,
+      "loss": 0.4094,
+      "step": 330
+    },
+    {
+      "epoch": 0.46735395189003437,
+      "grad_norm": 1.6057766675949097,
+      "learning_rate": 6.453574706592676e-05,
+      "loss": 0.3425,
+      "step": 340
+    },
+    {
+      "epoch": 0.48109965635738833,
+      "grad_norm": 1.774682879447937,
+      "learning_rate": 6.222532538790107e-05,
+      "loss": 0.3565,
+      "step": 350
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 2.349799156188965,
+      "learning_rate": 5.988678506971725e-05,
+      "loss": 0.3425,
+      "step": 360
+    },
+    {
+      "epoch": 0.5085910652920962,
+      "grad_norm": 1.7307243347167969,
+      "learning_rate": 5.752550482904674e-05,
+      "loss": 0.2837,
+      "step": 370
+    },
+    {
+      "epoch": 0.5223367697594502,
+      "grad_norm": 4.024322986602783,
+      "learning_rate": 5.51469156861113e-05,
+      "loss": 0.413,
+      "step": 380
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 1.6806915998458862,
+      "learning_rate": 5.2756488472162636e-05,
+      "loss": 0.3131,
+      "step": 390
+    },
+    {
+      "epoch": 0.5498281786941581,
+      "grad_norm": 2.0108752250671387,
+      "learning_rate": 5.035972124639511e-05,
+      "loss": 0.319,
+      "step": 400
+    },
+    {
+      "epoch": 0.563573883161512,
+      "grad_norm": 1.642941951751709,
+      "learning_rate": 4.7962126650233445e-05,
+      "loss": 0.3005,
+      "step": 410
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 1.4420604705810547,
+      "learning_rate": 4.556921922808081e-05,
+      "loss": 0.2988,
+      "step": 420
+    },
+    {
+      "epoch": 0.5910652920962199,
+      "grad_norm": 1.5599799156188965,
+      "learning_rate": 4.318650274368989e-05,
+      "loss": 0.2728,
+      "step": 430
+    },
+    {
+      "epoch": 0.6048109965635738,
+      "grad_norm": 2.0606956481933594,
+      "learning_rate": 4.0819457521329995e-05,
+      "loss": 0.2255,
+      "step": 440
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.487032175064087,
+      "learning_rate": 3.8473527840865555e-05,
+      "loss": 0.2422,
+      "step": 450
+    },
+    {
+      "epoch": 0.6323024054982818,
+      "grad_norm": 1.566791296005249,
+      "learning_rate": 3.615410941573799e-05,
+      "loss": 0.2398,
+      "step": 460
+    },
+    {
+      "epoch": 0.6460481099656358,
+      "grad_norm": 1.409690499305725,
+      "learning_rate": 3.386653698265189e-05,
+      "loss": 0.2259,
+      "step": 470
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.1732258796691895,
+      "learning_rate": 3.161607203150959e-05,
+      "loss": 0.2402,
+      "step": 480
+    },
+    {
+      "epoch": 0.6735395189003437,
+      "grad_norm": 1.263793706893921,
+      "learning_rate": 2.9407890703815867e-05,
+      "loss": 0.2172,
+      "step": 490
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "grad_norm": 1.4290318489074707,
+      "learning_rate": 2.7247071887386545e-05,
+      "loss": 0.2289,
+      "step": 500
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.325259804725647,
+      "learning_rate": 2.5138585534743818e-05,
+      "loss": 0.2088,
+      "step": 510
+    },
+    {
+      "epoch": 0.7147766323024055,
+      "grad_norm": 1.018134355545044,
+      "learning_rate": 2.3087281232066133e-05,
+      "loss": 0.2001,
+      "step": 520
+    },
+    {
+      "epoch": 0.7285223367697594,
+      "grad_norm": 1.3938742876052856,
+      "learning_rate": 2.109787704498459e-05,
+      "loss": 0.1869,
+      "step": 530
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 1.1285089254379272,
+      "learning_rate": 1.9174948666880803e-05,
+      "loss": 0.1904,
+      "step": 540
+    },
+    {
+      "epoch": 0.7560137457044673,
+      "grad_norm": 1.016331672668457,
+      "learning_rate": 1.7322918894645522e-05,
+      "loss": 0.191,
+      "step": 550
+    },
+    {
+      "epoch": 0.7697594501718213,
+      "grad_norm": 1.0006132125854492,
+      "learning_rate": 1.5546047456103964e-05,
+      "loss": 0.1845,
+      "step": 560
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.600069284439087,
+      "learning_rate": 1.3848421212505403e-05,
+      "loss": 0.204,
+      "step": 570
+    },
+    {
+      "epoch": 0.7972508591065293,
+      "grad_norm": 1.3062262535095215,
+      "learning_rate": 1.223394475861131e-05,
+      "loss": 0.2088,
+      "step": 580
+    },
+    {
+      "epoch": 0.8109965635738832,
+      "grad_norm": 1.23960280418396,
+      "learning_rate": 1.0706331442002227e-05,
+      "loss": 0.1979,
+      "step": 590
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.9770699739456177,
+      "learning_rate": 9.269094822259439e-06,
+      "loss": 0.1593,
+      "step": 600
+    },
+    {
+      "epoch": 0.8384879725085911,
+      "grad_norm": 1.1675751209259033,
+      "learning_rate": 7.925540589665186e-06,
+      "loss": 0.1538,
+      "step": 610
+    },
+    {
+      "epoch": 0.852233676975945,
+      "grad_norm": 0.9746043086051941,
+      "learning_rate": 6.678758962009241e-06,
+      "loss": 0.1542,
+      "step": 620
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.111664056777954,
+      "learning_rate": 5.531617576988879e-06,
+      "loss": 0.1789,
+      "step": 630
+    },
+    {
+      "epoch": 0.8797250859106529,
+      "grad_norm": 2.3860485553741455,
+      "learning_rate": 4.486754896550288e-06,
+      "loss": 0.162,
+      "step": 640
+    },
+    {
+      "epoch": 0.8934707903780069,
+      "grad_norm": 0.9039013385772705,
+      "learning_rate": 3.5465741383415686e-06,
+      "loss": 0.1478,
+      "step": 650
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.170327067375183,
+      "learning_rate": 2.7132377482351036e-06,
+      "loss": 0.1757,
+      "step": 660
+    },
+    {
+      "epoch": 0.9209621993127147,
+      "grad_norm": 1.6405361890792847,
+      "learning_rate": 1.9886624266327645e-06,
+      "loss": 0.1558,
+      "step": 670
+    },
+    {
+      "epoch": 0.9347079037800687,
+      "grad_norm": 0.7992695569992065,
+      "learning_rate": 1.3745147199935748e-06,
+      "loss": 0.1699,
+      "step": 680
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.9231282472610474,
+      "learning_rate": 8.72207187723445e-07,
+      "loss": 0.1615,
+      "step": 690
+    },
+    {
+      "epoch": 0.9621993127147767,
+      "grad_norm": 1.1540491580963135,
+      "learning_rate": 4.828951532432458e-07,
+      "loss": 0.2085,
+      "step": 700
+    },
+    {
+      "epoch": 0.9759450171821306,
+      "grad_norm": 1.1288212537765503,
+      "learning_rate": 2.0747404670796721e-07,
+      "loss": 0.1488,
+      "step": 710
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.1793612241744995,
+      "learning_rate": 4.65773454886298e-08,
+      "loss": 0.167,
+      "step": 720
+    },
+    {
+      "epoch": 1.0,
+      "step": 728,
+      "total_flos": 16529390043136.0,
+      "train_loss": 0.3663143482837048,
+      "train_runtime": 9513.5528,
+      "train_samples_per_second": 0.611,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 728,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 16529390043136.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2-os-limit118/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e78844faa9ecd5302463e87f007925780ecdc36d26289e14b7b6fe5bac5a45
+size 8401