初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-mbpp-s42-lambda-0p50 Source: Original Platform
2026-06-16 05:57:17 +08:00
commit 8feea536c8
33 changed files with 983 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,67 @@
+---
+base_model: harsha070/sft-warmup-qwen-v1
+library_name: transformers
+model_name: expfinal-qwen-mbpp-s42-lambda-0p50
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# Model Card for expfinal-qwen-mbpp-s42-lambda-0p50
+
+This model is a fine-tuned version of [harsha070/sft-warmup-qwen-v1](https://huggingface.co/harsha070/sft-warmup-qwen-v1).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="harsha070/expfinal-qwen-mbpp-s42-lambda-0p50", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/models-self5933/obfuscation-early-warning/runs/n7bw20up) 
+
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 1.3.0
+- Transformers: 5.7.0
+- Pytorch: 2.11.0
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{shao2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/chat_template.jinja
+++ b/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 %}
--- a/completions/completions_00010.parquet
+++ b/completions/completions_00010.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc2cb688023a4a85959fce662a42f319e13e96a87140f787412ef4689c68eae
+size 18295
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05168a94355234a9c1862dd8998c9ea8fd630ad883e914f36dacb99ce1428bcb
+size 15441
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66914703e375c0610f69d3da61efc82d775e145bbf5a938848be700771e1d83b
+size 15875
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed3743125bdd0f996eb130ba5eee668d7bcdf4b358bdab8245321bfe76eb792
+size 13064
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c033151bab6d8cee218ee79c0a46bd5669623224e2423487aff553f77a59e6ba
+size 13269
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da64af9d7fbc5185f427f2a67b308399be6e56a4b125ecf1a637bd2c1f3478a
+size 13167
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76aff20e23b5f2d68a037bc29c18580048ddd0eff9eaa6118ca5704cb83051c
+size 12300
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669ab8c3bff842c42e2a18ae3882874870b6a405f190fcf0a3e83315dbb764a7
+size 13673
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d340963ec9a90f97bd1faff86a13eba29f936e26489ff984376faaf099141d
+size 13861
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6714980e2b77e682532be0b78f9c9caf8ac234670584ce5999d5ef87959bb687
+size 13697
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbb0d4e0d55154c47aa40296611d0f59b6b0e5ebdf88e28fdadc1a285181c65
+size 15012
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43fe9ddc3857be0024a512f25dd33344531652f7773a0bcc301638aa2b6af717
+size 14771
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c9c6ec99dd298e717c3468f45cda7b37a4eaf8ea1188eda8c2c13e1f00e1f8
+size 13297
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d170de6065d44f7b44f1047e565631fed2b0526351c47326201390723c8d40
+size 10939
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cf83f97f29cd7b35f196e4dfb01a58a5acba6026aed61f7be283bfb472583c
+size 12116
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0c2693dc1f09027301ae11d4281c4af6b27b8c783be9888941d8b1120c3d09
+size 12553
--- a/config.json
+++ b/config.json
@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/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": "5.7.0"
+}
--- a/last-checkpoint/chat_template.jinja
+++ b/last-checkpoint/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 %}
--- a/last-checkpoint/config.json
+++ b/last-checkpoint/config.json
@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/last-checkpoint/generation_config.json
+++ b/last-checkpoint/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": "5.7.0"
+}
--- a/last-checkpoint/model.safetensors
+++ b/last-checkpoint/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155c3c86c366bde86b963e906171bb76328518aa7c48daf0c8b4837ccffc075c
+size 6171927112
--- a/last-checkpoint/tokenizer.json
+++ b/last-checkpoint/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
--- a/last-checkpoint/tokenizer_config.json
+++ b/last-checkpoint/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/last-checkpoint/trainer_state.json
+++ b/last-checkpoint/trainer_state.json
@@ -0,0 +1,482 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0666666666666667,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2125,
+      "completions/max_length": 490.8,
+      "completions/max_terminated_length": 470.6,
+      "completions/mean_length": 414.4625,
+      "completions/mean_terminated_length": 395.1430999755859,
+      "completions/min_length": 310.5,
+      "completions/min_terminated_length": 310.5,
+      "entropy": 0.5249067967757582,
+      "epoch": 0.06666666666666667,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 2.65625,
+      "kl": 0.03049815017875517,
+      "learning_rate": 9.4375e-06,
+      "loss": -0.010575222969055175,
+      "num_tokens": 46025.0,
+      "reward": 0.73009033203125,
+      "reward_std": 0.4704558838158846,
+      "rewards/JointRewardFunction/mean": 0.73009033203125,
+      "rewards/JointRewardFunction/std": 0.47045588716864584,
+      "step": 10,
+      "step_time": 21.721466124300058
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.15,
+      "completions/max_length": 474.6,
+      "completions/max_terminated_length": 432.8,
+      "completions/mean_length": 372.65,
+      "completions/mean_terminated_length": 348.14678955078125,
+      "completions/min_length": 280.5,
+      "completions/min_terminated_length": 280.5,
+      "entropy": 0.4361519979313016,
+      "epoch": 0.13333333333333333,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 4.15625,
+      "kl": 0.0652532160282135,
+      "learning_rate": 8.8125e-06,
+      "loss": 0.016564452648162843,
+      "num_tokens": 89597.0,
+      "reward": 0.95604248046875,
+      "reward_std": 0.5059975624084473,
+      "rewards/JointRewardFunction/mean": 0.95604248046875,
+      "rewards/JointRewardFunction/std": 0.5059975773096085,
+      "step": 20,
+      "step_time": 22.023339059400495
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 425.6,
+      "completions/max_terminated_length": 406.9,
+      "completions/mean_length": 317.9,
+      "completions/mean_terminated_length": 309.6845275878906,
+      "completions/min_length": 231.4,
+      "completions/min_terminated_length": 231.4,
+      "entropy": 0.45581948235630987,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 2.859375,
+      "kl": 0.1008026220370084,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.01793680489063263,
+      "num_tokens": 126445.0,
+      "reward": 1.2108154296875,
+      "reward_std": 0.40027157836593685,
+      "rewards/JointRewardFunction/mean": 1.2108154296875,
+      "rewards/JointRewardFunction/std": 0.40027157838921995,
+      "step": 30,
+      "step_time": 19.79602696299935
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1125,
+      "completions/max_length": 493.9,
+      "completions/max_terminated_length": 468.6,
+      "completions/mean_length": 352.1875,
+      "completions/mean_terminated_length": 335.66607666015625,
+      "completions/min_length": 238.5,
+      "completions/min_terminated_length": 238.5,
+      "entropy": 0.4116522930562496,
+      "epoch": 0.26666666666666666,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 2.5625,
+      "kl": 0.12701121605932714,
+      "learning_rate": 7.5625e-06,
+      "loss": 0.05010480284690857,
+      "num_tokens": 167932.0,
+      "reward": 1.2074462890625,
+      "reward_std": 0.42208707332611084,
+      "rewards/JointRewardFunction/mean": 1.2074462890625,
+      "rewards/JointRewardFunction/std": 0.4220870822668076,
+      "step": 40,
+      "step_time": 22.582551179301117
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 393.4,
+      "completions/max_terminated_length": 380.0,
+      "completions/mean_length": 300.8625,
+      "completions/mean_terminated_length": 296.27321472167966,
+      "completions/min_length": 226.3,
+      "completions/min_terminated_length": 226.3,
+      "entropy": 0.4190680437721312,
+      "epoch": 0.3333333333333333,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 3.25,
+      "kl": 0.13846059744246303,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.03549057841300964,
+      "num_tokens": 204717.0,
+      "reward": 1.26171875,
+      "reward_std": 0.38662562653189525,
+      "rewards/JointRewardFunction/mean": 1.26171875,
+      "rewards/JointRewardFunction/std": 0.3866256324923597,
+      "step": 50,
+      "step_time": 18.59559666490022
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 426.2,
+      "completions/max_terminated_length": 414.2,
+      "completions/mean_length": 285.9125,
+      "completions/mean_terminated_length": 280.5291687011719,
+      "completions/min_length": 190.9,
+      "completions/min_terminated_length": 190.9,
+      "entropy": 0.3493430153466761,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 2.375,
+      "kl": 0.15198964411392807,
+      "learning_rate": 6.3125e-06,
+      "loss": 0.01220681592822075,
+      "num_tokens": 240990.0,
+      "reward": 1.27255859375,
+      "reward_std": 0.34817005618242547,
+      "rewards/JointRewardFunction/mean": 1.27255859375,
+      "rewards/JointRewardFunction/std": 0.34817005618242547,
+      "step": 60,
+      "step_time": 19.868489251599385
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 370.4,
+      "completions/max_terminated_length": 365.0,
+      "completions/mean_length": 277.2875,
+      "completions/mean_terminated_length": 272.9107177734375,
+      "completions/min_length": 179.9,
+      "completions/min_terminated_length": 179.9,
+      "entropy": 0.34267437979578974,
+      "epoch": 0.4666666666666667,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 0.017333984375,
+      "kl": 0.18903981931507588,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.019876784086227416,
+      "num_tokens": 276969.0,
+      "reward": 1.381591796875,
+      "reward_std": 0.2380124439485371,
+      "rewards/JointRewardFunction/mean": 1.381591796875,
+      "rewards/JointRewardFunction/std": 0.23801244990900158,
+      "step": 70,
+      "step_time": 17.71040062670145
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 378.1,
+      "completions/max_terminated_length": 378.1,
+      "completions/mean_length": 271.3625,
+      "completions/mean_terminated_length": 271.3625,
+      "completions/min_length": 171.4,
+      "completions/min_terminated_length": 171.4,
+      "entropy": 0.3542415237054229,
+      "epoch": 0.5333333333333333,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.0751953125,
+      "kl": 0.19187260391190647,
+      "learning_rate": 5.0625e-06,
+      "loss": 0.0034067176282405855,
+      "num_tokens": 312350.0,
+      "reward": 1.40601806640625,
+      "reward_std": 0.2126459252787754,
+      "rewards/JointRewardFunction/mean": 1.40601806640625,
+      "rewards/JointRewardFunction/std": 0.21264592825900763,
+      "step": 80,
+      "step_time": 18.04391895070148
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.05,
+      "completions/max_length": 357.6,
+      "completions/max_terminated_length": 341.1,
+      "completions/mean_length": 272.275,
+      "completions/mean_terminated_length": 260.9375,
+      "completions/min_length": 171.3,
+      "completions/min_terminated_length": 171.3,
+      "entropy": 0.31064137276262044,
+      "epoch": 0.6,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 1.875,
+      "kl": 0.20775549318641423,
+      "learning_rate": 4.4375e-06,
+      "loss": 0.0008514203131198883,
+      "num_tokens": 348280.0,
+      "reward": 1.353466796875,
+      "reward_std": 0.21437984704971313,
+      "rewards/JointRewardFunction/mean": 1.353466796875,
+      "rewards/JointRewardFunction/std": 0.21437986195087433,
+      "step": 90,
+      "step_time": 17.224812426199787
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 386.0,
+      "completions/max_terminated_length": 357.8,
+      "completions/mean_length": 267.65,
+      "completions/mean_terminated_length": 250.7500030517578,
+      "completions/min_length": 169.7,
+      "completions/min_terminated_length": 169.7,
+      "entropy": 0.3662784457206726,
+      "epoch": 0.6666666666666666,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.01239013671875,
+      "kl": 0.21083315466530622,
+      "learning_rate": 3.8125e-06,
+      "loss": 0.011665140837430954,
+      "num_tokens": 384576.0,
+      "reward": 1.34949951171875,
+      "reward_std": 0.23986690491437912,
+      "rewards/JointRewardFunction/mean": 1.34949951171875,
+      "rewards/JointRewardFunction/std": 0.2398669108748436,
+      "step": 100,
+      "step_time": 18.349693166400904
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 382.2,
+      "completions/max_terminated_length": 364.2,
+      "completions/mean_length": 275.575,
+      "completions/mean_terminated_length": 272.3714294433594,
+      "completions/min_length": 188.2,
+      "completions/min_terminated_length": 188.2,
+      "entropy": 0.37121466230601075,
+      "epoch": 0.7333333333333333,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.0146484375,
+      "kl": 0.21329910093918442,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.007188273221254348,
+      "num_tokens": 419570.0,
+      "reward": 1.350439453125,
+      "reward_std": 0.23384397297631948,
+      "rewards/JointRewardFunction/mean": 1.350439453125,
+      "rewards/JointRewardFunction/std": 0.23384397297631948,
+      "step": 110,
+      "step_time": 18.14425329649821
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 346.6,
+      "completions/max_terminated_length": 345.3,
+      "completions/mean_length": 252.15,
+      "completions/mean_terminated_length": 250.38750305175782,
+      "completions/min_length": 166.8,
+      "completions/min_terminated_length": 166.8,
+      "entropy": 0.4173679456114769,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 2.09375,
+      "kl": 0.21794578088447453,
+      "learning_rate": 2.5625e-06,
+      "loss": -0.0005294814705848694,
+      "num_tokens": 452006.0,
+      "reward": 1.35863037109375,
+      "reward_std": 0.24987269788980485,
+      "rewards/JointRewardFunction/mean": 1.35863037109375,
+      "rewards/JointRewardFunction/std": 0.24987269788980485,
+      "step": 120,
+      "step_time": 16.82072365879685
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 441.8,
+      "completions/max_terminated_length": 440.3,
+      "completions/mean_length": 301.7375,
+      "completions/mean_terminated_length": 296.75750122070315,
+      "completions/min_length": 191.0,
+      "completions/min_terminated_length": 191.0,
+      "entropy": 0.33190380278974774,
+      "epoch": 0.8666666666666667,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 2.09375,
+      "kl": 0.18061227248981596,
+      "learning_rate": 1.9375e-06,
+      "loss": 0.008612716197967529,
+      "num_tokens": 490397.0,
+      "reward": 1.374853515625,
+      "reward_std": 0.2561936320271343,
+      "rewards/JointRewardFunction/mean": 1.374853515625,
+      "rewards/JointRewardFunction/std": 0.2561936320271343,
+      "step": 130,
+      "step_time": 20.63984096989916
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 340.1,
+      "completions/max_terminated_length": 340.1,
+      "completions/mean_length": 256.5,
+      "completions/mean_terminated_length": 256.5,
+      "completions/min_length": 179.7,
+      "completions/min_terminated_length": 179.7,
+      "entropy": 0.38072127737104894,
+      "epoch": 0.9333333333333333,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 2.96875,
+      "kl": 0.21334810927510262,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": 0.012666280567646026,
+      "num_tokens": 523549.0,
+      "reward": 1.436767578125,
+      "reward_std": 0.153020023368299,
+      "rewards/JointRewardFunction/mean": 1.436767578125,
+      "rewards/JointRewardFunction/std": 0.153020023368299,
+      "step": 140,
+      "step_time": 16.57510228729916
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 371.9,
+      "completions/max_terminated_length": 370.6,
+      "completions/mean_length": 257.4125,
+      "completions/mean_terminated_length": 254.5607147216797,
+      "completions/min_length": 169.0,
+      "completions/min_terminated_length": 169.0,
+      "entropy": 0.3929610840976238,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.01513671875,
+      "kl": 0.21818328225053846,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.011788636445999146,
+      "num_tokens": 556454.0,
+      "reward": 1.348779296875,
+      "reward_std": 0.3280519276857376,
+      "rewards/JointRewardFunction/mean": 1.348779296875,
+      "rewards/JointRewardFunction/std": 0.32805192805826666,
+      "step": 150,
+      "step_time": 17.876252979701167
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 343.0,
+      "completions/max_terminated_length": 343.0,
+      "completions/mean_length": 240.45,
+      "completions/mean_terminated_length": 240.45,
+      "completions/min_length": 176.0,
+      "completions/min_terminated_length": 176.0,
+      "entropy": 0.4010548871010542,
+      "epoch": 1.0666666666666667,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.025146484375,
+      "kl": 0.22879955088719725,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 0.022160810232162476,
+      "num_tokens": 587606.0,
+      "reward": 1.3880859375,
+      "reward_std": 0.237497678399086,
+      "rewards/JointRewardFunction/mean": 1.3880859375,
+      "rewards/JointRewardFunction/std": 0.2374976843595505,
+      "step": 160,
+      "step_time": 16.50347660660045
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 587606,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/last-checkpoint/training_args.bin
+++ b/last-checkpoint/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9417437bcdb8d0a5c5a8b4411c9c02ad6ca73bb11f583f0a84d5aa9f9ab022e4
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155c3c86c366bde86b963e906171bb76328518aa7c48daf0c8b4837ccffc075c
+size 6171927112
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9417437bcdb8d0a5c5a8b4411c9c02ad6ca73bb11f583f0a84d5aa9f9ab022e4
+size 7249