初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-mbpp-s42-lambda-0p75 Source: Original Platform
2026-06-16 06:58:17 +08:00
commit 72640e3c3c
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-0p75
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# Model Card for expfinal-qwen-mbpp-s42-lambda-0p75
+
+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-0p75", 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/ygj72uo9) 
+
+
+
+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 sha256:4759825f34ab1a4e2b3436d0e0c513856587e242d04bbcaee84f641f6f7db680
+size 14278
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1f1f51bdc71b4c076b70511255f730521face27b392168d5e7bcec64c2dd09
+size 14435
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a26e1179f8e08b57c51f03344f21b695c85b4ce2d17ff148919d3a5e6f2904
+size 14987
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800593a66d57f53c12faff4e1f426b11f846d1d8a809090ed918e0f9d64e96ab
+size 14276
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7ebf3cc40b42a20629d5207a831e6540c96fdf7200636c9f311be925d55fbd
+size 16951
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab839d5cd2fbb31028790207b60e13c9a41d0fc315d3ee52fd59914a46b57a1
+size 17181
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09134033cacd8cb6f64573317575cc1df987bb9091b134dd57d440d015c10c3
+size 15649
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaec41b4a4bae7fd30722d5614a141884b348085686861df21831771161086df
+size 17667
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515ba7091175f986b1a02166baba9170033faa51a7bd8b9801fc80547e351cd1
+size 16809
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28477cfbb7b51953c24cb577e9d0c7fb8519d255a79964524a90af665516a2aa
+size 15182
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85940ea412bb805d2f2f34defea92f36dda1fc608d4535fb7618f7e076082d85
+size 16789
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e38b75427052a43a4268081a0052a30a5c80b66ac4158ff109284bdb81e9438
+size 18474
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff4469e753ffa11b38a6e2153091f527ae743d9a9a4924d4992ec7a61ff322b
+size 12896
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5957b6ed35fe7a10bf49400f90f31ea2609cb1d3bde8d3198dd13df849d9d79b
+size 14117
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e7c50fa7aea973d00c0c85500fae58d0d80ac7cde60b4b657b1f0462239385
+size 15649
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a407d307866993e202b1e9801d5798223dbf42fe263f45b708725c27118c9b
+size 13980
--- 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 sha256:6753ac3d39840dcbcb8da23e74296953ddc011bb9abcf19b87e7c7e7bfb56447
+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": 0.0625,
+      "completions/max_length": 419.8,
+      "completions/max_terminated_length": 406.8,
+      "completions/mean_length": 314.8625,
+      "completions/mean_terminated_length": 307.5414337158203,
+      "completions/min_length": 206.3,
+      "completions/min_terminated_length": 206.3,
+      "entropy": 0.44715926721692084,
+      "epoch": 0.06666666666666667,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 4.625,
+      "kl": 0.09871633112052222,
+      "learning_rate": 9.4375e-06,
+      "loss": -0.010261553525924682,
+      "num_tokens": 38057.0,
+      "reward": 0.9905517578125,
+      "reward_std": 0.6565703094005585,
+      "rewards/JointRewardFunction/mean": 0.9905517578125,
+      "rewards/JointRewardFunction/std": 0.6565703094005585,
+      "step": 10,
+      "step_time": 19.035294922399043
+    },
+    {
+      "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": 0.2,
+      "completions/max_length": 458.4,
+      "completions/max_terminated_length": 426.1,
+      "completions/mean_length": 343.8,
+      "completions/mean_terminated_length": 313.08583984375,
+      "completions/min_length": 211.7,
+      "completions/min_terminated_length": 211.7,
+      "entropy": 0.31359912948682905,
+      "epoch": 0.13333333333333333,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 3.125,
+      "kl": 0.14868967132642866,
+      "learning_rate": 8.8125e-06,
+      "loss": -0.023439544439315795,
+      "num_tokens": 79321.0,
+      "reward": 1.072357177734375,
+      "reward_std": 0.5760923266410828,
+      "rewards/JointRewardFunction/mean": 1.072357177734375,
+      "rewards/JointRewardFunction/std": 0.5760923385620117,
+      "step": 20,
+      "step_time": 21.0788949906022
+    },
+    {
+      "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": 351.8,
+      "completions/max_terminated_length": 351.8,
+      "completions/mean_length": 260.625,
+      "completions/mean_terminated_length": 260.625,
+      "completions/min_length": 174.2,
+      "completions/min_terminated_length": 174.2,
+      "entropy": 0.3843053654767573,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 4.5625,
+      "kl": 0.18629266200587152,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.004870641976594925,
+      "num_tokens": 111587.0,
+      "reward": 1.3501953125,
+      "reward_std": 0.6562108278274537,
+      "rewards/JointRewardFunction/mean": 1.3501953125,
+      "rewards/JointRewardFunction/std": 0.6562108367681503,
+      "step": 30,
+      "step_time": 16.898221987598664
+    },
+    {
+      "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": 429.1,
+      "completions/max_terminated_length": 425.2,
+      "completions/mean_length": 327.5125,
+      "completions/mean_terminated_length": 321.53809814453126,
+      "completions/min_length": 227.9,
+      "completions/min_terminated_length": 227.9,
+      "entropy": 0.44414809048175813,
+      "epoch": 0.26666666666666666,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 6.34375,
+      "kl": 0.14110819818452,
+      "learning_rate": 7.5625e-06,
+      "loss": -0.03268973827362061,
+      "num_tokens": 151100.0,
+      "reward": 1.493701171875,
+      "reward_std": 0.3899420065339655,
+      "rewards/JointRewardFunction/mean": 1.493701171875,
+      "rewards/JointRewardFunction/std": 0.38994201249442995,
+      "step": 40,
+      "step_time": 20.12026042639991
+    },
+    {
+      "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": 0.225,
+      "completions/max_length": 472.2,
+      "completions/max_terminated_length": 427.6,
+      "completions/mean_length": 352.75,
+      "completions/mean_terminated_length": 313.9489349365234,
+      "completions/min_length": 201.0,
+      "completions/min_terminated_length": 201.0,
+      "entropy": 0.5324544316157699,
+      "epoch": 0.3333333333333333,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 5.3125,
+      "kl": 0.13007921809330583,
+      "learning_rate": 6.9375e-06,
+      "loss": -0.03016577959060669,
+      "num_tokens": 192036.0,
+      "reward": 1.0732177734375,
+      "reward_std": 0.5164182722568512,
+      "rewards/JointRewardFunction/mean": 1.0732177734375,
+      "rewards/JointRewardFunction/std": 0.5164182841777801,
+      "step": 50,
+      "step_time": 21.588160099001833
+    },
+    {
+      "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": 0.225,
+      "completions/max_length": 495.4,
+      "completions/max_terminated_length": 461.4,
+      "completions/mean_length": 396.95,
+      "completions/mean_terminated_length": 363.4666687011719,
+      "completions/min_length": 224.4,
+      "completions/min_terminated_length": 224.4,
+      "entropy": 0.47121726758778093,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 2.46875,
+      "kl": 0.10462474231608213,
+      "learning_rate": 6.3125e-06,
+      "loss": -0.031146174669265746,
+      "num_tokens": 237192.0,
+      "reward": 1.193585205078125,
+      "reward_std": 0.5929911494255066,
+      "rewards/JointRewardFunction/mean": 1.193585205078125,
+      "rewards/JointRewardFunction/std": 0.592991155385971,
+      "step": 60,
+      "step_time": 22.437090325800817
+    },
+    {
+      "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": 0.275,
+      "completions/max_length": 497.6,
+      "completions/max_terminated_length": 455.6,
+      "completions/mean_length": 392.0375,
+      "completions/mean_terminated_length": 351.8452484130859,
+      "completions/min_length": 243.3,
+      "completions/min_terminated_length": 243.3,
+      "entropy": 0.4913482774049044,
+      "epoch": 0.4666666666666667,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 4.21875,
+      "kl": 0.11023280541412532,
+      "learning_rate": 5.6875e-06,
+      "loss": -0.02786441147327423,
+      "num_tokens": 282351.0,
+      "reward": 1.166510009765625,
+      "reward_std": 0.5283917605876922,
+      "rewards/JointRewardFunction/mean": 1.166510009765625,
+      "rewards/JointRewardFunction/std": 0.528391769528389,
+      "step": 70,
+      "step_time": 22.72093682029881
+    },
+    {
+      "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": 0.3125,
+      "completions/max_length": 507.2,
+      "completions/max_terminated_length": 447.3,
+      "completions/mean_length": 409.9125,
+      "completions/mean_terminated_length": 365.60191040039064,
+      "completions/min_length": 248.5,
+      "completions/min_terminated_length": 248.5,
+      "entropy": 0.43941801562905314,
+      "epoch": 0.5333333333333333,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 1.640625,
+      "kl": 0.12287256089039147,
+      "learning_rate": 5.0625e-06,
+      "loss": -0.024439637362957,
+      "num_tokens": 328816.0,
+      "reward": 1.467431640625,
+      "reward_std": 0.4256438536103815,
+      "rewards/JointRewardFunction/mean": 1.467431640625,
+      "rewards/JointRewardFunction/std": 0.42564386553131045,
+      "step": 80,
+      "step_time": 23.137156244499057
+    },
+    {
+      "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": 0.1875,
+      "completions/max_length": 486.2,
+      "completions/max_terminated_length": 463.3,
+      "completions/mean_length": 379.0625,
+      "completions/mean_terminated_length": 360.1238128662109,
+      "completions/min_length": 241.6,
+      "completions/min_terminated_length": 241.6,
+      "entropy": 0.3873957570642233,
+      "epoch": 0.6,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 2.15625,
+      "kl": 0.12395602646283806,
+      "learning_rate": 4.4375e-06,
+      "loss": 0.0433960497379303,
+      "num_tokens": 373289.0,
+      "reward": 1.3514892578125,
+      "reward_std": 0.43082923418842256,
+      "rewards/JointRewardFunction/mean": 1.3514892578125,
+      "rewards/JointRewardFunction/std": 0.4308292371686548,
+      "step": 90,
+      "step_time": 22.175798371599377
+    },
+    {
+      "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": 0.1375,
+      "completions/max_length": 475.4,
+      "completions/max_terminated_length": 439.4,
+      "completions/mean_length": 344.5625,
+      "completions/mean_terminated_length": 319.0309600830078,
+      "completions/min_length": 209.0,
+      "completions/min_terminated_length": 209.0,
+      "entropy": 0.3818320112302899,
+      "epoch": 0.6666666666666666,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 1.7265625,
+      "kl": 0.1494429545942694,
+      "learning_rate": 3.8125e-06,
+      "loss": -0.00486765056848526,
+      "num_tokens": 415738.0,
+      "reward": 1.4651611328125,
+      "reward_std": 0.453005512803793,
+      "rewards/JointRewardFunction/mean": 1.4651611328125,
+      "rewards/JointRewardFunction/std": 0.45300552546977996,
+      "step": 100,
+      "step_time": 21.99789129000128
+    },
+    {
+      "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": 0.125,
+      "completions/max_length": 500.8,
+      "completions/max_terminated_length": 454.0,
+      "completions/mean_length": 348.225,
+      "completions/mean_terminated_length": 326.1460815429688,
+      "completions/min_length": 184.0,
+      "completions/min_terminated_length": 184.0,
+      "entropy": 0.38654828127473595,
+      "epoch": 0.7333333333333333,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 4.25,
+      "kl": 0.19588984637521206,
+      "learning_rate": 3.1875e-06,
+      "loss": -0.04184774756431579,
+      "num_tokens": 456544.0,
+      "reward": 1.449822998046875,
+      "reward_std": 0.40167671740055083,
+      "rewards/JointRewardFunction/mean": 1.449822998046875,
+      "rewards/JointRewardFunction/std": 0.40167671740055083,
+      "step": 110,
+      "step_time": 22.696052773901464
+    },
+    {
+      "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": 0.1875,
+      "completions/max_length": 474.8,
+      "completions/max_terminated_length": 426.7,
+      "completions/mean_length": 338.5375,
+      "completions/mean_terminated_length": 308.2898864746094,
+      "completions/min_length": 179.5,
+      "completions/min_terminated_length": 179.5,
+      "entropy": 0.42813673401251434,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 3.625,
+      "kl": 0.188834874285385,
+      "learning_rate": 2.5625e-06,
+      "loss": -0.022572511434555055,
+      "num_tokens": 495891.0,
+      "reward": 1.37578125,
+      "reward_std": 0.485464009642601,
+      "rewards/JointRewardFunction/mean": 1.37578125,
+      "rewards/JointRewardFunction/std": 0.4854640245437622,
+      "step": 120,
+      "step_time": 21.932242763400062
+    },
+    {
+      "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": 0.225,
+      "completions/max_length": 480.4,
+      "completions/max_terminated_length": 457.0,
+      "completions/mean_length": 353.0375,
+      "completions/mean_terminated_length": 309.4391723632813,
+      "completions/min_length": 93.9,
+      "completions/min_terminated_length": 93.9,
+      "entropy": 0.4207899322733283,
+      "epoch": 0.8666666666666667,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 3.140625,
+      "kl": 0.19314469541423024,
+      "learning_rate": 1.9375e-06,
+      "loss": -0.10344405174255371,
+      "num_tokens": 538386.0,
+      "reward": 1.3167236328125,
+      "reward_std": 0.5021238774061203,
+      "rewards/JointRewardFunction/mean": 1.3167236328125,
+      "rewards/JointRewardFunction/std": 0.5021239161491394,
+      "step": 130,
+      "step_time": 22.154275490202053
+    },
+    {
+      "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": 0.1375,
+      "completions/max_length": 468.1,
+      "completions/max_terminated_length": 443.4,
+      "completions/mean_length": 351.3625,
+      "completions/mean_terminated_length": 333.25274353027345,
+      "completions/min_length": 215.1,
+      "completions/min_terminated_length": 215.1,
+      "entropy": 0.3897366087883711,
+      "epoch": 0.9333333333333333,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 1.8828125,
+      "kl": 0.1783840640448034,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": -0.012397536635398864,
+      "num_tokens": 579127.0,
+      "reward": 1.5228759765625,
+      "reward_std": 0.3425671649631113,
+      "rewards/JointRewardFunction/mean": 1.5228759765625,
+      "rewards/JointRewardFunction/std": 0.3425671679433435,
+      "step": 140,
+      "step_time": 21.521125249801845
+    },
+    {
+      "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": 482.1,
+      "completions/max_terminated_length": 444.4,
+      "completions/mean_length": 354.5375,
+      "completions/mean_terminated_length": 328.6072692871094,
+      "completions/min_length": 207.4,
+      "completions/min_terminated_length": 207.4,
+      "entropy": 0.4106031972914934,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 1.703125,
+      "kl": 0.16290537370368838,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.014532069861888885,
+      "num_tokens": 619802.0,
+      "reward": 1.502001953125,
+      "reward_std": 0.44335485696792604,
+      "rewards/JointRewardFunction/mean": 1.502001953125,
+      "rewards/JointRewardFunction/std": 0.443354868888855,
+      "step": 150,
+      "step_time": 22.203639667498646
+    },
+    {
+      "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": 0.125,
+      "completions/max_length": 432.7,
+      "completions/max_terminated_length": 389.6,
+      "completions/mean_length": 310.0125,
+      "completions/mean_terminated_length": 283.19702911376953,
+      "completions/min_length": 129.3,
+      "completions/min_terminated_length": 129.3,
+      "entropy": 0.43815543316304684,
+      "epoch": 1.0666666666666667,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 3.484375,
+      "kl": 0.21010836036875843,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": -0.05822192430496216,
+      "num_tokens": 656519.0,
+      "reward": 1.34354248046875,
+      "reward_std": 0.5034710764884949,
+      "rewards/JointRewardFunction/mean": 1.34354248046875,
+      "rewards/JointRewardFunction/std": 0.503471103310585,
+      "step": 160,
+      "step_time": 20.17411774720167
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 656519,
+  "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 sha256:425595137c947d190b8d7b621fa2afaf7a55b15db5aef2061b280d7894998eec
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6753ac3d39840dcbcb8da23e74296953ddc011bb9abcf19b87e7c7e7bfb56447
+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 sha256:425595137c947d190b8d7b621fa2afaf7a55b15db5aef2061b280d7894998eec
+size 7249