初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-mbpp-s42-lambda-0p0 Source: Original Platform
2026-06-16 04:58:17 +08:00
commit 0aa83b89c8
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-0p0
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# Model Card for expfinal-qwen-mbpp-s42-lambda-0p0
+
+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-0p0", 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/v5edfncc) 
+
+
+
+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:fbc76d485fd0640b155715f10c54e062c47e16d028a433c04dcab1da16bef16b
+size 19054
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7595b59c0e45512a666b702a95ac8817a447d4041a09793d8c4a968ddbf17fd9
+size 19060
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de91d43dfdd8408746d32186d55a13f4d9b0310d946f32651ddbd7cf253b4fb7
+size 18232
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826bb48be565c377bb64de1e0688b0b4c71721ab76688f819cb2c95a50e63863
+size 19256
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827ad260db9247a389559e67e4016abda1c4ed4931a325e5237d10229587eaa0
+size 18962
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511f7d9b092ac8f8cfb8cc4f4046fa95673c629f4e04922c37d64d5ed453ee8d
+size 16945
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf7818fb11ac62e82f38e6a646b81649a724cf6660b7a9a5617636ea766087d
+size 17896
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13180d57fe71677d97394b97359f6f91662d2569509975ddd369f603510ffee
+size 17608
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1d870b788698195912cbaaad5171c08e1525806a6a22b4c55b62c82f6d013b
+size 16040
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5626a4822ba10a732b1e426d01e4f629a29d14c56df1a26cc5cc137a1431289
+size 18379
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46a71e799942190ec77c11e673e6fa80413246f6e99cd132f59cc514bec2547
+size 18650
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb1defb212f3dee8ef9af9bea31ca469271013ad1adb0682ad0854b06c37c1
+size 17250
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a8c82b842058697f48442f22899cbb19c2065e2b9790985a3b94099f197e1d
+size 16983
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c340c4dc7c4a16bee1b744271934fa158d9c26e5d9ce4c708bf7b2cb6d5015bd
+size 16791
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b2b305023df8ba192ff0d9ef22e7ab42504202a26efd150a9192d837adf1ee
+size 16827
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804fa87a96311fb60fc71585b0f16003713e44ee47ec8e0214cabeedc771900d
+size 17839
--- 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 sha256:94887323c99ef1d5a14a3a3bad2299ac61ee1ac32fc8cb5f292ff4ca3cd9210d
+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": 0.7375,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 424.3,
+      "completions/mean_length": 490.4875,
+      "completions/mean_terminated_length": 405.65333557128906,
+      "completions/min_length": 428.2,
+      "completions/min_terminated_length": 377.0,
+      "entropy": 0.25217165537178515,
+      "epoch": 0.06666666666666667,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 1.5703125,
+      "kl": 0.0473901923673111,
+      "learning_rate": 9.4375e-06,
+      "loss": -0.0006930597126483917,
+      "num_tokens": 52107.0,
+      "reward": 0.675,
+      "reward_std": 0.399344927072525,
+      "rewards/JointRewardFunction/mean": 0.675,
+      "rewards/JointRewardFunction/std": 0.39934495091438293,
+      "step": 10,
+      "step_time": 22.542225440999847
+    },
+    {
+      "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": 0.8625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 284.7,
+      "completions/mean_length": 504.1875,
+      "completions/mean_terminated_length": 272.675,
+      "completions/min_length": 467.3,
+      "completions/min_terminated_length": 262.5,
+      "entropy": 0.202899154368788,
+      "epoch": 0.13333333333333333,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.546875,
+      "kl": 0.09602957724127918,
+      "learning_rate": 8.8125e-06,
+      "loss": -1.602950505912304e-05,
+      "num_tokens": 106202.0,
+      "reward": 0.7,
+      "reward_std": 0.3110164314508438,
+      "rewards/JointRewardFunction/mean": 0.7,
+      "rewards/JointRewardFunction/std": 0.3110164374113083,
+      "step": 20,
+      "step_time": 23.115930349700285
+    },
+    {
+      "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": 0.8625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 228.9,
+      "completions/mean_length": 495.1875,
+      "completions/mean_terminated_length": 212.45,
+      "completions/min_length": 461.5,
+      "completions/min_terminated_length": 205.5,
+      "entropy": 0.21361660687252879,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 1.6640625,
+      "kl": 0.09101211386732758,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.0017554668709635734,
+      "num_tokens": 157233.0,
+      "reward": 0.8625,
+      "reward_std": 0.2857582807540894,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.28575828671455383,
+      "step": 30,
+      "step_time": 22.91968024349999
+    },
+    {
+      "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": 0.9375,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 141.1,
+      "completions/mean_length": 506.8625,
+      "completions/mean_terminated_length": 132.6,
+      "completions/min_length": 482.5,
+      "completions/min_terminated_length": 124.1,
+      "entropy": 0.1852631143294275,
+      "epoch": 0.26666666666666666,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.90625,
+      "kl": 0.08399276400450617,
+      "learning_rate": 7.5625e-06,
+      "loss": 0.000752098485827446,
+      "num_tokens": 211094.0,
+      "reward": 0.7875,
+      "reward_std": 0.35561010539531707,
+      "rewards/JointRewardFunction/mean": 0.7875,
+      "rewards/JointRewardFunction/std": 0.35561011731624603,
+      "step": 40,
+      "step_time": 23.1765345180007
+    },
+    {
+      "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": 0.7375,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 379.3,
+      "completions/mean_length": 490.375,
+      "completions/mean_terminated_length": 355.89500122070314,
+      "completions/min_length": 437.5,
+      "completions/min_terminated_length": 335.1,
+      "entropy": 0.20920381098985671,
+      "epoch": 0.3333333333333333,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 1.671875,
+      "kl": 0.08546415464952588,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.002159162983298302,
+      "num_tokens": 263040.0,
+      "reward": 0.8625,
+      "reward_std": 0.2857582807540894,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.28575828671455383,
+      "step": 50,
+      "step_time": 23.374498161900373
+    },
+    {
+      "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": 0.525,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 472.5,
+      "completions/mean_length": 468.2875,
+      "completions/mean_terminated_length": 420.48833923339845,
+      "completions/min_length": 354.2,
+      "completions/min_terminated_length": 354.2,
+      "entropy": 0.2077056860551238,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.4609375,
+      "kl": 0.09320587411057205,
+      "learning_rate": 6.3125e-06,
+      "loss": -0.0018056023865938187,
+      "num_tokens": 313903.0,
+      "reward": 0.8625,
+      "reward_std": 0.21504760384559632,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.2150476098060608,
+      "step": 60,
+      "step_time": 23.37301885729976
+    },
+    {
+      "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": 0.6625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 405.9,
+      "completions/mean_length": 482.5875,
+      "completions/mean_terminated_length": 375.9566711425781,
+      "completions/min_length": 381.3,
+      "completions/min_terminated_length": 330.1,
+      "entropy": 0.2098280948586762,
+      "epoch": 0.4666666666666667,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 1.2734375,
+      "kl": 0.07904624061193317,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.002197714149951935,
+      "num_tokens": 366306.0,
+      "reward": 0.7875,
+      "reward_std": 0.35561010539531707,
+      "rewards/JointRewardFunction/mean": 0.7875,
+      "rewards/JointRewardFunction/std": 0.35561011731624603,
+      "step": 70,
+      "step_time": 23.226104836099694
+    },
+    {
+      "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": 0.475,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 476.6,
+      "completions/mean_length": 462.95,
+      "completions/mean_terminated_length": 421.48095703125,
+      "completions/min_length": 355.3,
+      "completions/min_terminated_length": 355.3,
+      "entropy": 0.23389623733237386,
+      "epoch": 0.5333333333333333,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.421875,
+      "kl": 1.7520212520845235,
+      "learning_rate": 5.0625e-06,
+      "loss": 0.014839766919612885,
+      "num_tokens": 417014.0,
+      "reward": 0.825,
+      "reward_std": 0.3429849535226822,
+      "rewards/JointRewardFunction/mean": 0.825,
+      "rewards/JointRewardFunction/std": 0.34298495948314667,
+      "step": 80,
+      "step_time": 23.28830157520024
+    },
+    {
+      "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": 0.6125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 400.4,
+      "completions/mean_length": 469.4375,
+      "completions/mean_terminated_length": 354.97833557128905,
+      "completions/min_length": 361.2,
+      "completions/min_terminated_length": 310.0,
+      "entropy": 0.23284959373995662,
+      "epoch": 0.6,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.00860595703125,
+      "kl": 0.09338290304876865,
+      "learning_rate": 4.4375e-06,
+      "loss": -0.00816301703453064,
+      "num_tokens": 468717.0,
+      "reward": 0.775,
+      "reward_std": 0.2112731784582138,
+      "rewards/JointRewardFunction/mean": 0.775,
+      "rewards/JointRewardFunction/std": 0.2112731844186783,
+      "step": 90,
+      "step_time": 23.190502532400387
+    },
+    {
+      "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": 0.7125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 375.5,
+      "completions/mean_length": 486.9625,
+      "completions/mean_terminated_length": 343.10833435058595,
+      "completions/min_length": 421.6,
+      "completions/min_terminated_length": 319.2,
+      "entropy": 0.23229737337678671,
+      "epoch": 0.6666666666666666,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 2.265625,
+      "kl": 0.10509764784947037,
+      "learning_rate": 3.8125e-06,
+      "loss": 0.012743420898914337,
+      "num_tokens": 522558.0,
+      "reward": 0.7,
+      "reward_std": 0.3737070143222809,
+      "rewards/JointRewardFunction/mean": 0.7,
+      "rewards/JointRewardFunction/std": 0.37370702624320984,
+      "step": 100,
+      "step_time": 23.302893278999363
+    },
+    {
+      "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": 0.5625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 470.8,
+      "completions/mean_length": 468.9,
+      "completions/mean_terminated_length": 418.7083374023438,
+      "completions/min_length": 370.4,
+      "completions/min_terminated_length": 370.4,
+      "entropy": 0.21385292476043105,
+      "epoch": 0.7333333333333333,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 1.65625,
+      "kl": 0.10132698961533607,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.004469546675682068,
+      "num_tokens": 573018.0,
+      "reward": 0.8625,
+      "reward_std": 0.22768060266971588,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.22768060266971588,
+      "step": 110,
+      "step_time": 23.21463985899991
+    },
+    {
+      "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": 0.475,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 498.2,
+      "completions/mean_length": 464.075,
+      "completions/mean_terminated_length": 425.3933380126953,
+      "completions/min_length": 350.8,
+      "completions/min_terminated_length": 350.8,
+      "entropy": 0.24488159762695433,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 1.1953125,
+      "kl": 0.11085290028713643,
+      "learning_rate": 2.5625e-06,
+      "loss": 0.007788118720054626,
+      "num_tokens": 622408.0,
+      "reward": 0.85,
+      "reward_std": 0.3265853762626648,
+      "rewards/JointRewardFunction/mean": 0.85,
+      "rewards/JointRewardFunction/std": 0.3265853762626648,
+      "step": 120,
+      "step_time": 23.28342122000013
+    },
+    {
+      "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": 0.575,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 386.7,
+      "completions/mean_length": 473.75,
+      "completions/mean_terminated_length": 338.4150054931641,
+      "completions/min_length": 396.3,
+      "completions/min_terminated_length": 293.9,
+      "entropy": 0.20693162837997078,
+      "epoch": 0.8666666666666667,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.0274658203125,
+      "kl": 0.1018260810058564,
+      "learning_rate": 1.9375e-06,
+      "loss": 0.004177199304103851,
+      "num_tokens": 674560.0,
+      "reward": 0.7125,
+      "reward_std": 0.28489942848682404,
+      "rewards/JointRewardFunction/mean": 0.7125,
+      "rewards/JointRewardFunction/std": 0.284899440407753,
+      "step": 130,
+      "step_time": 23.369472190498527
+    },
+    {
+      "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": 0.5625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 474.9,
+      "completions/mean_length": 473.4625,
+      "completions/mean_terminated_length": 436.53857421875,
+      "completions/min_length": 387.5,
+      "completions/min_terminated_length": 387.5,
+      "entropy": 0.21715571610257028,
+      "epoch": 0.9333333333333333,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 2.65625,
+      "kl": 0.09930992983281613,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": -0.003046867996454239,
+      "num_tokens": 725069.0,
+      "reward": 0.8625,
+      "reward_std": 0.22220884561538695,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.22220885157585143,
+      "step": 140,
+      "step_time": 23.435090316800597
+    },
+    {
+      "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": 0.525,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 465.8,
+      "completions/mean_length": 467.0125,
+      "completions/mean_terminated_length": 418.62000427246096,
+      "completions/min_length": 369.5,
+      "completions/min_terminated_length": 369.5,
+      "entropy": 0.23989124922081828,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.031982421875,
+      "kl": 0.11200284436345101,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.0012525198981165886,
+      "num_tokens": 774742.0,
+      "reward": 0.9125,
+      "reward_std": 0.16875659823417663,
+      "rewards/JointRewardFunction/mean": 0.9125,
+      "rewards/JointRewardFunction/std": 0.1687566041946411,
+      "step": 150,
+      "step_time": 23.458841795299485
+    },
+    {
+      "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": 0.475,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 451.2,
+      "completions/mean_length": 453.7375,
+      "completions/mean_terminated_length": 395.75953063964846,
+      "completions/min_length": 338.2,
+      "completions/min_terminated_length": 338.2,
+      "entropy": 0.24999441923573612,
+      "epoch": 1.0666666666666667,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.0250244140625,
+      "kl": 0.10539310625754297,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 0.012749123573303222,
+      "num_tokens": 822957.0,
+      "reward": 0.8625,
+      "reward_std": 0.1759178400039673,
+      "rewards/JointRewardFunction/mean": 0.8625,
+      "rewards/JointRewardFunction/std": 0.17591784596443177,
+      "step": 160,
+      "step_time": 23.16400302819966
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 822957,
+  "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 sha256:826637f41ec8cfa7e08ea7c1254ad24a7fe46492afd59522ca1fccd468f245a7
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94887323c99ef1d5a14a3a3bad2299ac61ee1ac32fc8cb5f292ff4ca3cd9210d
+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 sha256:826637f41ec8cfa7e08ea7c1254ad24a7fe46492afd59522ca1fccd468f245a7
+size 7249