初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-mbpp-s42-lambda-0p25 Source: Original Platform
2026-06-16 08:03:16 +08:00
commit 9dc0196201
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-0p25
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for expfinal-qwen-mbpp-s42-lambda-0p25
+
+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-0p25", 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/gm3e1a5v) 
+
+
+
+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:f4ec43cbcc4049469c8d8ed147d69642670532465e9b3a5bc1c718dab7a8ea51
+size 15427
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbac651203da4456e98922a452894754f7141f941c573acfe2ec2ff4857a31ef
+size 13084
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96620b9645eaccce84afb8c1cd55b692f0b750cd32e33a386242811264a90f52
+size 14756
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4bce7b25f0c05f01cbc235049c838513243a3f65edcafea7029a9b663a66016
+size 13719
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26afd72f160676f36edd857a9a29c552969933b58c0e41abea2ac456e45874e8
+size 13841
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae78dc9b9cd88c9acdfdc44d5f98064877f0189f9c693351f200fa24189bc565
+size 13541
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9273bff550305db3d0a27eb6f19baae42a11e96024c6b577969ef3f37dc59241
+size 14092
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e846b2d4c85098e7f1e41fb09d660f47f541902bce73a8f619efd4f2cfccf66d
+size 14668
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac0a2276c2e46ff8a342959268a739a655605642e897ad3f889456489418a0e
+size 14579
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95d78dc9cfb50b4b303323c655fa3d32ccb009fc56852683a4dbecb38b367ee
+size 13899
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb0b22417b4f0a54330ab1955a3301c71fd7bc1c7541dac15da5124416ebf84
+size 15811
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f63d8b15223b2955c10b74ee5badaa799bf85bcb07902d3946506e7afe4d159
+size 15727
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1817d910b73c7e42a51fcdb38ac1816f98efdf1bfa2f714b9da1e0576504564
+size 12840
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6832d6faa5eec6b2020d5917a02326bacdc76486c41650185c4898f41f84ed87
+size 11624
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4b8fdcda57e47d0cd96d6d889287277faffc32e76a0ed33b23f61840d22003
+size 14016
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db2e72da9d9d0336cf0c1ab02a964f6e645871f012a600c852a7d10f2b8a968
+size 13955
--- 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 sha256:445184cfe8c9bc43ab65cca3d906547483b0194ed77777df583b30815b629be6
+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": 0.1125,
+      "completions/max_length": 461.2,
+      "completions/max_terminated_length": 447.5,
+      "completions/mean_length": 376.325,
+      "completions/mean_terminated_length": 362.7201232910156,
+      "completions/min_length": 279.3,
+      "completions/min_terminated_length": 279.3,
+      "entropy": 0.2633976127021015,
+      "epoch": 0.06666666666666667,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 2.515625,
+      "kl": 0.06368143780127866,
+      "learning_rate": 9.4375e-06,
+      "loss": 0.013505807518959046,
+      "num_tokens": 42974.0,
+      "reward": 0.83304443359375,
+      "reward_std": 0.4131676867604256,
+      "rewards/JointRewardFunction/mean": 0.83304443359375,
+      "rewards/JointRewardFunction/std": 0.4131676971912384,
+      "step": 10,
+      "step_time": 20.514270653799578
+    },
+    {
+      "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": 409.6,
+      "completions/max_terminated_length": 384.0,
+      "completions/mean_length": 317.925,
+      "completions/mean_terminated_length": 308.6857147216797,
+      "completions/min_length": 249.7,
+      "completions/min_terminated_length": 249.7,
+      "entropy": 0.18158590691164136,
+      "epoch": 0.13333333333333333,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 3.421875,
+      "kl": 0.1635891743004322,
+      "learning_rate": 8.8125e-06,
+      "loss": 0.009117365628480912,
+      "num_tokens": 82168.0,
+      "reward": 1.0664794921875,
+      "reward_std": 0.29466880708932874,
+      "rewards/JointRewardFunction/mean": 1.0664794921875,
+      "rewards/JointRewardFunction/std": 0.29466880932450296,
+      "step": 20,
+      "step_time": 19.10480176490073
+    },
+    {
+      "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": 406.0,
+      "completions/max_terminated_length": 389.9,
+      "completions/mean_length": 295.1375,
+      "completions/mean_terminated_length": 285.5047637939453,
+      "completions/min_length": 206.6,
+      "completions/min_terminated_length": 206.6,
+      "entropy": 0.21663210522383453,
+      "epoch": 0.2,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 2.5625,
+      "kl": 0.18388604540377856,
+      "learning_rate": 8.1875e-06,
+      "loss": -0.01458892971277237,
+      "num_tokens": 117195.0,
+      "reward": 1.017388916015625,
+      "reward_std": 0.4210638031363487,
+      "rewards/JointRewardFunction/mean": 1.017388916015625,
+      "rewards/JointRewardFunction/std": 0.4210638180375099,
+      "step": 30,
+      "step_time": 19.004520852699535
+    },
+    {
+      "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": 453.9,
+      "completions/max_terminated_length": 431.6,
+      "completions/mean_length": 362.6625,
+      "completions/mean_terminated_length": 344.75762634277345,
+      "completions/min_length": 264.3,
+      "completions/min_terminated_length": 264.3,
+      "entropy": 0.2015760915353894,
+      "epoch": 0.26666666666666666,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 2.484375,
+      "kl": 0.17142300652340053,
+      "learning_rate": 7.5625e-06,
+      "loss": 0.021102146804332735,
+      "num_tokens": 159520.0,
+      "reward": 1.040948486328125,
+      "reward_std": 0.31338895484805107,
+      "rewards/JointRewardFunction/mean": 1.040948486328125,
+      "rewards/JointRewardFunction/std": 0.31338896676898004,
+      "step": 40,
+      "step_time": 20.873488509700472
+    },
+    {
+      "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": 410.2,
+      "completions/max_terminated_length": 389.0,
+      "completions/mean_length": 307.825,
+      "completions/mean_terminated_length": 303.1875030517578,
+      "completions/min_length": 237.3,
+      "completions/min_terminated_length": 237.3,
+      "entropy": 0.22014566687867046,
+      "epoch": 0.3333333333333333,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 0.014892578125,
+      "kl": 0.22832224890589714,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.039792636036872865,
+      "num_tokens": 196862.0,
+      "reward": 1.0728515625,
+      "reward_std": 0.32390306144952774,
+      "rewards/JointRewardFunction/mean": 1.0728515625,
+      "rewards/JointRewardFunction/std": 0.3239030599594116,
+      "step": 50,
+      "step_time": 19.236986151600284
+    },
+    {
+      "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": 397.9,
+      "completions/max_terminated_length": 383.6,
+      "completions/mean_length": 315.625,
+      "completions/mean_terminated_length": 310.5375,
+      "completions/min_length": 221.9,
+      "completions/min_terminated_length": 221.9,
+      "entropy": 0.19608328267931938,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 1.8203125,
+      "kl": 0.2169005206786096,
+      "learning_rate": 6.3125e-06,
+      "loss": 0.017893573641777037,
+      "num_tokens": 235512.0,
+      "reward": 1.103521728515625,
+      "reward_std": 0.26875718161463735,
+      "rewards/JointRewardFunction/mean": 1.103521728515625,
+      "rewards/JointRewardFunction/std": 0.26875719204545023,
+      "step": 60,
+      "step_time": 18.723443715600297
+    },
+    {
+      "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": 0.075,
+      "completions/max_length": 438.1,
+      "completions/max_terminated_length": 423.8,
+      "completions/mean_length": 340.4875,
+      "completions/mean_terminated_length": 326.67738342285156,
+      "completions/min_length": 246.7,
+      "completions/min_terminated_length": 246.7,
+      "entropy": 0.17470104116946458,
+      "epoch": 0.4666666666666667,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 1.90625,
+      "kl": 0.17606046590954066,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.012082196772098541,
+      "num_tokens": 276547.0,
+      "reward": 1.0309814453125,
+      "reward_std": 0.3187349811196327,
+      "rewards/JointRewardFunction/mean": 1.0309814453125,
+      "rewards/JointRewardFunction/std": 0.31873499751091006,
+      "step": 70,
+      "step_time": 20.5276982866013
+    },
+    {
+      "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": 441.0,
+      "completions/max_terminated_length": 439.9,
+      "completions/mean_length": 336.4,
+      "completions/mean_terminated_length": 334.3732147216797,
+      "completions/min_length": 238.0,
+      "completions/min_terminated_length": 238.0,
+      "entropy": 0.18340560160577296,
+      "epoch": 0.5333333333333333,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.04248046875,
+      "kl": 0.1858743063174188,
+      "learning_rate": 5.0625e-06,
+      "loss": -0.010596746206283569,
+      "num_tokens": 317131.0,
+      "reward": 1.1973876953125,
+      "reward_std": 0.14741100370883942,
+      "rewards/JointRewardFunction/mean": 1.1973876953125,
+      "rewards/JointRewardFunction/std": 0.1474110044538975,
+      "step": 80,
+      "step_time": 20.424764195699574
+    },
+    {
+      "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": 422.6,
+      "completions/max_terminated_length": 411.2,
+      "completions/mean_length": 319.8375,
+      "completions/mean_terminated_length": 309.8089294433594,
+      "completions/min_length": 222.4,
+      "completions/min_terminated_length": 222.4,
+      "entropy": 0.17013722923584282,
+      "epoch": 0.6,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 1.75,
+      "kl": 0.22596123907715082,
+      "learning_rate": 4.4375e-06,
+      "loss": 0.0059959739446640015,
+      "num_tokens": 356866.0,
+      "reward": 1.0788330078125,
+      "reward_std": 0.2970864400267601,
+      "rewards/JointRewardFunction/mean": 1.0788330078125,
+      "rewards/JointRewardFunction/std": 0.29708646088838575,
+      "step": 90,
+      "step_time": 19.734197501099334
+    },
+    {
+      "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": 397.6,
+      "completions/max_terminated_length": 372.7,
+      "completions/mean_length": 300.6,
+      "completions/mean_terminated_length": 287.1,
+      "completions/min_length": 220.5,
+      "completions/min_terminated_length": 220.5,
+      "entropy": 0.18155792271718382,
+      "epoch": 0.6666666666666666,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0279541015625,
+      "kl": 0.23375053312629462,
+      "learning_rate": 3.8125e-06,
+      "loss": 8.478660020045936e-05,
+      "num_tokens": 395798.0,
+      "reward": 1.1875,
+      "reward_std": 0.08880758583545685,
+      "rewards/JointRewardFunction/mean": 1.1875,
+      "rewards/JointRewardFunction/std": 0.08880758583545685,
+      "step": 100,
+      "step_time": 18.690151827099545
+    },
+    {
+      "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": 459.3,
+      "completions/max_terminated_length": 430.1,
+      "completions/mean_length": 335.3875,
+      "completions/mean_terminated_length": 328.3857177734375,
+      "completions/min_length": 243.9,
+      "completions/min_terminated_length": 243.9,
+      "entropy": 0.1711413566954434,
+      "epoch": 0.7333333333333333,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 1.4140625,
+      "kl": 0.18389353882521392,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.0026162829250097274,
+      "num_tokens": 435577.0,
+      "reward": 1.116802978515625,
+      "reward_std": 0.22371026836335658,
+      "rewards/JointRewardFunction/mean": 1.116802978515625,
+      "rewards/JointRewardFunction/std": 0.2237102746963501,
+      "step": 110,
+      "step_time": 21.052574327701223
+    },
+    {
+      "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": 380.6,
+      "completions/max_terminated_length": 371.3,
+      "completions/mean_length": 303.3,
+      "completions/mean_terminated_length": 292.425,
+      "completions/min_length": 222.7,
+      "completions/min_terminated_length": 222.7,
+      "entropy": 0.19935499429702758,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.59375,
+      "kl": 0.19222176214680076,
+      "learning_rate": 2.5625e-06,
+      "loss": 0.01612665057182312,
+      "num_tokens": 472105.0,
+      "reward": 1.0654541015625,
+      "reward_std": 0.28345242142677307,
+      "rewards/JointRewardFunction/mean": 1.0654541015625,
+      "rewards/JointRewardFunction/std": 0.28345243632793427,
+      "step": 120,
+      "step_time": 18.070694422099404
+    },
+    {
+      "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": 451.0,
+      "completions/max_terminated_length": 385.2,
+      "completions/mean_length": 331.925,
+      "completions/mean_terminated_length": 312.57203063964846,
+      "completions/min_length": 237.9,
+      "completions/min_terminated_length": 237.9,
+      "entropy": 0.1600348782725632,
+      "epoch": 0.8666666666666667,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 2.390625,
+      "kl": 0.18412442253902556,
+      "learning_rate": 1.9375e-06,
+      "loss": 0.01880526840686798,
+      "num_tokens": 512911.0,
+      "reward": 1.0941162109375,
+      "reward_std": 0.313115157186985,
+      "rewards/JointRewardFunction/mean": 1.0941162109375,
+      "rewards/JointRewardFunction/std": 0.31311516016721724,
+      "step": 130,
+      "step_time": 20.829227783899295
+    },
+    {
+      "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": 361.2,
+      "completions/max_terminated_length": 361.2,
+      "completions/mean_length": 285.1,
+      "completions/mean_terminated_length": 285.1,
+      "completions/min_length": 226.3,
+      "completions/min_terminated_length": 226.3,
+      "entropy": 0.18776001809164883,
+      "epoch": 0.9333333333333333,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.038818359375,
+      "kl": 0.2174981951713562,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": 0.00478580966591835,
+      "num_tokens": 548351.0,
+      "reward": 1.18388671875,
+      "reward_std": 0.18575088679790497,
+      "rewards/JointRewardFunction/mean": 1.18388671875,
+      "rewards/JointRewardFunction/std": 0.1857508897781372,
+      "step": 140,
+      "step_time": 17.17216874960086
+    },
+    {
+      "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": 431.1,
+      "completions/max_terminated_length": 389.6,
+      "completions/mean_length": 295.625,
+      "completions/mean_terminated_length": 285.92440643310545,
+      "completions/min_length": 217.1,
+      "completions/min_terminated_length": 217.1,
+      "entropy": 0.19556321045383812,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 1.984375,
+      "kl": 0.22088080924004316,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.03738939166069031,
+      "num_tokens": 584313.0,
+      "reward": 1.14267578125,
+      "reward_std": 0.25464810580015185,
+      "rewards/JointRewardFunction/mean": 1.14267578125,
+      "rewards/JointRewardFunction/std": 0.2546481089666486,
+      "step": 150,
+      "step_time": 20.206593494599836
+    },
+    {
+      "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": 372.0,
+      "completions/max_terminated_length": 365.0,
+      "completions/mean_length": 278.375,
+      "completions/mean_terminated_length": 276.0125,
+      "completions/min_length": 212.7,
+      "completions/min_terminated_length": 212.7,
+      "entropy": 0.19452018961310386,
+      "epoch": 1.0666666666666667,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 2.03125,
+      "kl": 0.2295491287484765,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": -0.003883980959653854,
+      "num_tokens": 618499.0,
+      "reward": 1.161102294921875,
+      "reward_std": 0.1998678043484688,
+      "rewards/JointRewardFunction/mean": 1.161102294921875,
+      "rewards/JointRewardFunction/std": 0.19986780881881713,
+      "step": 160,
+      "step_time": 17.52442454840075
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 618499,
+  "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:cd54c42cca96a218cec23fd7b18a28bd3cfc9a58f782c35554e1f9a8899e176d
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445184cfe8c9bc43ab65cca3d906547483b0194ed77777df583b30815b629be6
+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:cd54c42cca96a218cec23fd7b18a28bd3cfc9a58f782c35554e1f9a8899e176d
+size 7249