初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-island-s42-lambda-0p0 Source: Original Platform
2026-06-16 05:36:17 +08:00
commit 23e0010cda
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: Qwen/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: expfinal-qwen-island-s42-lambda-0p0
+tags:
+- generated_from_trainer
+- grpo
+- trl
+licence: license
+---
+
+# Model Card for expfinal-qwen-island-s42-lambda-0p0
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
+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-island-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/w7r1ivm1) 
+
+
+
+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 sha256:709d5f1748fb55b0462c6b61c3eb2f9ec74ea16c8373b0d32ee0a618c6311bd3
+size 18500
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b70299be669593867088632af6e2ac9332993402b6d23582cdcb161b161245
+size 20219
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19274048def0678aaae235dccfee33e64691ef8225a4ae5b873f643b0c47eb8b
+size 24563
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2b9f7c4d5742a82eada06a275d0b18e30c6a6e2692f129977cf33eb9d08fd3
+size 21514
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f45b4f7cff64bbd18c32d94b096828c57f4f3193c6c5d7f9a9545d9af050fc
+size 27209
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5071d1f07f49831a7cc85dc41bcd5ad3ae4aa7b14562b82932039fc747e85d0d
+size 22894
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3792f5cb2075ce7b444c54e237529a0e0a0161920941e25f7b92b89ff062db38
+size 21338
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00825a02117e4ca226ae94bf40d21eb6086a3d101f72e69131af83cb1141d9aa
+size 21057
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed71a7755dfa973f55a514a2d2cf7015b669ae63e8e0960e3cd9ce513dead6ac
+size 22697
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0d4224c99a311dd866c863871ca09f9a168096ee669c8a66b19ba67240f7f0
+size 24068
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b41e1b8759b1b1000e36d3e74fa8da3067eb4b2274eb1b827863de954ab091c
+size 24804
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671507b63f1e5f22f963785f15d17e6decca4359f123c5e0cc50ad6d43c56104
+size 22330
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c943d189936de8af274d38829e2286c2d6fad1e4d26d253db1153912abfb6f6
+size 23072
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d8430dcfd67ff33bd0570cb856d84a45f7f1298dc933af80602870837d49f2
+size 24019
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d937515c8720c05d349bab053159685dfae3616027ac87867ea9e90dc0ff5bb
+size 21606
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e27f7525ffcf770056b275a4fe9791033657edd2cd2c86d1bb1a11bfd6ff20
+size 24367
--- 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 sha256:19ec7b8100fdbb732326b9938aaf5de706ac0cd9a0aa6fbb12e56ff42f02fc49
+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": 1.28,
+  "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": 0.05,
+      "completions/max_length": 894.8,
+      "completions/max_terminated_length": 821.2,
+      "completions/mean_length": 560.2,
+      "completions/mean_terminated_length": 540.6345306396485,
+      "completions/min_length": 279.5,
+      "completions/min_terminated_length": 279.5,
+      "entropy": 0.38268125932663677,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.4375,
+      "kl": 0.07789193278222228,
+      "learning_rate": 9.4375e-06,
+      "loss": -0.007836591452360153,
+      "num_tokens": 65460.0,
+      "reward": 0.65,
+      "reward_std": 0.46797851026058196,
+      "rewards/JointRewardFunction/mean": 0.65,
+      "rewards/JointRewardFunction/std": 0.4679785281419754,
+      "step": 10,
+      "step_time": 36.23508502000004
+    },
+    {
+      "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": 900.1,
+      "completions/max_terminated_length": 823.7,
+      "completions/mean_length": 578.525,
+      "completions/mean_terminated_length": 543.8116729736328,
+      "completions/min_length": 254.6,
+      "completions/min_terminated_length": 254.6,
+      "entropy": 0.23411482032388448,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.775,
+      "grad_norm": 1.1484375,
+      "kl": 0.1648747116792947,
+      "learning_rate": 8.8125e-06,
+      "loss": 0.0052785202860832214,
+      "num_tokens": 132386.0,
+      "reward": 0.6625,
+      "reward_std": 0.46628117859363555,
+      "rewards/JointRewardFunction/mean": 0.6625,
+      "rewards/JointRewardFunction/std": 0.4662812024354935,
+      "step": 20,
+      "step_time": 37.938748809599566
+    },
+    {
+      "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": 876.9,
+      "completions/max_terminated_length": 829.5,
+      "completions/mean_length": 622.2,
+      "completions/mean_terminated_length": 611.7642944335937,
+      "completions/min_length": 477.6,
+      "completions/min_terminated_length": 477.6,
+      "entropy": 0.22628286899998784,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.0218505859375,
+      "kl": 0.12199527090415359,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.007959160953760147,
+      "num_tokens": 202606.0,
+      "reward": 0.9375,
+      "reward_std": 0.12246559262275696,
+      "rewards/JointRewardFunction/mean": 0.9375,
+      "rewards/JointRewardFunction/std": 0.12246559858322144,
+      "step": 30,
+      "step_time": 37.057444848399975
+    },
+    {
+      "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": 810.6,
+      "completions/max_terminated_length": 731.4,
+      "completions/mean_length": 596.8625,
+      "completions/mean_terminated_length": 584.707144165039,
+      "completions/min_length": 438.4,
+      "completions/min_terminated_length": 438.4,
+      "entropy": 0.42070485297590493,
+      "epoch": 0.32,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 1.1015625,
+      "kl": 0.10627949037589132,
+      "learning_rate": 7.5625e-06,
+      "loss": -0.00913204848766327,
+      "num_tokens": 270929.0,
+      "reward": 0.9,
+      "reward_std": 0.20411193668842315,
+      "rewards/JointRewardFunction/mean": 0.9,
+      "rewards/JointRewardFunction/std": 0.20411194264888763,
+      "step": 40,
+      "step_time": 34.16536340820039
+    },
+    {
+      "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": 916.6,
+      "completions/max_terminated_length": 800.7,
+      "completions/mean_length": 642.275,
+      "completions/mean_terminated_length": 620.6982238769531,
+      "completions/min_length": 483.4,
+      "completions/min_terminated_length": 483.4,
+      "entropy": 0.545534435659647,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.9921875,
+      "kl": 0.09743389897048474,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.019783291220664977,
+      "num_tokens": 343141.0,
+      "reward": 0.9125,
+      "reward_std": 0.19864802658557892,
+      "rewards/JointRewardFunction/mean": 0.9125,
+      "rewards/JointRewardFunction/std": 0.19864802658557892,
+      "step": 50,
+      "step_time": 38.55176728389906
+    },
+    {
+      "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": 774.9,
+      "completions/max_terminated_length": 774.9,
+      "completions/mean_length": 599.525,
+      "completions/mean_terminated_length": 599.525,
+      "completions/min_length": 438.8,
+      "completions/min_terminated_length": 438.8,
+      "entropy": 0.5808290097862482,
+      "epoch": 0.48,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.035400390625,
+      "kl": 0.10702053690329194,
+      "learning_rate": 6.3125e-06,
+      "loss": -0.009540864825248718,
+      "num_tokens": 411443.0,
+      "reward": 0.9625,
+      "reward_std": 0.10606601536273956,
+      "rewards/JointRewardFunction/mean": 0.9625,
+      "rewards/JointRewardFunction/std": 0.10606601536273956,
+      "step": 60,
+      "step_time": 33.111361246699744
+    },
+    {
+      "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": 848.1,
+      "completions/max_terminated_length": 757.4,
+      "completions/mean_length": 626.325,
+      "completions/mean_terminated_length": 609.8857238769531,
+      "completions/min_length": 511.5,
+      "completions/min_terminated_length": 511.5,
+      "entropy": 0.4436331996694207,
+      "epoch": 0.56,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.060791015625,
+      "kl": 0.08952742610126734,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.014259077608585358,
+      "num_tokens": 482005.0,
+      "reward": 0.95,
+      "reward_std": 0.11700168251991272,
+      "rewards/JointRewardFunction/mean": 0.95,
+      "rewards/JointRewardFunction/std": 0.11700168251991272,
+      "step": 70,
+      "step_time": 35.991650615099935
+    },
+    {
+      "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": 787.7,
+      "completions/max_terminated_length": 747.8,
+      "completions/mean_length": 593.25,
+      "completions/mean_terminated_length": 587.5642883300782,
+      "completions/min_length": 493.6,
+      "completions/min_terminated_length": 493.6,
+      "entropy": 0.328166064620018,
+      "epoch": 0.64,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.017822265625,
+      "kl": 0.1307119549252093,
+      "learning_rate": 5.0625e-06,
+      "loss": 0.0031396135687828063,
+      "num_tokens": 550079.0,
+      "reward": 0.975,
+      "reward_std": 0.07071067690849304,
+      "rewards/JointRewardFunction/mean": 0.975,
+      "rewards/JointRewardFunction/std": 0.07071067690849304,
+      "step": 80,
+      "step_time": 33.55307105900029
+    },
+    {
+      "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": 788.4,
+      "completions/max_terminated_length": 788.4,
+      "completions/mean_length": 619.825,
+      "completions/mean_terminated_length": 619.825,
+      "completions/min_length": 510.4,
+      "completions/min_terminated_length": 510.4,
+      "entropy": 0.4017201948910952,
+      "epoch": 0.72,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0172119140625,
+      "kl": 0.08959094756282866,
+      "learning_rate": 4.4375e-06,
+      "loss": 0.001467562187463045,
+      "num_tokens": 620285.0,
+      "reward": 0.9625,
+      "reward_std": 0.10606601536273956,
+      "rewards/JointRewardFunction/mean": 0.9625,
+      "rewards/JointRewardFunction/std": 0.10606601536273956,
+      "step": 90,
+      "step_time": 33.41816141909967
+    },
+    {
+      "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": 911.0,
+      "completions/max_terminated_length": 831.5,
+      "completions/mean_length": 671.025,
+      "completions/mean_terminated_length": 653.7214416503906,
+      "completions/min_length": 537.5,
+      "completions/min_terminated_length": 537.5,
+      "entropy": 0.4100338226184249,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.021240234375,
+      "kl": 0.07856191159226,
+      "learning_rate": 3.8125e-06,
+      "loss": 0.017280958592891693,
+      "num_tokens": 694633.0,
+      "reward": 0.9375,
+      "reward_std": 0.1767766922712326,
+      "rewards/JointRewardFunction/mean": 0.9375,
+      "rewards/JointRewardFunction/std": 0.1767766922712326,
+      "step": 100,
+      "step_time": 38.310592102500415
+    },
+    {
+      "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": 867.4,
+      "completions/max_terminated_length": 779.6,
+      "completions/mean_length": 642.0875,
+      "completions/mean_terminated_length": 616.8726257324219,
+      "completions/min_length": 501.5,
+      "completions/min_terminated_length": 501.5,
+      "entropy": 0.40164962466806176,
+      "epoch": 0.88,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 1.1328125,
+      "kl": 0.0828359558712691,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.009746464341878891,
+      "num_tokens": 766544.0,
+      "reward": 0.9625,
+      "reward_std": 0.0816463440656662,
+      "rewards/JointRewardFunction/mean": 0.9625,
+      "rewards/JointRewardFunction/std": 0.0816463440656662,
+      "step": 110,
+      "step_time": 36.619024862399236
+    },
+    {
+      "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": 807.3,
+      "completions/max_terminated_length": 713.2,
+      "completions/mean_length": 611.7875,
+      "completions/mean_terminated_length": 595.7928649902344,
+      "completions/min_length": 508.7,
+      "completions/min_terminated_length": 508.7,
+      "entropy": 0.40618473663926125,
+      "epoch": 0.96,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 1.03125,
+      "kl": 0.08407443668693304,
+      "learning_rate": 2.5625e-06,
+      "loss": 0.01084473505616188,
+      "num_tokens": 835859.0,
+      "reward": 0.9625,
+      "reward_std": 0.10606601536273956,
+      "rewards/JointRewardFunction/mean": 0.9625,
+      "rewards/JointRewardFunction/std": 0.10606601536273956,
+      "step": 120,
+      "step_time": 34.16594214020042
+    },
+    {
+      "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": 751.9,
+      "completions/max_terminated_length": 748.3,
+      "completions/mean_length": 631.1,
+      "completions/mean_terminated_length": 626.9517883300781,
+      "completions/min_length": 544.1,
+      "completions/min_terminated_length": 544.1,
+      "entropy": 0.42196682561188936,
+      "epoch": 1.04,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.041748046875,
+      "kl": 0.08644672441296279,
+      "learning_rate": 1.9375e-06,
+      "loss": 0.00017178469570353628,
+      "num_tokens": 906965.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/JointRewardFunction/mean": 1.0,
+      "rewards/JointRewardFunction/std": 0.0,
+      "step": 130,
+      "step_time": 31.96281487729957
+    },
+    {
+      "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": 837.6,
+      "completions/max_terminated_length": 826.9,
+      "completions/mean_length": 642.5625,
+      "completions/mean_terminated_length": 637.825,
+      "completions/min_length": 522.1,
+      "completions/min_terminated_length": 522.1,
+      "entropy": 0.39782516546547414,
+      "epoch": 1.12,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.9375,
+      "kl": 0.08095719190314413,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": 0.0059084448963403705,
+      "num_tokens": 979018.0,
+      "reward": 0.9375,
+      "reward_std": 0.1767766922712326,
+      "rewards/JointRewardFunction/mean": 0.9375,
+      "rewards/JointRewardFunction/std": 0.1767766922712326,
+      "step": 140,
+      "step_time": 35.47339765110009
+    },
+    {
+      "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": 780.2,
+      "completions/max_terminated_length": 709.4,
+      "completions/mean_length": 608.125,
+      "completions/mean_terminated_length": 597.3017883300781,
+      "completions/min_length": 514.2,
+      "completions/min_terminated_length": 514.2,
+      "entropy": 0.3825716434046626,
+      "epoch": 1.2,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0263671875,
+      "kl": 0.0812916701193899,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.014202636480331422,
+      "num_tokens": 1048244.0,
+      "reward": 0.95,
+      "reward_std": 0.11700168251991272,
+      "rewards/JointRewardFunction/mean": 0.95,
+      "rewards/JointRewardFunction/std": 0.11700168251991272,
+      "step": 150,
+      "step_time": 33.213279404800595
+    },
+    {
+      "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": 785.1,
+      "completions/max_terminated_length": 743.9,
+      "completions/mean_length": 621.9,
+      "completions/mean_terminated_length": 612.2803649902344,
+      "completions/min_length": 508.9,
+      "completions/min_terminated_length": 508.9,
+      "entropy": 0.4208029452711344,
+      "epoch": 1.28,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.92578125,
+      "kl": 0.08554110652767122,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 0.011326169967651368,
+      "num_tokens": 1118898.0,
+      "reward": 0.975,
+      "reward_std": 0.07071067690849304,
+      "rewards/JointRewardFunction/mean": 0.975,
+      "rewards/JointRewardFunction/std": 0.07071067690849304,
+      "step": 160,
+      "step_time": 33.45168144740146
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 1118898,
+  "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:d40f250c23d01fe898035903f1d852e03e4dfb5197a6039e86d76bf7e9a8eaa8
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ec7b8100fdbb732326b9938aaf5de706ac0cd9a0aa6fbb12e56ff42f02fc49
+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:d40f250c23d01fe898035903f1d852e03e4dfb5197a6039e86d76bf7e9a8eaa8
+size 7249