初始化项目，由ModelHub XC社区提供模型

Model: harsha070/expfinal-qwen-island-s42-lambda-0p75 Source: Original Platform
2026-06-16 07:40:17 +08:00
commit de5c08a12c
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-0p75
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for expfinal-qwen-island-s42-lambda-0p75
+
+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-0p75", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/models-self5933/obfuscation-early-warning/runs/9b5b5fg9) 
+
+
+
+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 sha256:1adff6d35ca30e9962cfdc1c1a90e165246b8aa4ae1f3cc0903795cf5d53bbb3
+size 15462
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2cf42000b2f499fc751d25154e7eb0e02911870139c33060bbd44f40b0331b
+size 13294
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903994d208b45c7bf1f7a6777ab29bb26cb72fed06baac7937cd5d204cab2df2
+size 22318
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc225f17db7d00fb6abcb05ee14e8d81930467f09b934bc162f6516b3c39ea0
+size 19068
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700c7127efef7e4ad8ef4886387afda5fcc7cbcfb915398d26f592985a491535
+size 15660
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b58202738ca184a499b6071fc4a0e000a722ecc7612829b6bfb84a27ea8a94
+size 20592
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81bab122c0f2aee8cd4493881883d269d5fbaca859df7a444662a11b671f2f15
+size 15758
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee487fe2973939aa229c70f517e7cddbd1b7cacf03aa5f7c1bddc0b189d95cb
+size 15033
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b272d026125dc2244cb38f4b0e770b71985c86d3deca9047cd3616897829448
+size 18720
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc320191cbea05160197d9e8c920cb0f9850a7402ad2ef668e0d6acd2e17a47
+size 13283
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714bcbdced8e4d38e99125c1fe6053d350a51448877fafa622702b5ef044da57
+size 15580
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e4f0c26d61f85db75700093b7cedd13aa3f55ac334581f184fc60acb107033
+size 20100
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7eb952f5a2de3db51855a86f396224a189ee940c510347fc1f43497570c0d2a
+size 17732
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7803a897216d4a7dd3209f81c0a6cdf59dedf88e34aa1f3d867f5a19b0ad4381
+size 11083
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a4ced60b5878ee47f7ad975317234ff93381b5cbf79e6d041f87266b9d2e24
+size 16206
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5946aa10869aea755491362fcef6a83fe28da550db1586e54355a991d7da338a
+size 15264
--- 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 sha256:01b6936f0e5ca14f4d6360795d02b25c43457a020c930e833bc09e83abd68971
+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": 0.15,
+      "completions/max_length": 920.8,
+      "completions/max_terminated_length": 815.0,
+      "completions/mean_length": 575.9125,
+      "completions/mean_terminated_length": 512.0958465576172,
+      "completions/min_length": 250.5,
+      "completions/min_terminated_length": 250.5,
+      "entropy": 1.1609928414225579,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 4.6875,
+      "kl": 0.13114853966326337,
+      "learning_rate": 9.4375e-06,
+      "loss": 0.012817811965942384,
+      "num_tokens": 66717.0,
+      "reward": 0.730865478515625,
+      "reward_std": 0.7215771168470383,
+      "rewards/JointRewardFunction/mean": 0.730865478515625,
+      "rewards/JointRewardFunction/std": 0.7215771168470383,
+      "step": 10,
+      "step_time": 38.070080343699374
+    },
+    {
+      "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": 391.7,
+      "completions/max_terminated_length": 391.7,
+      "completions/mean_length": 177.925,
+      "completions/mean_terminated_length": 177.925,
+      "completions/min_length": 49.9,
+      "completions/min_terminated_length": 49.9,
+      "entropy": 2.0190576702356338,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 17.375,
+      "kl": 1.693755827844143,
+      "learning_rate": 8.8125e-06,
+      "loss": 0.07697797417640687,
+      "num_tokens": 101595.0,
+      "reward": 0.496136474609375,
+      "reward_std": 0.7558781564235687,
+      "rewards/JointRewardFunction/mean": 0.496136474609375,
+      "rewards/JointRewardFunction/std": 0.7558781564235687,
+      "step": 20,
+      "step_time": 18.131606991801892
+    },
+    {
+      "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": 0.175,
+      "completions/max_length": 988.7,
+      "completions/max_terminated_length": 802.5,
+      "completions/mean_length": 531.1125,
+      "completions/mean_terminated_length": 433.47263793945314,
+      "completions/min_length": 180.2,
+      "completions/min_terminated_length": 180.2,
+      "entropy": 1.3736804876476527,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 4.4375,
+      "kl": 0.4292584811337292,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.12034453153610229,
+      "num_tokens": 164528.0,
+      "reward": 0.727508544921875,
+      "reward_std": 0.5448802873492241,
+      "rewards/JointRewardFunction/mean": 0.727508544921875,
+      "rewards/JointRewardFunction/std": 0.5448802877217531,
+      "step": 30,
+      "step_time": 42.41746253830024
+    },
+    {
+      "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": 926.7,
+      "completions/max_terminated_length": 754.3,
+      "completions/mean_length": 494.75,
+      "completions/mean_terminated_length": 441.88750610351565,
+      "completions/min_length": 215.1,
+      "completions/min_terminated_length": 215.1,
+      "entropy": 1.0656868401914834,
+      "epoch": 0.32,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 5.125,
+      "kl": 0.3164741122163832,
+      "learning_rate": 7.5625e-06,
+      "loss": 0.0320564866065979,
+      "num_tokens": 224682.0,
+      "reward": 0.874420166015625,
+      "reward_std": 0.6246562719345092,
+      "rewards/JointRewardFunction/mean": 0.874420166015625,
+      "rewards/JointRewardFunction/std": 0.6246562749147415,
+      "step": 40,
+      "step_time": 39.87609361880059
+    },
+    {
+      "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": 629.9,
+      "completions/max_terminated_length": 629.9,
+      "completions/mean_length": 327.525,
+      "completions/mean_terminated_length": 327.525,
+      "completions/min_length": 114.7,
+      "completions/min_terminated_length": 114.7,
+      "entropy": 1.2003333028405905,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 7.5,
+      "kl": 0.43942997977137566,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.022251369059085847,
+      "num_tokens": 271714.0,
+      "reward": 1.063922119140625,
+      "reward_std": 0.6383892238140106,
+      "rewards/JointRewardFunction/mean": 1.063922119140625,
+      "rewards/JointRewardFunction/std": 0.6383892357349396,
+      "step": 50,
+      "step_time": 27.557733834501413
+    },
+    {
+      "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": 641.7,
+      "completions/max_terminated_length": 590.3,
+      "completions/mean_length": 302.5,
+      "completions/mean_terminated_length": 293.0178588867187,
+      "completions/min_length": 102.5,
+      "completions/min_terminated_length": 102.5,
+      "entropy": 1.3896781962364912,
+      "epoch": 0.48,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 4.375,
+      "kl": 0.5564426928758621,
+      "learning_rate": 6.3125e-06,
+      "loss": -0.0015912272036075592,
+      "num_tokens": 316254.0,
+      "reward": 0.9928466796875,
+      "reward_std": 0.6274125874042511,
+      "rewards/JointRewardFunction/mean": 0.9928466796875,
+      "rewards/JointRewardFunction/std": 0.6274125933647156,
+      "step": 60,
+      "step_time": 28.0631938617993
+    },
+    {
+      "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": 586.9,
+      "completions/max_terminated_length": 586.9,
+      "completions/mean_length": 294.55,
+      "completions/mean_terminated_length": 294.55,
+      "completions/min_length": 114.6,
+      "completions/min_terminated_length": 114.6,
+      "entropy": 1.4918637625873088,
+      "epoch": 0.56,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 5.15625,
+      "kl": 0.5497013371437788,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.047078275680541994,
+      "num_tokens": 360274.0,
+      "reward": 1.1190673828125,
+      "reward_std": 0.609263214468956,
+      "rewards/JointRewardFunction/mean": 1.1190673828125,
+      "rewards/JointRewardFunction/std": 0.609263226389885,
+      "step": 70,
+      "step_time": 26.138083929998174
+    },
+    {
+      "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": 847.5,
+      "completions/max_terminated_length": 678.8,
+      "completions/mean_length": 365.3375,
+      "completions/mean_terminated_length": 321.4898880004883,
+      "completions/min_length": 90.4,
+      "completions/min_terminated_length": 90.4,
+      "entropy": 1.5532763354480266,
+      "epoch": 0.64,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 5.78125,
+      "kl": 0.4981705164536834,
+      "learning_rate": 5.0625e-06,
+      "loss": 0.11404727697372437,
+      "num_tokens": 410115.0,
+      "reward": 0.9597900390625,
+      "reward_std": 0.6095708787441254,
+      "rewards/JointRewardFunction/mean": 0.9597900390625,
+      "rewards/JointRewardFunction/std": 0.6095708817243576,
+      "step": 80,
+      "step_time": 36.49904953569931
+    },
+    {
+      "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": 732.5,
+      "completions/max_terminated_length": 677.8,
+      "completions/mean_length": 299.875,
+      "completions/mean_terminated_length": 282.1875030517578,
+      "completions/min_length": 96.0,
+      "completions/min_terminated_length": 96.0,
+      "entropy": 1.4728075489401817,
+      "epoch": 0.72,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 3.5625,
+      "kl": 0.4925263602286577,
+      "learning_rate": 4.4375e-06,
+      "loss": 0.054662787914276124,
+      "num_tokens": 454725.0,
+      "reward": 1.019183349609375,
+      "reward_std": 0.61219422519207,
+      "rewards/JointRewardFunction/mean": 1.019183349609375,
+      "rewards/JointRewardFunction/std": 0.6121942341327667,
+      "step": 90,
+      "step_time": 31.705154634100108
+    },
+    {
+      "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": 760.6,
+      "completions/max_terminated_length": 660.6,
+      "completions/mean_length": 352.475,
+      "completions/mean_terminated_length": 312.0821502685547,
+      "completions/min_length": 105.0,
+      "completions/min_terminated_length": 105.0,
+      "entropy": 1.3954405788332225,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.125,
+      "grad_norm": 5.78125,
+      "kl": 0.4322750365361571,
+      "learning_rate": 3.8125e-06,
+      "loss": 0.009273938834667206,
+      "num_tokens": 503589.0,
+      "reward": 0.9172119140625,
+      "reward_std": 0.6775627821683884,
+      "rewards/JointRewardFunction/mean": 0.9172119140625,
+      "rewards/JointRewardFunction/std": 0.6775627851486206,
+      "step": 100,
+      "step_time": 33.002576629400934
+    },
+    {
+      "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": 687.7,
+      "completions/max_terminated_length": 653.3,
+      "completions/mean_length": 315.025,
+      "completions/mean_terminated_length": 306.5357147216797,
+      "completions/min_length": 97.6,
+      "completions/min_terminated_length": 97.6,
+      "entropy": 1.4698836095631123,
+      "epoch": 0.88,
+      "frac_reward_zero_std": 0.275,
+      "grad_norm": 8.125,
+      "kl": 0.4709475075826049,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.09247303009033203,
+      "num_tokens": 549335.0,
+      "reward": 0.997833251953125,
+      "reward_std": 0.6001621454954147,
+      "rewards/JointRewardFunction/mean": 0.997833251953125,
+      "rewards/JointRewardFunction/std": 0.6001621544361114,
+      "step": 110,
+      "step_time": 30.22435642040182
+    },
+    {
+      "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": 865.7,
+      "completions/max_terminated_length": 724.8,
+      "completions/mean_length": 377.4125,
+      "completions/mean_terminated_length": 342.6226211547852,
+      "completions/min_length": 102.6,
+      "completions/min_terminated_length": 102.6,
+      "entropy": 1.4377100937068463,
+      "epoch": 0.96,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 3.15625,
+      "kl": 0.4150696059688926,
+      "learning_rate": 2.5625e-06,
+      "loss": -0.021556401252746583,
+      "num_tokens": 599900.0,
+      "reward": 1.0236083984375,
+      "reward_std": 0.6392961710691452,
+      "rewards/JointRewardFunction/mean": 1.0236083984375,
+      "rewards/JointRewardFunction/std": 0.6392962068319321,
+      "step": 120,
+      "step_time": 37.14680036250138
+    },
+    {
+      "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": 698.9,
+      "completions/max_terminated_length": 598.9,
+      "completions/mean_length": 299.0125,
+      "completions/mean_terminated_length": 260.36726531982424,
+      "completions/min_length": 72.3,
+      "completions/min_terminated_length": 72.3,
+      "entropy": 1.3930659301578998,
+      "epoch": 1.04,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 5.71875,
+      "kl": 0.48926177779212593,
+      "learning_rate": 1.9375e-06,
+      "loss": 0.016721364855766297,
+      "num_tokens": 644439.0,
+      "reward": 0.972833251953125,
+      "reward_std": 0.6092687845230103,
+      "rewards/JointRewardFunction/mean": 0.972833251953125,
+      "rewards/JointRewardFunction/std": 0.6092687904834747,
+      "step": 130,
+      "step_time": 30.47871646400163
+    },
+    {
+      "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": 623.9,
+      "completions/max_terminated_length": 623.9,
+      "completions/mean_length": 286.925,
+      "completions/mean_terminated_length": 286.925,
+      "completions/min_length": 71.1,
+      "completions/min_terminated_length": 71.1,
+      "entropy": 1.4094880308955908,
+      "epoch": 1.12,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 10.8125,
+      "kl": 0.4836927611380816,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": 0.08277995586395263,
+      "num_tokens": 688041.0,
+      "reward": 1.046673583984375,
+      "reward_std": 0.5450149297714233,
+      "rewards/JointRewardFunction/mean": 1.046673583984375,
+      "rewards/JointRewardFunction/std": 0.5450149476528168,
+      "step": 140,
+      "step_time": 27.556023125701177
+    },
+    {
+      "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": 781.7,
+      "completions/max_terminated_length": 652.2,
+      "completions/mean_length": 349.275,
+      "completions/mean_terminated_length": 317.290478515625,
+      "completions/min_length": 88.2,
+      "completions/min_terminated_length": 88.2,
+      "entropy": 1.334358724579215,
+      "epoch": 1.2,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 5.9375,
+      "kl": 0.44102346180006863,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.12827397584915162,
+      "num_tokens": 736559.0,
+      "reward": 0.999505615234375,
+      "reward_std": 0.6881234139204025,
+      "rewards/JointRewardFunction/mean": 0.999505615234375,
+      "rewards/JointRewardFunction/std": 0.6881234139204025,
+      "step": 150,
+      "step_time": 33.79141057000161
+    },
+    {
+      "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": 678.4,
+      "completions/max_terminated_length": 558.1,
+      "completions/mean_length": 299.375,
+      "completions/mean_terminated_length": 261.2517883300781,
+      "completions/min_length": 71.7,
+      "completions/min_terminated_length": 71.7,
+      "entropy": 1.3799165710806847,
+      "epoch": 1.28,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 7.21875,
+      "kl": 0.4770205244421959,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 0.08484221696853637,
+      "num_tokens": 781411.0,
+      "reward": 0.87017822265625,
+      "reward_std": 0.6314140051603317,
+      "rewards/JointRewardFunction/mean": 0.87017822265625,
+      "rewards/JointRewardFunction/std": 0.6314140141010285,
+      "step": 160,
+      "step_time": 30.14368499219854
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 781411,
+  "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 sha256:097ba1449d336ba5ce121ddd53380281d14f6040068d1d8375eaa4b8f24c83b8
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b6936f0e5ca14f4d6360795d02b25c43457a020c930e833bc09e83abd68971
+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 sha256:097ba1449d336ba5ce121ddd53380281d14f6040068d1d8375eaa4b8f24c83b8
+size 7249