初始化项目，由ModelHub XC社区提供模型

Model: harsha070/exp2-qwen-island-s42-lambda-0p45 Source: Original Platform
2026-06-16 07:12:17 +08:00
commit 39fcc471d5
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: exp2-qwen-island-s42-lambda-0p45
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for exp2-qwen-island-s42-lambda-0p45
+
+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/exp2-qwen-island-s42-lambda-0p45", 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/yeg20xyd) 
+
+
+
+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:a2e91e8631ca5c6726a1b03a5a3caf92454481d1e9aad5de83352011c3bfdd24
+size 22400
--- a/completions/completions_00020.parquet
+++ b/completions/completions_00020.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd47305e123ca1f88bf25dec0b906d6d802901fde7a42132a5397eaa052b58a
+size 18796
--- a/completions/completions_00030.parquet
+++ b/completions/completions_00030.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458f95dad8ff52051ff95899017ee15be64e4e40c8c19f439301ec5037bf4b0a
+size 32319
--- a/completions/completions_00040.parquet
+++ b/completions/completions_00040.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a3855279bd5bdbbf5949abf10aedd90f398345ad897baf9f6e84c2c9253293
+size 20334
--- a/completions/completions_00050.parquet
+++ b/completions/completions_00050.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629a79aca73afecb306892366740b28e0d8f88e986deceb305a30dbb4240a640
+size 25568
--- a/completions/completions_00060.parquet
+++ b/completions/completions_00060.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a7ca75c53f8b5b7f8b76f4d49a2f15e7aca82124ff892484be8630717fcd65
+size 24450
--- a/completions/completions_00070.parquet
+++ b/completions/completions_00070.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d297394ac565f7fd311b728788ec9c1b27433def675454031c06a97844104e7
+size 21272
--- a/completions/completions_00080.parquet
+++ b/completions/completions_00080.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996557868ea18ec7633b1d48226080762a2340d66212a6b67fe79f0580eb4d2e
+size 21345
--- a/completions/completions_00090.parquet
+++ b/completions/completions_00090.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44da506ee9c5ae1cb436b31f17b9281ba690ff1334fbeb5588a40008128f94cc
+size 23882
--- a/completions/completions_00100.parquet
+++ b/completions/completions_00100.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b06e867df640bc48f60572b0b66aa0dc42622b89f2e3eb46997dba5eebb275b
+size 24262
--- a/completions/completions_00110.parquet
+++ b/completions/completions_00110.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5b5034bcb507ce150e604a0d653a75b39faae287f8555141fb8f7563bf5f24
+size 23218
--- a/completions/completions_00120.parquet
+++ b/completions/completions_00120.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9ac528a68c832e11c5fafd279e3246c5c4939debfdd85695590ba89402aae6
+size 20241
--- a/completions/completions_00130.parquet
+++ b/completions/completions_00130.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051d80e6d8e9e7c749411b0bbf2b785c4a90c56cf854e25fed912b128985505b
+size 21915
--- a/completions/completions_00140.parquet
+++ b/completions/completions_00140.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424047c438601bbea0a529d167b9a37a8cdcec08b9f8476d02264bb9fbd21677
+size 18931
--- a/completions/completions_00150.parquet
+++ b/completions/completions_00150.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c84255798b66a111fb779448cd37c12ccc28ba5f09025a5fe441068d3880929
+size 22378
--- a/completions/completions_00160.parquet
+++ b/completions/completions_00160.parquet
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9784d76b2ce42a96583a0d6c4712f944bb9dd5be2a5904f1040bba13b637838a
+size 23287
--- 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 sha256:49aef298d5ac0da244b9510e3897fc2feed1ca55b3ae1c237ce1faf27f872639
+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": 892.4,
+      "completions/max_terminated_length": 819.9,
+      "completions/mean_length": 573.1125,
+      "completions/mean_terminated_length": 551.0821472167969,
+      "completions/min_length": 313.1,
+      "completions/min_terminated_length": 313.1,
+      "entropy": 0.7912669345736504,
+      "epoch": 0.08,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 2.359375,
+      "kl": 0.04604918217446539,
+      "learning_rate": 9.4375e-06,
+      "loss": 0.021108362078666686,
+      "num_tokens": 66493.0,
+      "reward": 0.6003784224390983,
+      "reward_std": 0.5601114392280578,
+      "rewards/JointRewardFunction/mean": 0.6003784224390983,
+      "rewards/JointRewardFunction/std": 0.5601114451885223,
+      "step": 10,
+      "step_time": 37.44416529300106
+    },
+    {
+      "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": 800.3,
+      "completions/max_terminated_length": 673.7,
+      "completions/mean_length": 473.2875,
+      "completions/mean_terminated_length": 445.1142974853516,
+      "completions/min_length": 249.0,
+      "completions/min_terminated_length": 249.0,
+      "entropy": 1.0140388168394565,
+      "epoch": 0.16,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 3.75,
+      "kl": 0.25841885171830653,
+      "learning_rate": 8.8125e-06,
+      "loss": 0.03933271169662476,
+      "num_tokens": 125000.0,
+      "reward": 0.9494775831699371,
+      "reward_std": 0.4877780556678772,
+      "rewards/JointRewardFunction/mean": 0.9494775831699371,
+      "rewards/JointRewardFunction/std": 0.4877780944108963,
+      "step": 20,
+      "step_time": 35.173660528497564
+    },
+    {
+      "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": 951.5,
+      "completions/max_terminated_length": 813.4,
+      "completions/mean_length": 634.375,
+      "completions/mean_terminated_length": 576.2744140625,
+      "completions/min_length": 331.8,
+      "completions/min_terminated_length": 331.8,
+      "entropy": 1.309154535830021,
+      "epoch": 0.24,
+      "frac_reward_zero_std": 0.375,
+      "grad_norm": 1.859375,
+      "kl": 0.2194912993349135,
+      "learning_rate": 8.1875e-06,
+      "loss": 0.026669433712959288,
+      "num_tokens": 196194.0,
+      "reward": 1.0899658679962159,
+      "reward_std": 0.5111429423093796,
+      "rewards/JointRewardFunction/mean": 1.0899658679962159,
+      "rewards/JointRewardFunction/std": 0.5111429691314697,
+      "step": 30,
+      "step_time": 41.286807323301765
+    },
+    {
+      "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": 848.0,
+      "completions/max_terminated_length": 783.4,
+      "completions/mean_length": 569.7125,
+      "completions/mean_terminated_length": 549.1333435058593,
+      "completions/min_length": 369.3,
+      "completions/min_terminated_length": 369.3,
+      "entropy": 1.1440452575683593,
+      "epoch": 0.32,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 2.671875,
+      "kl": 0.13953614169731737,
+      "learning_rate": 7.5625e-06,
+      "loss": 0.013277828693389893,
+      "num_tokens": 262345.0,
+      "reward": 0.8887524664402008,
+      "reward_std": 0.5226060330867768,
+      "rewards/JointRewardFunction/mean": 0.8887524664402008,
+      "rewards/JointRewardFunction/std": 0.5226060688495636,
+      "step": 40,
+      "step_time": 37.13389427080001
+    },
+    {
+      "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": 875.8,
+      "completions/max_terminated_length": 875.8,
+      "completions/mean_length": 560.675,
+      "completions/mean_terminated_length": 560.675,
+      "completions/min_length": 320.4,
+      "completions/min_terminated_length": 320.4,
+      "entropy": 1.1498947571963072,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 2.875,
+      "kl": 0.09845088529400528,
+      "learning_rate": 6.9375e-06,
+      "loss": 0.03778347373008728,
+      "num_tokens": 328029.0,
+      "reward": 0.8338769674301147,
+      "reward_std": 0.5376368969678879,
+      "rewards/JointRewardFunction/mean": 0.8338769674301147,
+      "rewards/JointRewardFunction/std": 0.5376369208097458,
+      "step": 50,
+      "step_time": 38.24463103190137
+    },
+    {
+      "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": 829.7,
+      "completions/max_terminated_length": 829.7,
+      "completions/mean_length": 531.85,
+      "completions/mean_terminated_length": 531.85,
+      "completions/min_length": 287.5,
+      "completions/min_terminated_length": 287.5,
+      "entropy": 1.1666041024029254,
+      "epoch": 0.48,
+      "frac_reward_zero_std": 0.075,
+      "grad_norm": 2.015625,
+      "kl": 0.0893499652389437,
+      "learning_rate": 6.3125e-06,
+      "loss": 0.008259650319814682,
+      "num_tokens": 390917.0,
+      "reward": 0.6566748261451721,
+      "reward_std": 0.5261385977268219,
+      "rewards/JointRewardFunction/mean": 0.6566748261451721,
+      "rewards/JointRewardFunction/std": 0.5261386096477508,
+      "step": 60,
+      "step_time": 36.22042608499832
+    },
+    {
+      "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": 760.1,
+      "completions/max_terminated_length": 760.1,
+      "completions/mean_length": 505.25,
+      "completions/mean_terminated_length": 505.25,
+      "completions/min_length": 287.4,
+      "completions/min_terminated_length": 287.4,
+      "entropy": 1.1663248613476753,
+      "epoch": 0.56,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 1.9296875,
+      "kl": 0.09666758836247027,
+      "learning_rate": 5.6875e-06,
+      "loss": 0.04623619616031647,
+      "num_tokens": 451793.0,
+      "reward": 0.8685888767242431,
+      "reward_std": 0.5478669673204422,
+      "rewards/JointRewardFunction/mean": 0.8685888767242431,
+      "rewards/JointRewardFunction/std": 0.5478669852018356,
+      "step": 70,
+      "step_time": 33.734915479502526
+    },
+    {
+      "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": 692.8,
+      "completions/max_terminated_length": 692.8,
+      "completions/mean_length": 482.775,
+      "completions/mean_terminated_length": 482.775,
+      "completions/min_length": 305.5,
+      "completions/min_terminated_length": 305.5,
+      "entropy": 1.1494709253311157,
+      "epoch": 0.64,
+      "frac_reward_zero_std": 0.125,
+      "grad_norm": 2.765625,
+      "kl": 0.11551248212344944,
+      "learning_rate": 5.0625e-06,
+      "loss": -0.016333292424678802,
+      "num_tokens": 511029.0,
+      "reward": 1.0234729290008544,
+      "reward_std": 0.49485546052455903,
+      "rewards/JointRewardFunction/mean": 1.0234729290008544,
+      "rewards/JointRewardFunction/std": 0.4948554873466492,
+      "step": 80,
+      "step_time": 31.04121985129932
+    },
+    {
+      "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": 633.5,
+      "completions/max_terminated_length": 633.5,
+      "completions/mean_length": 459.7625,
+      "completions/mean_terminated_length": 459.7625,
+      "completions/min_length": 280.1,
+      "completions/min_terminated_length": 280.1,
+      "entropy": 1.1554153360426427,
+      "epoch": 0.72,
+      "frac_reward_zero_std": 0.325,
+      "grad_norm": 1.78125,
+      "kl": 0.1084105208516121,
+      "learning_rate": 4.4375e-06,
+      "loss": -0.037684041261672976,
+      "num_tokens": 568430.0,
+      "reward": 1.0063842952251434,
+      "reward_std": 0.45139331221580503,
+      "rewards/JointRewardFunction/mean": 1.0063842952251434,
+      "rewards/JointRewardFunction/std": 0.45139334285631777,
+      "step": 90,
+      "step_time": 28.41928261620196
+    },
+    {
+      "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": 694.2,
+      "completions/max_terminated_length": 694.2,
+      "completions/mean_length": 483.575,
+      "completions/mean_terminated_length": 483.575,
+      "completions/min_length": 270.1,
+      "completions/min_terminated_length": 270.1,
+      "entropy": 1.1369776532053948,
+      "epoch": 0.8,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 2.25,
+      "kl": 0.12164497645571828,
+      "learning_rate": 3.8125e-06,
+      "loss": -0.011769261211156845,
+      "num_tokens": 627782.0,
+      "reward": 1.045616489648819,
+      "reward_std": 0.48985774293541906,
+      "rewards/JointRewardFunction/mean": 1.045616489648819,
+      "rewards/JointRewardFunction/std": 0.48985776007175447,
+      "step": 100,
+      "step_time": 30.974922098598473
+    },
+    {
+      "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": 711.8,
+      "completions/max_terminated_length": 711.8,
+      "completions/mean_length": 478.5875,
+      "completions/mean_terminated_length": 478.5875,
+      "completions/min_length": 269.1,
+      "completions/min_terminated_length": 269.1,
+      "entropy": 1.1295112110674381,
+      "epoch": 0.88,
+      "frac_reward_zero_std": 0.275,
+      "grad_norm": 1.9765625,
+      "kl": 0.11388859800063074,
+      "learning_rate": 3.1875e-06,
+      "loss": 0.00085725337266922,
+      "num_tokens": 686613.0,
+      "reward": 0.9904785633087159,
+      "reward_std": 0.5183025985956192,
+      "rewards/JointRewardFunction/mean": 0.9904785633087159,
+      "rewards/JointRewardFunction/std": 0.5183026134967804,
+      "step": 110,
+      "step_time": 31.47189465950178
+    },
+    {
+      "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": 681.1,
+      "completions/max_terminated_length": 681.1,
+      "completions/mean_length": 474.575,
+      "completions/mean_terminated_length": 474.575,
+      "completions/min_length": 306.6,
+      "completions/min_terminated_length": 306.6,
+      "entropy": 1.0753874629735947,
+      "epoch": 0.96,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 2.3125,
+      "kl": 0.11223098039627075,
+      "learning_rate": 2.5625e-06,
+      "loss": 0.02290368378162384,
+      "num_tokens": 744951.0,
+      "reward": 1.1014428853988647,
+      "reward_std": 0.43211724162101744,
+      "rewards/JointRewardFunction/mean": 1.1014428853988647,
+      "rewards/JointRewardFunction/std": 0.4321172535419464,
+      "step": 120,
+      "step_time": 30.187947676197656
+    },
+    {
+      "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": 700.8,
+      "completions/max_terminated_length": 700.8,
+      "completions/mean_length": 482.3,
+      "completions/mean_terminated_length": 482.3,
+      "completions/min_length": 292.0,
+      "completions/min_terminated_length": 292.0,
+      "entropy": 1.100510736554861,
+      "epoch": 1.04,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 1.890625,
+      "kl": 0.11114813778549433,
+      "learning_rate": 1.9375e-06,
+      "loss": -0.00960662066936493,
+      "num_tokens": 804153.0,
+      "reward": 1.0441894710063935,
+      "reward_std": 0.4884881317615509,
+      "rewards/JointRewardFunction/mean": 1.0441894710063935,
+      "rewards/JointRewardFunction/std": 0.48848815858364103,
+      "step": 130,
+      "step_time": 31.431871901799603
+    },
+    {
+      "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": 654.8,
+      "completions/max_terminated_length": 654.8,
+      "completions/mean_length": 455.1875,
+      "completions/mean_terminated_length": 455.1875,
+      "completions/min_length": 274.1,
+      "completions/min_terminated_length": 274.1,
+      "entropy": 1.1068335216492415,
+      "epoch": 1.12,
+      "frac_reward_zero_std": 0.35,
+      "grad_norm": 2.296875,
+      "kl": 0.11968475547619165,
+      "learning_rate": 1.3125000000000001e-06,
+      "loss": -0.020959584414958952,
+      "num_tokens": 861216.0,
+      "reward": 1.0450488328933716,
+      "reward_std": 0.4309545159339905,
+      "rewards/JointRewardFunction/mean": 1.0450488328933716,
+      "rewards/JointRewardFunction/std": 0.43095452189445493,
+      "step": 140,
+      "step_time": 29.483576541099684
+    },
+    {
+      "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": 677.2,
+      "completions/max_terminated_length": 677.2,
+      "completions/mean_length": 466.3125,
+      "completions/mean_terminated_length": 466.3125,
+      "completions/min_length": 296.8,
+      "completions/min_terminated_length": 296.8,
+      "entropy": 1.0722076326608658,
+      "epoch": 1.2,
+      "frac_reward_zero_std": 0.45,
+      "grad_norm": 0.85546875,
+      "kl": 0.1184447065461427,
+      "learning_rate": 6.875000000000001e-07,
+      "loss": 0.02653493583202362,
+      "num_tokens": 919097.0,
+      "reward": 1.2055200517177582,
+      "reward_std": 0.3585283608641475,
+      "rewards/JointRewardFunction/mean": 1.2055200517177582,
+      "rewards/JointRewardFunction/std": 0.35852835562545804,
+      "step": 150,
+      "step_time": 30.24508252329979
+    },
+    {
+      "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": 672.0,
+      "completions/max_terminated_length": 672.0,
+      "completions/mean_length": 470.9375,
+      "completions/mean_terminated_length": 470.9375,
+      "completions/min_length": 331.2,
+      "completions/min_terminated_length": 331.2,
+      "entropy": 1.0674828842282296,
+      "epoch": 1.28,
+      "frac_reward_zero_std": 0.425,
+      "grad_norm": 1.875,
+      "kl": 0.12561513194814325,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": -0.007510318607091904,
+      "num_tokens": 977674.0,
+      "reward": 1.1753845453262328,
+      "reward_std": 0.39318075180053713,
+      "rewards/JointRewardFunction/mean": 1.1753845453262328,
+      "rewards/JointRewardFunction/std": 0.3931807607412338,
+      "step": 160,
+      "step_time": 29.98714039499864
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 977674,
+  "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 sha256:3906488e422259322b7d06064404a5ecab931aab5f19b82f239e2f3da07e7f99
+size 7249
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49aef298d5ac0da244b9510e3897fc2feed1ca55b3ae1c237ce1faf27f872639
+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 sha256:3906488e422259322b7d06064404a5ecab931aab5f19b82f239e2f3da07e7f99
+size 7249