Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-Math-7B
-datasets: DigitalLearningGmbH/MATH-lighteval
+base_model: Qwen/Qwen2.5-Math-7B-Instruct
 library_name: transformers
 model_name: Qwen-2.5-7B-Simple-RL
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen-2.5-7B-Simple-RL
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) on the [DigitalLearningGmbH/MATH-lighteval](https://huggingface.co/datasets/DigitalLearningGmbH/MATH-lighteval) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +27,7 @@ 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/huggingface/huggingface/runs/pq5sovxv) 
+[<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/huggingface/huggingface/runs/e8ipvp9s) 
 
 
 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).
@@ -37,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 
 - TRL: 0.17.0.dev0
-- Transformers: 4.49.0
+- Transformers: 4.51.0
 - Pytorch: 2.6.0
 - Datasets: 3.4.1
 - Tokenizers: 0.21.1

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": -4.392043727967474,
-    "train_runtime": 13254.7719,
+    "train_loss": 0.12281362387614372,
+    "train_runtime": 10554.7907,
     "train_samples": 7500,
-    "train_samples_per_second": 0.566,
-    "train_steps_per_second": 0.035
+    "train_samples_per_second": 0.711,
+    "train_steps_per_second": 0.011
 }

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
@@ -18,13 +17,12 @@
   "num_key_value_heads": 4,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
+  "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
-  "use_cache": true,
-  "use_mrope": false,
+  "transformers_version": "4.51.0",
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

generation_config.json

@@ -1,6 +1,9 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.49.0"
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.51.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1eb6e5679e4d58dd28e87c12fa85b41e6f8649886af1b00e5e560fe9d132ea
+oid sha256:229710b12313b19d22035cd22c92aa7ad6a4ed36452951819b53266fa32c70a4
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cd0d8bf08fa8ef084bd405054d1ec4dfa7a3e1b856c6f80bcbdb25a01118a8
+oid sha256:9522a64b8db4d386c053355132b2cd00602614f0e8979e394d34f7ce40c331b7
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f846aafa78bf493ca9d4cb53df3c719240a90c7046ca60255a7bf169ba1165
+oid sha256:3e55a974b789e82ee4755da9b66d4eee5e1e0ec997ebd41e7886505b948d14c2
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621840d94a3e10c3fd2b1d1227690bb2b13530236ad68b97eabacb16ccb7cd2c
+oid sha256:bc9e59c746ada8810f79f0985b9941a57f71cc14dc500b93fdbde4c64a8d935d
 size 1089994880

special_tokens_map.json

@@ -15,7 +15,7 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -197,7 +197,7 @@
   "bos_token": null,
   "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": -4.392043727967474,
-    "train_runtime": 13254.7719,
+    "train_loss": 0.12281362387614372,
+    "train_runtime": 10554.7907,
     "train_samples": 7500,
-    "train_samples_per_second": 0.566,
-    "train_steps_per_second": 0.035
+    "train_samples_per_second": 0.711,
+    "train_steps_per_second": 0.011
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5677e339fd6306f1bd6b6bc1ee482248770155ab82c82caf21fa6542781d24
+oid sha256:6d6ac3cfc11a0c97d69bb715ed0de66399a36fc026b721684ac5f8c83cc60b9b
 size 8568