Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-7B-Instruct
-datasets: DigitalLearningGmbH/MATH-lighteval
 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-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) 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/e8ipvp9s) 
+[<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/h6ll256w) 
 
 
 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).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.12281362387614372,
-    "train_runtime": 10554.7907,
+    "train_loss": 0.19539536322411308,
+    "train_runtime": 10586.276,
     "train_samples": 7500,
-    "train_samples_per_second": 0.711,
+    "train_samples_per_second": 0.708,
     "train_steps_per_second": 0.011
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229710b12313b19d22035cd22c92aa7ad6a4ed36452951819b53266fa32c70a4
+oid sha256:4a24be9beb2930e96f55a144307e5c503fcd17311e68900a3e3f31474996e24c
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9522a64b8db4d386c053355132b2cd00602614f0e8979e394d34f7ce40c331b7
+oid sha256:415d738c2420cc8bfabcbfc69073b2134b63a3f2478bab1482b7bf4df2ba3d4c
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e55a974b789e82ee4755da9b66d4eee5e1e0ec997ebd41e7886505b948d14c2
+oid sha256:e76d163c7fb609ff969414089ba6fc3dd69cb219373392bab68bed60c6e67ef8
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc9e59c746ada8810f79f0985b9941a57f71cc14dc500b93fdbde4c64a8d935d
+oid sha256:f9436e8ca5f15b5727a6df3d264fd8c7938f0a2294c3d61ae58a45b52c1f6750
 size 1089994880

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.12281362387614372,
-    "train_runtime": 10554.7907,
+    "train_loss": 0.19539536322411308,
+    "train_runtime": 10586.276,
     "train_samples": 7500,
-    "train_samples_per_second": 0.711,
+    "train_samples_per_second": 0.708,
     "train_steps_per_second": 0.011
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6ac3cfc11a0c97d69bb715ed0de66399a36fc026b721684ac5f8c83cc60b9b
+oid sha256:24aa22826ce5722987ffd0895d76ea41b7c867f3895817af221a89244b40b616
 size 8568