Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-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/wen-chuang_chou-tu-dresden/huggingface/runs/dh0uq8l7) 
+[<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/wen-chuang_chou-tu-dresden/huggingface/runs/4qiosci8) 
 
 
 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

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.1366361528635025,
-    "eval_runtime": 49.5719,
-    "eval_samples": 99,
-    "eval_samples_per_second": 1.997,
-    "eval_steps_per_second": 0.182,
     "total_flos": 0.0,
-    "train_loss": 0.0071978370242955,
-    "train_runtime": 34249.203,
+    "train_loss": 0.1895141939236091,
+    "train_runtime": 34465.7092,
     "train_samples": 93733,
-    "train_samples_per_second": 2.737,
-    "train_steps_per_second": 0.086
+    "train_samples_per_second": 2.72,
+    "train_steps_per_second": 0.17
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7983e947a311ccb3baaa8f57fe28ad7ac2990f19ee68aa3aaa74182576a9e1
+oid sha256:18cd8a8841ef227302bdfe5855a14e699d5cd22164978a0a914d9ad045ccde2c
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0071978370242955,
-    "train_runtime": 34249.203,
+    "train_loss": 0.1895141939236091,
+    "train_runtime": 34465.7092,
     "train_samples": 93733,
-    "train_samples_per_second": 2.737,
-    "train_steps_per_second": 0.086
+    "train_samples_per_second": 2.72,
+    "train_steps_per_second": 0.17
 }