End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+datasets: DigitalLearningGmbH/MATH-lighteval
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-new
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-new
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the [DigitalLearningGmbH/MATH-lighteval](https://huggingface.co/datasets/DigitalLearningGmbH/MATH-lighteval) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.01550294179469347,
+    "eval_runtime": 7053.2454,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 0.709,
+    "eval_steps_per_second": 0.006,
     "total_flos": 0.0,
     "train_loss": 0.019923711259817255,
     "train_runtime": 38027.4532,

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.01550294179469347,
+    "eval_runtime": 7053.2454,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 0.709,
+    "eval_steps_per_second": 0.006
+}