End of training

README.md

@@ -1,8 +1,10 @@
 ---
+datasets: samitizerxu/math-hard
 library_name: transformers
 model_name: Qwen2.5-R1-Distill-GRPO-h
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -10,7 +12,7 @@ licence: license
 
 # Model Card for Qwen2.5-R1-Distill-GRPO-h
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [samitizerxu/math-hard](https://huggingface.co/datasets/samitizerxu/math-hard) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }