End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner
+datasets: akhauriyash/OpenR1_Math_SpecR_GRPO
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-GRPO-SpeculativeReasoner
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for DeepSeek-R1-Distill-Qwen-1.5B-GRPO-SpeculativeReasoner
 
-This model is a fine-tuned version of [akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner](https://huggingface.co/akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner).
+This model is a fine-tuned version of [akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner](https://huggingface.co/akhauriyash/DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner) on the [akhauriyash/OpenR1_Math_SpecR_GRPO](https://huggingface.co/datasets/akhauriyash/OpenR1_Math_SpecR_GRPO) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151665