End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets: chansung/verifiable-coding-problems-python-v2
 library_name: transformers
 model_name: Qwen3-4B-CCRL-CUR-UNI-1E
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Qwen3-4B-CCRL-CUR-UNI-1E
 
-This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the [chansung/verifiable-coding-problems-python-v2](https://huggingface.co/datasets/chansung/verifiable-coding-problems-python-v2) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }