Model save

README.md

@@ -1,6 +1,5 @@
 ---
-base_model: JayHyeon/Qwen2.5-0.5B_ultrainteract_sft_2e-5_1ep
-datasets: JayHyeon/trl_ultrainteract-pair
+base_model: JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep
 library_name: transformers
 model_name: Qwen_0.5-ultrainteract_BDPO_5e-7-1ep_0.5bdpo_lambda
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for Qwen_0.5-ultrainteract_BDPO_5e-7-1ep_0.5bdpo_lambda
 
-This model is a fine-tuned version of [JayHyeon/Qwen2.5-0.5B_ultrainteract_sft_2e-5_1ep](https://huggingface.co/JayHyeon/Qwen2.5-0.5B_ultrainteract_sft_2e-5_1ep) on the [JayHyeon/trl_ultrainteract-pair](https://huggingface.co/datasets/JayHyeon/trl_ultrainteract-pair) dataset.
+This model is a fine-tuned version of [JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep](https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +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/bonin147/huggingface/runs/f5n9yktr) 
+[<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/bonin147/huggingface/runs/jd8xbeby) 
 
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).