Update README.md

README.md

@@ -89,7 +89,7 @@ print(processor.tokenizer.batch_decode(out))
 * **Language(s)**: Japanese
 
 ### Training
-This model was initially trained with the Adaptor using STAIR Captions. In the second phase, it was fine-tuned with [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA) and Japanese Visual Genome using LoRA.
+This model was fully fine-tuned with [LLaVA-Instruct-150K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA).
 
 ### Training Dataset