Update README.md

README.md

@@ -25,7 +25,7 @@ This model is a fine-tuned version of the Qwen3-VL-8B-Instruct model using the U
 
 ## Training
 
-The model was trained for 200 steps with a batch size of 8 (2 per device with 4 gradient accumulation steps). LoRA adapters were used for parameter efficient finetuning, targeting both vision and language layers, as well as attention and MLP modules.
+The model was trained for 4 epochs with a batch size of 8 (4 per device with 8 gradient accumulation steps). LoRA adapters were used for parameter efficient finetuning, targeting both vision and language layers, as well as attention and MLP modules.
 
 
 ## Dataset