Update README.md

README.md

@@ -27,7 +27,7 @@ pipeline_tag: visual-document-retrieval
 
 ## Ranked #1 on the Vidore benchmark (as of February 11, 2025). The reported scores are on the [Vidore Leaderboard](https://huggingface.co/spaces/vidore/vidore-leaderboard).
 
-### This is the base version trained on 4xA100 80GB with per_device_batch_size=128 and gradient_accumulation_steps=2 for 5 epoch. 
+### This is the base version trained on 4xA100 80GB with per_device_batch_size=64 and gradient_accumulation_steps=2 for 5 epoch. 
 
 ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
 It is a [Qwen2.5-VL-3B](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.