Update README.md

README.md

@@ -4,4 +4,4 @@ Part of the [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-t
 
 The GPT2 model source code is modified so it can accept an encoder's output.
 The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
-The model is trained on 65000 images from the COCO dataset for about 1500 steps, with the original english cpationis are translated to french for training purpose.
+The model is trained on 65000 images from the COCO dataset for about 1500 steps (batch\_size=256), with the original english cpationis being translated to french for training purpose.