update model card README.md

README.md

@@ -33,13 +33,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 32
-- eval_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 2048
-- total_eval_batch_size: 256
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1