update model card README.md

README.md

@@ -32,15 +32,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 5
+- train_batch_size: 10
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 10
+- total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results