End of training

README.md

@@ -35,14 +35,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 100
+- train_batch_size: 4
+- eval_batch_size: 64
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 10
+- training_steps: 1
 - mixed_precision_training: Native AMP
 
 ### Training results