End of training

README.md

@@ -37,12 +37,12 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 32
-- total_train_batch_size: 512
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
 - 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
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 100
 - mixed_precision_training: Native AMP
 
 ### Training results