Model save

README.md

@@ -38,10 +38,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 8
+- num_devices: 7
+- gradient_accumulation_steps: 9
+- total_train_batch_size: 63
+- total_eval_batch_size: 7
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03