update model card README.md

README.md

@@ -31,13 +31,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7.310841466783574e-06
-- train_batch_size: 13
+- learning_rate: 5.266531009081949e-06
+- train_batch_size: 14
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 693
+- lr_scheduler_warmup_steps: 507
 - num_epochs: 30
 - mixed_precision_training: Native AMP