update model card README.md

README.md

@@ -31,16 +31,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 25
+- learning_rate: 0.1
+- train_batch_size: 15
 - eval_batch_size: 8
 - seed: 8
-- gradient_accumulation_steps: 25
-- total_train_batch_size: 625
+- gradient_accumulation_steps: 15
+- total_train_batch_size: 225
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 900
-- num_epochs: 20
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 30
 
 ### Training results