learning_rate: 6.121682549710445e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	20	0.7101	0.5054
No log	2.0	40	0.6264	0.6679
No log	3.0	60	0.6796	0.6606
No log	4.0	80	0.8850	0.6968
No log	5.0	100	1.1607	0.6679
No log	6.0	120	1.3237	0.6606
No log	7.0	140	1.4720	0.6534
No log	8.0	160	1.5483	0.6679
No log	9.0	180	1.7616	0.6570
No log	10.0	200	1.7248	0.6534
No log	11.0	220	1.8424	0.6715
No log	12.0	240	1.8870	0.6823
No log	13.0	260	1.9615	0.6715
No log	14.0	280	1.9907	0.6823
No log	15.0	300	1.9896	0.6895

borantorun/bert-base-uncased-finetuned-rte-run_18

bert-base-uncased-finetuned-rte-run_18