learning_rate: 9.282390627980626e-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	0.6745	0.6101
No log	2.0	40	0.6317	0.6426
No log	3.0	60	0.6616	0.6426
No log	4.0	80	0.9532	0.6354
No log	5.0	100	1.1841	0.6318
No log	6.0	120	1.4911	0.6462
No log	7.0	140	1.7021	0.6245
No log	8.0	160	1.7384	0.6462
No log	9.0	180	1.8543	0.6606
No log	10.0	200	1.9697	0.6534
No log	11.0	220	2.0101	0.6679
No log	12.0	240	2.1047	0.6534
No log	13.0	260	2.3315	0.6318
No log	14.0	280	2.1342	0.6426
No log	15.0	300	2.2079	0.6462

borantorun/bert-base-uncased-finetuned-rte-run_16

bert-base-uncased-finetuned-rte-run_16