learning_rate: 6.860482946498176e-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	0.6625	0.6173
No log	2.0	40	0.6870	0.6462
No log	3.0	60	0.7449	0.6679
No log	4.0	80	1.1313	0.6101
No log	5.0	100	1.2756	0.6498
No log	6.0	120	1.2574	0.7076
No log	7.0	140	1.4191	0.6931
No log	8.0	160	1.6799	0.6823
No log	9.0	180	1.8608	0.6679
No log	10.0	200	1.8329	0.6931
No log	11.0	220	1.9104	0.6859
No log	12.0	240	2.0106	0.6679
No log	13.0	260	1.9847	0.6787
No log	14.0	280	2.1079	0.6715
No log	15.0	300	2.0576	0.6679

alpiskitt/bert-base-uncased-finetuned-rte-run_1

bert-base-uncased-finetuned-rte-run_1