learning_rate: 0.00011357199085352113
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	0.6514	0.6245
No log	2.0	40	0.6411	0.6895
No log	3.0	60	0.8792	0.6498
No log	4.0	80	0.9813	0.6715
No log	5.0	100	1.3011	0.6679
No log	6.0	120	1.2946	0.6751
No log	7.0	140	1.5953	0.6823
No log	8.0	160	1.4640	0.7040
No log	9.0	180	1.4020	0.7076
No log	10.0	200	1.5325	0.6968
No log	11.0	220	1.5469	0.6895
No log	12.0	240	1.6298	0.6968
No log	13.0	260	1.7015	0.6931
No log	14.0	280	1.6853	0.7040
No log	15.0	300	1.6948	0.7004

fguzelant/bert-base-uncased-finetuned-rte-run_6_best

bert-base-uncased-finetuned-rte-run_6_best