learning_rate: 7.464983850525022e-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	0.6503	0.5993
No log	2.0	40	0.6473	0.6679
No log	3.0	60	0.7858	0.6643
No log	4.0	80	0.8281	0.6895
No log	5.0	100	1.3617	0.6354
No log	6.0	120	1.1805	0.6859
No log	7.0	140	1.3449	0.7112
No log	8.0	160	1.4317	0.6859
No log	9.0	180	1.7205	0.6931
No log	10.0	200	1.5252	0.7148
No log	11.0	220	1.5785	0.7040
No log	12.0	240	1.6318	0.7040
No log	13.0	260	1.8415	0.6931
No log	14.0	280	1.8565	0.6931
No log	15.0	300	1.8965	0.6931

borantorun/bert-base-uncased-finetuned-rte-run_15

bert-base-uncased-finetuned-rte-run_15