learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0249	1.0	60	0.0205	0.9958
0.0011	2.0	120	0.0009	1.0
0.0006	3.0	180	0.0005	1.0
0.0004	4.0	240	0.0003	1.0
0.0003	5.0	300	0.0002	1.0
0.0002	6.0	360	0.0002	1.0
0.0002	7.0	420	0.0001	1.0
0.0002	8.0	480	0.0001	1.0
0.0001	9.0	540	0.0001	1.0
0.0001	10.0	600	0.0001	1.0
0.0001	11.0	660	0.0001	1.0
0.0001	12.0	720	0.0001	1.0
0.0001	13.0	780	0.0001	1.0
0.0001	14.0	840	0.0001	1.0
0.0001	15.0	900	0.0001	1.0
0.0001	16.0	960	0.0001	1.0
0.0001	17.0	1020	0.0001	1.0
0.0001	18.0	1080	0.0001	1.0
0.0001	19.0	1140	0.0001	1.0
0.0001	20.0	1200	0.0001	1.0

singhshiva/my-bert-classifier2

my-bert-classifier2