learning_rate: 2e-05
train_batch_size: 90
eval_batch_size: 90
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: 3

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8984	0.1589	200	0.7369	0.6892
0.6427	0.3177	400	0.5919	0.7621
0.5597	0.4766	600	0.5397	0.7810
0.5361	0.6354	800	0.5033	0.7983
0.5291	0.7943	1000	0.5028	0.7982
0.5042	0.9531	1200	0.4763	0.8158
0.4036	1.1120	1400	0.4849	0.8184
0.4082	1.2708	1600	0.4690	0.8253
0.4241	1.4297	1800	0.4604	0.8282
0.3989	1.5886	2000	0.4544	0.8300
0.3932	1.7474	2200	0.4628	0.8267
0.3881	1.9063	2400	0.4436	0.8373
0.3366	2.0651	2600	0.4664	0.8346
0.3091	2.2240	2800	0.4624	0.8377
0.3125	2.3828	3000	0.4536	0.8437

julzhao/text_entailment_anli

text_entailment_anli