learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
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
0.927	0.0170	100	0.4956	0.7806
0.5634	0.0340	200	0.4637	0.8044
0.4876	0.0509	300	0.7024	0.8648
0.4179	0.0679	400	0.3941	0.8944
0.4397	0.0849	500	0.5622	0.8291
0.3985	0.1019	600	0.3185	0.8997
0.4607	0.1188	700	0.4404	0.8942
0.4023	0.1358	800	0.2967	0.9091
0.3185	0.1528	900	0.3033	0.8980
0.335	0.1698	1000	0.2653	0.9232
0.3665	0.1868	1100	0.2280	0.9246
0.3033	0.2037	1200	0.1975	0.9320
0.2578	0.2207	1300	0.2171	0.9341
0.3417	0.2377	1400	0.2497	0.9301
0.3222	0.2547	1500	0.2855	0.9328

EndOfLe/fine_tuned_yelp

fine_tuned_yelp