learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
4.4133	1.0	118	1.6447
1.4683	2.0	236	0.9098
1.0820	3.0	354	0.8103
0.9835	4.0	472	0.7475
0.8894	5.0	590	0.7058
0.8284	6.0	708	0.6739
0.8025	7.0	826	0.6582
0.7705	8.0	944	0.6364
0.7530	9.0	1062	0.6233
0.7372	10.0	1180	0.6214
0.7270	11.0	1298	0.6152
0.7113	12.0	1416	0.6129
0.6898	13.0	1534	0.6107
0.6977	14.0	1652	0.6100
0.6864	15.0	1770	0.6099

whismyswift/t5-absa-2

t5-absa-2