learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	458	0.1666	0.9803	0.9574	0.9553	0.9534
0.3261	2.0	916	0.1540	0.9891	0.9806	0.9722	0.9762
0.0261	3.0	1374	0.1243	0.9913	0.9821	0.9781	0.9795
0.0002	4.0	1832	0.1403	0.9913	0.9821	0.9781	0.9795
0.0000	5.0	2290	0.1418	0.9913	0.9821	0.9781	0.9795
0.0000	6.0	2748	0.1441	0.9913	0.9821	0.9781	0.9795
0.0000	7.0	3206	0.1459	0.9913	0.9821	0.9781	0.9795
0.0000	8.0	3664	0.1474	0.9913	0.9821	0.9781	0.9795
0.0000	9.0	4122	0.1483	0.9913	0.9821	0.9781	0.9795
0.0000	10.0	4580	0.1487	0.9913	0.9821	0.9781	0.9795