learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 12
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5714	0.6202	100	0.4776	0.7879	0.7800	0.7900	0.7879
0.3897	1.2357	200	0.3239	0.8716	0.8704	0.8711	0.8716
0.2951	1.8558	300	0.3120	0.8765	0.8724	0.8858	0.8765
0.23	2.4713	400	0.1994	0.9281	0.9271	0.9304	0.9281
0.2135	3.0868	500	0.2157	0.9281	0.9267	0.9333	0.9281
0.2106	3.7070	600	0.1809	0.9380	0.9382	0.9387	0.9380
0.1576	4.3225	700	0.1629	0.9403	0.9404	0.9404	0.9403
0.1434	4.9426	800	0.1526	0.9543	0.9542	0.9543	0.9543
0.1391	5.5581	900	0.1268	0.9575	0.9575	0.9575	0.9575
0.1048	6.1736	1000	0.1489	0.9557	0.9555	0.9558	0.9557
0.1271	6.7938	1100	0.1448	0.9570	0.9566	0.9586	0.9570
0.091	7.4093	1200	0.1451	0.9570	0.9567	0.9580	0.9570
0.1159	8.0248	1300	0.1205	0.9629	0.9627	0.9636	0.9629
0.1151	8.6450	1400	0.1124	0.9665	0.9664	0.9666	0.9665
0.0735	9.2605	1500	0.1175	0.9643	0.9641	0.9645	0.9643
0.0537	9.8806	1600	0.1154	0.9679	0.9678	0.9679	0.9679
0.0666	10.4961	1700	0.1162	0.9701	0.9701	0.9701	0.9701
0.0732	11.1116	1800	0.1133	0.9679	0.9678	0.9679	0.9679
0.0775	11.7318	1900	0.1130	0.9683	0.9683	0.9684	0.9683