learning_rate: 0.0001
train_batch_size: 256
eval_batch_size: 256
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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
1.7349	1.0	161	0.7668	0.8664	0.8687	0.8664	0.8658	0.9880
0.6429	2.0	322	0.2021	0.9498	0.9506	0.9498	0.9498	0.9979
0.4363	3.0	483	0.1325	0.9601	0.9606	0.9601	0.9600	0.9991
0.3774	4.0	644	0.1117	0.966	0.9667	0.966	0.9660	0.9992
0.3413	5.0	805	0.0979	0.9694	0.9697	0.9694	0.9693	0.9994
0.3051	6.0	966	0.0824	0.9748	0.9749	0.9748	0.9748	0.9995
0.2808	7.0	1127	0.0796	0.9742	0.9744	0.9742	0.9742	0.9995
0.2622	8.0	1288	0.0753	0.9764	0.9765	0.9764	0.9765	0.9995
0.2512	9.0	1449	0.0769	0.9748	0.9748	0.9748	0.9747	0.9996
0.2368	10.0	1610	0.0816	0.9777	0.9780	0.9777	0.9777	0.9995
0.2303	11.0	1771	0.0686	0.98	0.9800	0.98	0.9800	0.9996
0.2141	12.0	1932	0.0684	0.9791	0.9792	0.9791	0.9791	0.9996
0.2086	13.0	2093	0.0766	0.9782	0.9787	0.9782	0.9783	0.9996
0.2012	14.0	2254	0.0830	0.9783	0.9787	0.9783	0.9783	0.9995

BeckerAnas/cool-darkness-225

cool-darkness-225