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: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.3625	1.0	424	0.3429	0.0	0.5	0.3816
0.316	2.0	848	0.3081	0.0856	0.5333	0.4205
0.272	3.0	1272	0.2985	0.1488	0.5538	0.4558
0.2695	4.0	1696	0.2985	0.2374	0.6014	0.4488
0.2439	5.0	2120	0.2813	0.2373	0.5876	0.4488
0.1876	6.0	2544	0.3057	0.3314	0.6359	0.4753
0.1632	7.0	2968	0.3038	0.3638	0.6432	0.4700
0.1424	8.0	3392	0.3192	0.3414	0.6367	0.4629
0.1022	9.0	3816	0.3529	0.3305	0.6343	0.4576
0.1193	10.0	4240	0.3394	0.3746	0.6468	0.4823
0.1682	11.0	4664	0.3672	0.3730	0.6496	0.4647
0.0763	12.0	5088	0.3775	0.4060	0.6618	0.4770
0.0897	13.0	5512	0.3814	0.3783	0.6498	0.4770
0.0484	14.0	5936	0.4058	0.3884	0.6572	0.4806
0.0566	15.0	6360	0.4310	0.3783	0.6566	0.4576

Kuongan/CS221-xlm-roberta-base-finetuned-som

CS221-xlm-roberta-base-finetuned-som