learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use 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
0.3999	1.0	81	0.3892	0.0	0.5	0.2862
0.3836	2.0	162	0.3703	0.0	0.5	0.2862
0.3553	3.0	243	0.3388	0.1057	0.5453	0.3608
0.3288	4.0	324	0.3273	0.2269	0.5868	0.3857
0.2659	5.0	405	0.2807	0.4160	0.6611	0.5241
0.2297	6.0	486	0.2574	0.4654	0.6816	0.5490
0.1998	7.0	567	0.2470	0.5514	0.7486	0.6019
0.1758	8.0	648	0.2302	0.5512	0.7352	0.6143
0.1516	9.0	729	0.2246	0.5846	0.7540	0.6454
0.1308	10.0	810	0.1982	0.6635	0.8007	0.6983
0.1187	11.0	891	0.1837	0.7002	0.8110	0.7185
0.1014	12.0	972	0.1852	0.6715	0.8036	0.7201
0.0865	13.0	1053	0.1773	0.7168	0.8247	0.7527
0.079	14.0	1134	0.1710	0.7410	0.8337	0.7543
0.0728	15.0	1215	0.1729	0.7450	0.8393	0.7543
0.0752	16.0	1296	0.1661	0.7406	0.8385	0.7605
0.0613	17.0	1377	0.1646	0.7404	0.8375	0.7636
0.0726	18.0	1458	0.1628	0.7445	0.8413	0.7683
0.0629	19.0	1539	0.1621	0.7455	0.8405	0.7667
0.0678	20.0	1620	0.1620	0.7539	0.8440	0.7683

Kuongan/xlm-roberta-base-ary-finetuned-RC

xlm-roberta-base-ary-finetuned-RC