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
0.3196	1.0	133	0.3019	0.2619	0.6071	0.4759
0.2552	2.0	266	0.2433	0.3165	0.6360	0.5667
0.2156	3.0	399	0.2394	0.3730	0.6689	0.5421
0.1662	4.0	532	0.1915	0.6021	0.7807	0.6528
0.141	5.0	665	0.1571	0.6416	0.7900	0.7256
0.1144	6.0	798	0.1406	0.6766	0.8088	0.7531
0.0859	7.0	931	0.1295	0.7186	0.8437	0.7956
0.0663	8.0	1064	0.1129	0.7474	0.8489	0.8193
0.0527	9.0	1197	0.1110	0.7849	0.8705	0.8373
0.0423	10.0	1330	0.1029	0.8321	0.8897	0.8505
0.0323	11.0	1463	0.0984	0.8575	0.9003	0.8657
0.0235	12.0	1596	0.0944	0.8558	0.9192	0.8770
0.0209	13.0	1729	0.0930	0.8688	0.9231	0.8798
0.0164	14.0	1862	0.0940	0.8847	0.9277	0.8798
0.0139	15.0	1995	0.0905	0.8924	0.9343	0.8874
0.0127	16.0	2128	0.0896	0.8945	0.9319	0.8827
0.0111	17.0	2261	0.0902	0.8903	0.9338	0.8836
0.0108	18.0	2394	0.0902	0.8918	0.9330	0.8865
0.0099	19.0	2527	0.0894	0.8928	0.9339	0.8874
0.0105	20.0	2660	0.0894	0.8928	0.9339	0.8874

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

xlm-roberta-base-chn-finetuned-RC