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
0.3801	1.0	185	0.3884	0.0711	0.5125	0.3037
0.378	2.0	370	0.3604	0.1008	0.5323	0.3621
0.3409	3.0	555	0.3236	0.2468	0.6012	0.4293
0.3172	4.0	740	0.3339	0.2853	0.6254	0.4103
0.285	5.0	925	0.3379	0.2884	0.6321	0.3913
0.2552	6.0	1110	0.2744	0.4278	0.6808	0.5238
0.2263	7.0	1295	0.2649	0.4540	0.6968	0.5510
0.1882	8.0	1480	0.2491	0.4927	0.7088	0.5842
0.1995	9.0	1665	0.2375	0.5314	0.7263	0.6114
0.161	10.0	1850	0.2436	0.5328	0.7366	0.6121
0.1596	11.0	2035	0.2274	0.5553	0.7462	0.6447
0.1454	12.0	2220	0.2240	0.5889	0.7672	0.6542
0.1182	13.0	2405	0.2160	0.5964	0.7690	0.6624
0.1178	14.0	2590	0.2158	0.5866	0.7615	0.6773
0.1124	15.0	2775	0.2099	0.6397	0.7889	0.6855
0.1033	16.0	2960	0.2111	0.6396	0.7879	0.6923
0.1027	17.0	3145	0.2089	0.6479	0.7918	0.6943
0.1005	18.0	3330	0.2085	0.6481	0.7919	0.6943
0.0971	19.0	3515	0.2074	0.6495	0.7914	0.6984
0.0983	20.0	3700	0.2075	0.6497	0.7913	0.6990

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

xlm-roberta-base-tir-finetuned-RC