UIT-NO-PRExlnet-base-cased-finetuned

This model is a fine-tuned version of xlnet/xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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: 30

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.5578	1.0	139	0.5043	0.3149	0.5892	0.2022
0.4414	2.0	278	0.4142	0.6034	0.7089	0.3827
0.3813	3.0	417	0.3941	0.6657	0.7419	0.4061
0.2291	4.0	556	0.4109	0.6806	0.7463	0.4260
0.23	5.0	695	0.4438	0.6914	0.7605	0.4386
0.15	6.0	834	0.4506	0.7001	0.7664	0.4513
0.1324	7.0	973	0.4842	0.6910	0.7646	0.4603
0.0803	8.0	1112	0.5092	0.7164	0.7915	0.4513
0.0772	9.0	1251	0.5448	0.7000	0.7734	0.4404
0.0459	10.0	1390	0.5791	0.6958	0.7693	0.4332
0.0308	11.0	1529	0.5954	0.7102	0.7836	0.4386
0.0343	12.0	1668	0.6288	0.7030	0.7780	0.4350
0.0254	13.0	1807	0.6397	0.7187	0.7856	0.4531
0.0269	14.0	1946	0.6693	0.6932	0.7705	0.4368
0.0144	15.0	2085	0.6778	0.6949	0.7711	0.4386
0.0104	16.0	2224	0.7106	0.6943	0.7684	0.4368
0.006	17.0	2363	0.7217	0.7053	0.7749	0.4422
0.0109	18.0	2502	0.7313	0.7124	0.7826	0.4368
0.0063	19.0	2641	0.7416	0.7116	0.7796	0.4314
0.0043	20.0	2780	0.7470	0.7124	0.7795	0.4332
0.0031	21.0	2919	0.7647	0.7012	0.7710	0.4296
0.0041	22.0	3058	0.7516	0.7019	0.7722	0.4350
0.0028	23.0	3197	0.7591	0.7035	0.7721	0.4386
0.0027	24.0	3336	0.7587	0.7052	0.7748	0.4386
0.0028	25.0	3475	0.7644	0.7099	0.7770	0.4422
0.0027	26.0	3614	0.7656	0.7081	0.7758	0.4422
0.0033	27.0	3753	0.7629	0.7097	0.7764	0.4477
0.0026	28.0	3892	0.7622	0.7082	0.7758	0.4458
0.0025	29.0	4031	0.7626	0.7082	0.7758	0.4458
0.0023	30.0	4170	0.7627	0.7082	0.7758	0.4458