UIT-NO-PREPROCESSING-xlnet-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 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: 30

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.5449	1.0	139	0.4804	0.4118	0.6260	0.2599
0.4223	2.0	278	0.4035	0.6112	0.7102	0.3845
0.3608	3.0	417	0.3775	0.6760	0.7563	0.4296
0.2465	4.0	556	0.4056	0.6806	0.7474	0.4206
0.2267	5.0	695	0.4280	0.6797	0.7575	0.4440
0.1656	6.0	834	0.4314	0.6991	0.7686	0.4422
0.1019	7.0	973	0.4682	0.7132	0.7819	0.4422
0.085	8.0	1112	0.4941	0.7248	0.8006	0.4513
0.0614	9.0	1251	0.5406	0.7215	0.7958	0.4422
0.0367	10.0	1390	0.5513	0.7084	0.7777	0.4458
0.0303	11.0	1529	0.6009	0.7116	0.7847	0.4368
0.0333	12.0	1668	0.6034	0.6836	0.7609	0.4368
0.0274	13.0	1807	0.6468	0.7166	0.7867	0.4296
0.019	14.0	1946	0.6636	0.7017	0.7776	0.4350
0.0153	15.0	2085	0.6902	0.6958	0.7641	0.4206
0.0067	16.0	2224	0.6829	0.7159	0.7844	0.4458
0.0074	17.0	2363	0.6976	0.7179	0.7832	0.4621
0.0114	18.0	2502	0.6938	0.7170	0.7854	0.4458
0.0065	19.0	2641	0.7382	0.7111	0.7780	0.4404
0.0053	20.0	2780	0.7199	0.7057	0.7758	0.4513
0.0033	21.0	2919	0.7228	0.7176	0.7878	0.4567
0.0038	22.0	3058	0.7277	0.7179	0.7851	0.4603
0.0031	23.0	3197	0.7350	0.7229	0.7883	0.4567
0.003	24.0	3336	0.7448	0.7195	0.7856	0.4513
0.0028	25.0	3475	0.7453	0.7241	0.7896	0.4495
0.0029	26.0	3614	0.7428	0.7176	0.7843	0.4440
0.0024	27.0	3753	0.7421	0.7155	0.7823	0.4495
0.0026	28.0	3892	0.7425	0.7156	0.7830	0.4477
0.0091	29.0	4031	0.7466	0.7168	0.7839	0.4495
0.0023	30.0	4170	0.7467	0.7175	0.7844	0.4513