UIT-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 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
0.0278	1.0	139	0.6977	0.6913	0.7650	0.4097
0.0277	2.0	278	0.7416	0.6805	0.7529	0.4170
0.0148	3.0	417	0.7729	0.6738	0.7538	0.4242
0.0125	4.0	556	0.7640	0.7112	0.7836	0.4296
0.0101	5.0	695	0.8752	0.6852	0.7555	0.3917
0.0281	6.0	834	0.8986	0.6937	0.7653	0.3899
0.007	7.0	973	0.8798	0.6716	0.7569	0.4025
0.0172	8.0	1112	0.8986	0.6850	0.7671	0.3899
0.014	9.0	1251	0.9143	0.6916	0.7763	0.4007
0.0075	10.0	1390	0.9429	0.6885	0.7660	0.4025
0.0029	11.0	1529	0.9481	0.6762	0.7569	0.4134
0.0042	12.0	1668	0.9592	0.6889	0.7698	0.4134
0.0023	13.0	1807	0.9875	0.6925	0.7666	0.3899
0.0119	14.0	1946	0.9721	0.6824	0.7620	0.4134
0.003	15.0	2085	0.9458	0.7012	0.7752	0.4422
0.0074	16.0	2224	0.9593	0.7031	0.7746	0.4495
0.0011	17.0	2363	0.9751	0.6947	0.7704	0.4314
0.0056	18.0	2502	1.0365	0.6796	0.7579	0.4170
0.0089	19.0	2641	1.0168	0.6950	0.7698	0.4224
0.0066	20.0	2780	1.0006	0.7073	0.7766	0.4386
0.0014	21.0	2919	0.9940	0.7030	0.7729	0.4296
0.0007	22.0	3058	0.9877	0.7073	0.7776	0.4368
0.0007	23.0	3197	0.9888	0.7038	0.7758	0.4332
0.0008	24.0	3336	0.9920	0.7035	0.7749	0.4296
0.0019	25.0	3475	0.9938	0.6986	0.7694	0.4332
0.0007	26.0	3614	0.9943	0.7034	0.7731	0.4350
0.0012	27.0	3753	0.9978	0.7046	0.7739	0.4404
0.0006	28.0	3892	0.9969	0.7035	0.7731	0.4350
0.0007	29.0	4031	0.9971	0.7035	0.7731	0.4314
0.0005	30.0	4170	0.9969	0.7042	0.7736	0.4332