UIT-NO-PREPROCESSING-deberta-v3-base-finetuned

This model is a fine-tuned version of microsoft/deberta-v3-base 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
0.0139	1.0	139	0.6990	0.7565	0.8141	0.4711
0.0205	2.0	278	0.7726	0.7326	0.7961	0.4693
0.0359	3.0	417	0.8357	0.7401	0.8094	0.4747
0.0204	4.0	556	0.8613	0.7332	0.7975	0.4693
0.0102	5.0	695	0.8587	0.7452	0.8108	0.4657
0.0152	6.0	834	0.9166	0.7366	0.8008	0.4458
0.008	7.0	973	0.9269	0.7207	0.7874	0.4603
0.0092	8.0	1112	0.9466	0.7486	0.8156	0.4513
0.016	9.0	1251	1.0921	0.7259	0.7835	0.4260
0.0014	10.0	1390	0.9858	0.7452	0.8065	0.4621
0.004	11.0	1529	1.0044	0.7349	0.7971	0.4819
0.0009	12.0	1668	1.0357	0.7274	0.7906	0.4585
0.0006	13.0	1807	1.0344	0.7577	0.8171	0.4856
0.0013	14.0	1946	1.0302	0.7493	0.8112	0.4711
0.0004	15.0	2085	1.0197	0.7609	0.8178	0.4964
0.0005	16.0	2224	1.0398	0.7476	0.8082	0.4765
0.0003	17.0	2363	1.0740	0.7410	0.8014	0.4838
0.0003	18.0	2502	1.0296	0.7552	0.8147	0.4892
0.0004	19.0	2641	1.0621	0.7462	0.8045	0.4946
0.0003	20.0	2780	1.0575	0.7563	0.8132	0.4982
0.0043	21.0	2919	1.0494	0.7543	0.8137	0.4982
0.0002	22.0	3058	1.0548	0.7586	0.8154	0.5018
0.0003	23.0	3197	1.0443	0.7530	0.8127	0.4964
0.0003	24.0	3336	1.0533	0.7561	0.8137	0.5036
0.0006	25.0	3475	1.0386	0.7568	0.8158	0.4928
0.0008	26.0	3614	1.0413	0.7569	0.8152	0.4910
0.0002	27.0	3753	1.0443	0.7507	0.8106	0.4982
0.0002	28.0	3892	1.0500	0.7490	0.8091	0.4928
0.0006	29.0	4031	1.0506	0.7495	0.8093	0.4928
0.0001	30.0	4170	1.0506	0.7495	0.8093	0.4928