UIT-NO-PREPROCESSING-deberta-v3-large-finetuned

This model is a fine-tuned version of microsoft/deberta-v3-large 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: 20

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.5077	1.0	139	0.4600	0.4594	0.6568	0.3357
0.3888	2.0	278	0.3953	0.6320	0.7310	0.4007
0.3306	3.0	417	0.3528	0.7181	0.7846	0.4838
0.1688	4.0	556	0.3831	0.7490	0.8098	0.4603
0.127	5.0	695	0.4009	0.7598	0.8160	0.5090
0.0984	6.0	834	0.4668	0.7282	0.7928	0.4892
0.0477	7.0	973	0.4952	0.7547	0.8093	0.5018
0.0293	8.0	1112	0.5263	0.7688	0.8207	0.5199
0.0205	9.0	1251	0.6005	0.7445	0.8044	0.4856
0.0202	10.0	1390	0.6518	0.7581	0.8079	0.4892
0.01	11.0	1529	0.6087	0.7662	0.8228	0.5162
0.0021	12.0	1668	0.6349	0.7584	0.8118	0.5090
0.0019	13.0	1807	0.6584	0.7567	0.8089	0.5126
0.0014	14.0	1946	0.6690	0.7608	0.8127	0.5072
0.0024	15.0	2085	0.6591	0.7637	0.8165	0.5108
0.0014	16.0	2224	0.6727	0.7632	0.8157	0.5162
0.0015	17.0	2363	0.6736	0.7619	0.8144	0.5144
0.0015	18.0	2502	0.6753	0.7641	0.8158	0.5199
0.002	19.0	2641	0.6768	0.7631	0.8151	0.5181
0.0014	20.0	2780	0.6769	0.7631	0.8151	0.5181