deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-DAIR – AI Model by sercetexam9 | AlphaNeural AI

You can deploy this model and start earning money today!

sercetexam9/
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-DAIR

like

0

text-classification

generated_from_trainer

microsoft/deberta-v3-large

autotrain_compatible

endpoints_compatible

Views

No views yet

deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-DAIR

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:

Loss: 0.4415
F1: 0.8617
Roc Auc: 0.9130
Accuracy: 0.7521

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2536	1.0	627	0.2525	0.7755	0.8495	0.6407
0.1897	2.0	1254	0.2188	0.8190	0.8742	0.6894
0.1368	3.0	1881	0.1937	0.8448	0.8948	0.7277
0.1092	4.0	2508	0.2213	0.8486	0.8993	0.7385
0.0603	5.0	3135	0.2761	0.8417	0.9013	0.7202
0.0417	6.0	3762	0.2963	0.8469	0.9071	0.7293
0.0245	7.0	4389	0.3429	0.8508	0.9001	0.7437
0.0137	8.0	5016	0.3727	0.8477	0.8993	0.7297
0.0128	9.0	5643	0.3763	0.8577	0.9139	0.7473
0.0061	10.0	6270	0.3809	0.8568	0.9041	0.7473
0.0048	11.0	6897	0.3992	0.8584	0.9048	0.7453
0.0016	12.0	7524	0.4154	0.8614	0.9061	0.7517
0.0067	13.0	8151	0.4415	0.8617	0.9130	0.7521
0.0004	14.0	8778	0.4380	0.8596	0.9074	0.7529
0.0002	15.0	9405	0.4420	0.8597	0.9065	0.7525
0.0009	16.0	10032	0.4489	0.8605	0.9110	0.7493
0.0001	17.0	10659	0.4516	0.8591	0.9087	0.7501

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0