fold_4_model_deberta – AI Model by Kuongan | AlphaNeural AI

You can deploy this model and start earning money today!

Kuongan/
fold_4_model_deberta

like

0

text-classification

generated_from_trainer

microsoft/deberta-v3-base

autotrain_compatible

endpoints_compatible

Views

No views yet

fold_4_model_deberta

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4724
F1: 0.8242
Roc Auc: 0.8687
Accuracy: 0.5248

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.0796	1.0	102	0.4758	0.7977	0.8495	0.4752
0.0729	2.0	204	0.4724	0.8242	0.8687	0.5248
0.0545	3.0	306	0.4535	0.7954	0.8466	0.4752
0.0243	4.0	408	0.4856	0.8069	0.8555	0.5248
0.0261	5.0	510	0.4587	0.8150	0.8614	0.5248

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0