deberta-wic-angle3 – AI Model by Deehan1866 | AlphaNeural AI

You can deploy this model and start earning money today!

Deehan1866/
deberta-wic-angle3

like

0

text-classification

generated_from_trainer

microsoft/deberta-v3-large

endpoints_compatible

Views

No views yet

deberta-wic-angle3

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

Loss: 0.1912
Accuracy: 0.9687

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2234	1.0	170	0.1966	0.9530
0.1351	2.0	340	0.1612	0.9624
0.1019	3.0	510	0.1375	0.9624
0.0831	4.0	680	0.1117	0.9687
0.0448	5.0	850	0.1555	0.9655
0.0217	6.0	1020	0.1744	0.9687
0.0262	7.0	1190	0.1912	0.9687

Framework versions

Transformers 4.57.6
Pytorch 2.8.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2