Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
deberta-v3-base-finetuned-LoRA-QNLI – AI Model by rambodazimi | AlphaNeural AI
You can deploy this model and start earning money today!
rambodazimi
/
deberta-v3-base-finetuned-LoRA-QNLI
like
0
safetensors
generated_from_trainer
glue
apache-2.0
model-index
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
deberta-v3-base-finetuned-lora-qnli
This model is a fine-tuned version of
deberta-v3-base
on the glue dataset. It achieves the following results on the evaluation set:
Accuracy: 0.9414
trainable model parameters: 591362
all model parameters: 185015044
percentage of trainable model parameters: 0.32%
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-04
train_batch_size: 32
eval_batch_size: 32
seed: 42
weight_decay: 0.01
rank: 16
lora_alpha: 32
lora_dropout: 0.1
num_epochs: 4
