Hugging Face's logo

nc33
/
qna2_deberta_model

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
deberta-v2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
3
qna2_deberta_model / README.md
nc33's picture
nc33
Update README.md
85e0e12
preview code
|
raw history blame contribute delete
No virus
1.27 kB
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - super_glue
model-index:
  - name: qna2_deberta_model
    results: []

boolq_deberta_model

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

  • eval_loss: 0.4066
  • eval_accuracy: 0.8468
  • eval_runtime: 111.0255
  • eval_samples_per_second: 29.453
  • eval_steps_per_second: 1.846
  • epoch: 2.0
  • step: 1180

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: linear
  • num_epochs: 3

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2