Amrit Puhan
End of training
7e9287a verified
metadata
license: mit
base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
tags:
  - generated_from_trainer
datasets:
  - swag
metrics:
  - accuracy
model-index:
  - name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag
    results: []

fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag

This model is a fine-tuned version of MoritzLaurer/deberta-v3-large-zeroshot-v2.0 on the swag dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5968
  • Accuracy: 0.9142

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: 1.5e-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: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4957 1.0 4597 0.2545 0.9058
0.2768 2.0 9194 0.2780 0.9089
0.1333 3.0 13791 0.4016 0.9126
0.0599 4.0 18388 0.5968 0.9142

Framework versions

  • Transformers 4.41.2
  • Pytorch 1.11.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1