deberta-base-peft / README.md
alitolga's picture
End of training
e94aa33
metadata
license: mit
base_model: microsoft/deberta-base
tags:
  - generated_from_trainer
model-index:
  - name: deberta-base-peft
    results: []

deberta-base-peft

This model is a fine-tuned version of microsoft/deberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5691

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
2.4191 1.0 389 1.2536
1.2007 2.0 778 0.6712
0.9788 3.0 1167 0.5691

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1