Edit model card

electra-base-discriminator-finetuned-cola

This model is a fine-tuned version of google/electra-base-discriminator on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6367
  • Matthews Correlation: 0.6824

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: 5

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.4139 1.0 535 0.4137 0.6381
0.2452 2.0 1070 0.4887 0.6504
0.17 3.0 1605 0.5335 0.6757
0.1135 4.0 2140 0.6367 0.6824
0.0817 5.0 2675 0.6742 0.6755

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu111
  • Datasets 1.17.0
  • Tokenizers 0.10.3
Downloads last month
21

Dataset used to train D3xter1922/electra-base-discriminator-finetuned-cola

Evaluation results