distilbert-base-uncased-finetuned-cola

This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8549
  • Matthews Correlation: 0.5332

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
0.5213 1.0 535 0.5163 0.4183
0.3479 2.0 1070 0.5351 0.5182
0.231 3.0 1605 0.6271 0.5291
0.166 4.0 2140 0.7531 0.5279
0.1313 5.0 2675 0.8549 0.5332

Framework versions

  • Transformers 4.10.0.dev0
  • Pytorch 1.8.1
  • Datasets 1.11.0
  • Tokenizers 0.10.3
Downloads last month
4
Hosted inference API
Text Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.