Edit model card

finetuned-bert-mrpc

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

  • Loss: 0.3874
  • Accuracy: 0.8676
  • F1: 0.9066

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: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5751 1.0 230 0.3812 0.8284 0.8768
0.327 2.0 460 0.4207 0.8505 0.8992
0.176 3.0 690 0.3874 0.8676 0.9066

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.13.3
Downloads last month
5

Finetuned from

Dataset used to train Zynab/finetuned-bert-mrpc

Evaluation results