Edit model card

distilbert-base-uncased-finetuned-mrpc

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: 0.3830
  • Accuracy: 0.8456
  • F1: 0.8959

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 Accuracy F1
No log 1.0 230 0.3826 0.8186 0.8683
No log 2.0 460 0.3830 0.8456 0.8959
0.4408 3.0 690 0.3835 0.8382 0.8866
0.4408 4.0 920 0.5036 0.8431 0.8919
0.1941 5.0 1150 0.5783 0.8431 0.8930

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu111
  • Datasets 1.17.0
  • Tokenizers 0.10.3
Downloads last month
27

Dataset used to train anirudh21/distilbert-base-uncased-finetuned-mrpc

Evaluation results