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: 0.5579
  • Accuracy: 0.7328
  • F1: 0.8310

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 23 0.5797 0.7010 0.8195
No log 2.0 46 0.5647 0.7083 0.8242
No log 3.0 69 0.5677 0.7181 0.8276
No log 4.0 92 0.5495 0.7328 0.8300
No log 5.0 115 0.5579 0.7328 0.8310

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.9.0+cu111
  • Datasets 1.12.1
  • Tokenizers 0.10.3
Downloads last month
23

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

Evaluation results