Edit model card

canine-c-finetuned-mrpc

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

  • Loss: 0.4066
  • Accuracy: 0.8627
  • F1: 0.9014

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 0.5014 0.7696 0.8479
No log 2.0 460 0.4755 0.7892 0.8622
0.5096 3.0 690 0.3645 0.8431 0.8869
0.5096 4.0 920 0.4066 0.8627 0.9014
0.2619 5.0 1150 0.4551 0.8431 0.8877

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.0.0
  • Tokenizers 0.11.6
Downloads last month
53

Dataset used to train vicl/canine-c-finetuned-mrpc

Evaluation results