bart-large-mrpc / README.md
juliensimon's picture
Librarian Bot: Add base_model information to model (#2)
e4885d3
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
base_model: facebook/bart-large
model-index:
  - name: bart-large-mrpc
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - type: accuracy
            value: 0.8774509803921569
            name: Accuracy
          - type: f1
            value: 0.9119718309859154
            name: F1

bart-large-mrpc

This model is a fine-tuned version of facebook/bart-large on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5684
  • Accuracy: 0.8775
  • F1: 0.9120
  • Combined Score: 0.8947

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: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.0+cu102
  • Datasets 2.1.0
  • Tokenizers 0.11.6