glue-mrpc / README.md
sgugger's picture
sgugger
HF staff
Add evaluation results on the mrpc config of glue (#1)
7735f02
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: glue-mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8553921568627451
          - name: F1
            type: f1
            value: 0.897391304347826
      - task:
          type: natural-language-inference
          name: Natural Language Inference
        dataset:
          name: glue
          type: glue
          config: mrpc
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8553921568627451
            verified: true
          - name: Precision
            type: precision
            value: 0.8716216216216216
            verified: true
          - name: Recall
            type: recall
            value: 0.9247311827956989
            verified: true
          - name: AUC
            type: auc
            value: 0.90464282737351
            verified: true
          - name: F1
            type: f1
            value: 0.897391304347826
            verified: true
          - name: loss
            type: loss
            value: 0.6564616560935974
            verified: true

glue-mrpc

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

  • Loss: 0.6566
  • Accuracy: 0.8554
  • F1: 0.8974
  • Combined Score: 0.8764

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: 5e-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

Framework versions

  • Transformers 4.13.0.dev0
  • Pytorch 1.10.0+cu102
  • Datasets 1.15.2.dev0
  • Tokenizers 0.10.3