lewtun's picture
lewtun HF staff
Add evaluation results on glue
cc997b2
|
raw
history blame
2.39 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: autoevaluate-binary-classification
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8967889908256881
      - metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8967889908256881
            verified: true
          - name: Precision
            type: precision
            value: 0.8898678414096917
            verified: true
          - name: Recall
            type: recall
            value: 0.9099099099099099
            verified: true
          - name: AUC
            type: auc
            value: 0.9672423591816115
            verified: true
          - name: F1
            type: f1
            value: 0.8997772828507795
            verified: true
          - name: loss
            type: loss
            value: 0.300935298204422
            verified: true
          - name: matthews_correlation
            type: matthews_correlation
            value: 0.793630584795814
            verified: true
        task:
          type: text-classification
          name: Text Classification
        dataset:
          name: glue
          type: glue

binary-classification

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: 0.3009
  • Accuracy: 0.8968

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: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.175 1.0 4210 0.3009 0.8968

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1