metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - pearsonr
  - spearmanr
model-index:
  - name: deberta-v3-base-finetuned-FFT-STSB
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: stsb
        metrics:
          - name: Pearsonr
            type: pearsonr
            value: 0.9083306190960106
          - name: Spearmanr
            type: spearmanr
            value: 0.9063517759229397

deberta-v3-base-finetuned-fft-stsb

This model is a fine-tuned version of deberta-v3-base on the glue dataset. It achieves the following results on the evaluation set:

Pearsonr: 0.9083
Spearmanr: 0.9064

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
weight_decay: 0.01
num_epochs: 3