README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: distilbert-base-uncased-finetuned-FFT-CoLA
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.5049093009936784

distilbert-base-uncased-finetuned-lora-cola

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

• Matthews Correlation: 0.5049
• trainable model parameters: 1181954
• all model parameters: 68136964
• percentage of trainable model parameters: 1.73%

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-04
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• weight_decay: 0.01
• rank: 32
• lora_alpha: 16
• lora_dropout: 0.05
• num_epochs: 5