tuni's picture
update model card README.md
9a79d94
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: distilbert-base-uncased-finetuned-mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8204788588894549

distilbert-base-uncased-finetuned-mnli

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: 0.6574
  • Accuracy: 0.8205

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: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5188 1.0 24544 0.4979 0.8047
0.4153 2.0 49088 0.4845 0.8147
0.3008 3.0 73632 0.5631 0.8204
0.2226 4.0 98176 0.6574 0.8205
0.189 5.0 122720 0.8209 0.8194

Framework versions

  • Transformers 4.19.4
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.0
  • Tokenizers 0.12.1