anirudh21's picture
update model card README.md
518ac61
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: distilbert-base-uncased-finetuned-rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6173285198555957

distilbert-base-uncased-finetuned-rte

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: 0.6661
  • Accuracy: 0.6173

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
No log 1.0 156 0.6921 0.5162
No log 2.0 312 0.6661 0.6173
No log 3.0 468 0.7794 0.5632
0.5903 4.0 624 0.8832 0.5921
0.5903 5.0 780 0.9376 0.5921

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu111
  • Datasets 1.17.0
  • Tokenizers 0.10.3