nc33's picture
update model card README.md
972dc75
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - super_glue
metrics:
  - accuracy
model-index:
  - name: finetune_deberta_small_model
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: super_glue
          type: super_glue
          config: boolq
          split: train
          args: boolq
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8021406727828746

finetune_deberta_small_model

This model is a fine-tuned version of nc33/finetune_deberta_small_model on the super_glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6788
  • Accuracy: 0.8021

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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3666 1.0 590 0.5625 0.8003
0.2501 2.0 1180 0.6762 0.7976
0.2343 3.0 1770 0.6788 0.8021

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2