GCopoulos's picture
update model card README.md
26d01d1
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - f1
model-index:
  - name: deberta-finetuned-answer-polarity-warmup-f1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: answer_pol
          split: validation
          args: answer_pol
        metrics:
          - name: F1
            type: f1
            value: 0.8602499021892139

deberta-finetuned-answer-polarity-warmup-f1

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

  • Loss: 0.3748
  • F1: 0.8602

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: 7e-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 F1
No log 1.0 364 0.5669 0.8303
0.0791 2.0 728 0.5405 0.4630
0.3408 3.0 1092 0.3748 0.8602

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3