README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - feverous
metrics:
  - accuracy
model-index:
  - name: deberta-v3-base-finetuned-fever
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: feverous
          type: feverous
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6153358681875792

deberta-v3-base-finetuned-fever

This model is a fine-tuned version of microsoft/deberta-v3-base on the feverous dataset. It achieves the following results on the evaluation set:

• Loss: 0.8830
• Accuracy: 0.6153

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
0.7054	1.0	4456	0.8351	0.6027
0.6389	2.0	8912	0.8830	0.6153
0.5562	3.0	13368	0.9398	0.6134
0.4614	4.0	17824	1.0787	0.6115
0.3867	5.0	22280	1.1430	0.6091

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3