bert-azahead-v0.1 / README.md
zwellington's picture
update model card README.md
a3260b5
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - azaheadhealth
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: bert-azahead-v0.1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: azaheadhealth
          type: azaheadhealth
          config: small
          split: test
          args: small
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.75
          - name: F1
            type: f1
            value: 0.4
          - name: Precision
            type: precision
            value: 0.6666666666666666
          - name: Recall
            type: recall
            value: 0.2857142857142857

bert-azahead-v0.1

This model is a fine-tuned version of bert-base-uncased on the azaheadhealth dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4710
  • Accuracy: 0.75
  • F1: 0.4
  • Precision: 0.6667
  • Recall: 0.2857

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.6325 0.5 20 0.5001 0.7917 0.7059 0.6 0.8571
0.5346 1.0 40 0.4710 0.75 0.4 0.6667 0.2857

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.2.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.13.2