metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - azaheadhealth
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: azahead-bert-v1.0
    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: 0.7916666666666666
          - name: F1
            type: f1
            value: 0.6666666666666666
          - name: Precision
            type: precision
            value: 0.625
          - name: Recall
            type: recall
            value: 0.7142857142857143

azahead-bert-v1.0

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: 0.5108
Accuracy: 0.7917
F1: 0.6667
Precision: 0.625
Recall: 0.7143

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6157	1.0	20	0.5087	0.7083	0.0	0.0	0.0
0.4057	2.0	40	0.5892	0.7083	0.2222	0.5	0.1429
0.2788	3.0	60	0.4834	0.7917	0.4444	1.0	0.2857
0.1726	4.0	80	0.5108	0.7917	0.6667	0.625	0.7143
0.1271	5.0	100	0.6210	0.7917	0.6154	0.6667	0.5714
0.1045	6.0	120	0.6850	0.7917	0.6154	0.6667	0.5714
0.0108	7.0	140	0.7771	0.75	0.5714	0.5714	0.5714
0.0248	8.0	160	0.8454	0.7917	0.6154	0.6667	0.5714
0.0152	9.0	180	0.8667	0.7917	0.6154	0.6667	0.5714
0.0064	10.0	200	0.8776	0.75	0.5714	0.5714	0.5714

Framework versions

Transformers 4.31.0
Pytorch 2.2.0+cu121
Datasets 2.16.1
Tokenizers 0.13.2