---
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-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: 0.7083333333333334
    - name: F1
      type: f1
      value: 0.46153846153846156
    - name: Precision
      type: precision
      value: 0.5
    - name: Recall
      type: recall
      value: 0.42857142857142855
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert-azahead-v1.0

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the azaheadhealth dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7204
- Accuracy: 0.7083
- F1: 0.4615
- Precision: 0.5
- Recall: 0.4286

## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.5889        | 1.0   | 10   | 0.5438          | 0.625    | 0.0    | 0.0       | 0.0    |
| 0.4926        | 2.0   | 20   | 0.4309          | 0.75     | 0.5714 | 0.5714    | 0.5714 |
| 0.3613        | 3.0   | 30   | 0.4260          | 0.75     | 0.5714 | 0.5714    | 0.5714 |
| 0.2628        | 4.0   | 40   | 0.4989          | 0.75     | 0.5714 | 0.5714    | 0.5714 |
| 0.1658        | 5.0   | 50   | 0.5883          | 0.7083   | 0.4615 | 0.5       | 0.4286 |
| 0.1153        | 6.0   | 60   | 0.6374          | 0.6667   | 0.3333 | 0.4       | 0.2857 |
| 0.074         | 7.0   | 70   | 0.6709          | 0.6667   | 0.3333 | 0.4       | 0.2857 |
| 0.0548        | 8.0   | 80   | 0.6848          | 0.7083   | 0.4615 | 0.5       | 0.4286 |
| 0.0456        | 9.0   | 90   | 0.7322          | 0.7083   | 0.4615 | 0.5       | 0.4286 |
| 0.0439        | 10.0  | 100  | 0.7204          | 0.7083   | 0.4615 | 0.5       | 0.4286 |


### Framework versions

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