---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- ag_news
metrics:
- f1
model-index:
- name: ag-news-twitter-19200-bert-base-uncased
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: ag_news
      type: ag_news
      config: default
      split: test
      args: default
    metrics:
    - name: F1
      type: f1
      value: 0.9254893465332044
---

<!-- 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. -->

# ag-news-twitter-19200-bert-base-uncased

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ag_news dataset.
It achieves the following results on the evaluation set:
- F1: 0.9255
- Acc: 0.9255
- Loss: 0.5130

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | F1     | Acc    | Validation Loss |
|:-------------:|:-----:|:----:|:------:|:------:|:---------------:|
| 0.3437        | 1.0   | 1200 | 0.9111 | 0.9111 | 0.2769          |
| 0.2374        | 2.0   | 2400 | 0.9199 | 0.9199 | 0.2585          |
| 0.1792        | 3.0   | 3600 | 0.9244 | 0.9243 | 0.2789          |
| 0.1021        | 4.0   | 4800 | 0.9274 | 0.9271 | 0.3265          |
| 0.0697        | 5.0   | 6000 | 0.9267 | 0.9264 | 0.3897          |
| 0.0425        | 6.0   | 7200 | 0.9247 | 0.9249 | 0.4872          |
| 0.0266        | 7.0   | 8400 | 0.9255 | 0.9255 | 0.5130          |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1