metadata

license: mit
base_model: bert-base-cased
tags:
  - CENIA
  - News
metrics:
  - accuracy
model-index:
  - name: bert-base-cased-finetuned
    results: []
datasets:
  - cmunhozc/usa_news_en
language:
  - en
pipeline_tag: text-classification
widget:
  - text: >-
      Pfizer CEO tests positive for COVID-19, has mild symptoms || DHS Secretary
      Alejandro Mayorkas tests positive for COVID-19, reports mild symptoms
    output:
      - label: RELATED
        score: 0.2
      - label: UNRELATED
        score: 0.8
  - text: >-
      California’s most destructive earthquakes || Deadly and destructive
      California earthquakes with images from The San Francisco Chronicle’s
      archive.
    output:
      - label: RELATED
        score: 0.8
      - label: UNRELATED
        score: 0.1

bert-base-cased-finetuned

This model is a fine-tuned version of bert-base-cased on the "cmunhozc/usa_news_en" train dataset. It achieves the following results on the evaluation set:

Loss: 0.0900
Accuracy: 0.9800

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: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0967	1.0	3526	0.0651	0.9771
0.0439	2.0	7052	0.0820	0.9776
0.0231	3.0	10578	0.0900	0.9800

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0