erickrribeiro's picture
update model card README.md
9b06654
|
raw
history blame
2.49 kB
metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
  - generated_from_trainer
datasets:
  - glue-ptpt
metrics:
  - accuracy
  - f1
model-index:
  - name: bert-base-portuguese-fine-tuned-mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue-ptpt
          type: glue-ptpt
          config: mrpc
          split: validation
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8504901960784313
          - name: F1
            type: f1
            value: 0.8920353982300885

bert-base-portuguese-fine-tuned-mrpc

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the glue-ptpt dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2843
  • Accuracy: 0.8505
  • F1: 0.8920

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
No log 1.0 459 0.6757 0.8603 0.8966
0.2011 2.0 918 0.7120 0.8505 0.8897
0.1215 3.0 1377 0.9679 0.8382 0.8764
0.0901 4.0 1836 1.0548 0.8333 0.8799
0.0478 5.0 2295 1.3125 0.8260 0.8769
0.0312 6.0 2754 1.0122 0.8578 0.8953
0.0309 7.0 3213 1.2197 0.8431 0.8849
0.0095 8.0 3672 1.1705 0.8554 0.8941
0.0076 9.0 4131 1.3132 0.8480 0.8912
0.0014 10.0 4590 1.2843 0.8505 0.8920

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3