paraphrase-bert-portuguese

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: 1.2267
  • Accuracy: 0.8676
  • F1: 0.9029

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 0.7241 0.8603 0.9012
0.0658 2.0 918 0.7902 0.8725 0.9071
0.1499 3.0 1377 0.7895 0.8676 0.9022
0.0654 4.0 1836 0.9841 0.8676 0.9036
0.018 5.0 2295 1.0520 0.8627 0.8989
0.0144 6.0 2754 1.1002 0.8725 0.9081
0.007 7.0 3213 1.1303 0.8652 0.9005
0.0056 8.0 3672 1.2298 0.8725 0.9081
0.0019 9.0 4131 1.2353 0.8701 0.9038
0.0001 10.0 4590 1.2267 0.8676 0.9029

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3
Downloads last month
42
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for erickrribeiro/paraphrase-bert-portuguese

Finetuned
(99)
this model

Evaluation results