Hugging Face's logo

azmina
/
ia-feminista-bert-posicao

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
ia-feminista-bert-posicao / README.md
belisards's picture
belisards
azmn-posicao-fin
1926e72 verified
preview code
|
raw
history blame
3.21 kB
metadata
library_name: transformers
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - recall
  - precision
model-index:
  - name: neuralmind/bert-base-portuguese-cased
    results: []

neuralmind/bert-base-portuguese-cased

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0460
  • Accuracy: 0.8367
  • F1: 0.7871
  • Recall: 0.8194
  • Precision: 0.7687

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: 64
  • eval_batch_size: 64
  • seed: 5151
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 150
  • num_epochs: 19

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Recall Precision
0.0801 1.0 18 0.0769 0.7411 0.4256 0.5 0.3705
0.0691 2.0 36 0.0709 0.75 0.4612 0.5172 0.8739
0.0647 3.0 54 0.0661 0.75 0.4612 0.5172 0.8739
0.0644 4.0 72 0.0648 0.6518 0.5774 0.5856 0.5753
0.0621 5.0 90 0.0632 0.7054 0.6424 0.6554 0.6367
0.0621 6.0 108 0.0627 0.7232 0.6265 0.6226 0.6319
0.0586 7.0 126 0.0595 0.75 0.6937 0.7079 0.6857
0.0547 8.0 144 0.0582 0.7768 0.7338 0.7597 0.7223
0.0509 9.0 162 0.0554 0.7768 0.7338 0.7597 0.7223
0.0462 10.0 180 0.0557 0.75 0.7091 0.7416 0.6998
0.0437 11.0 198 0.0532 0.7768 0.7382 0.7709 0.7264
0.0415 12.0 216 0.0515 0.7857 0.7466 0.7769 0.7341
0.0356 13.0 234 0.0545 0.8036 0.7547 0.7665 0.7461
0.0301 14.0 252 0.0543 0.8214 0.7770 0.7898 0.7675
0.0262 15.0 270 0.0541 0.8036 0.7594 0.7777 0.7481
0.0248 16.0 288 0.0583 0.8125 0.7584 0.7613 0.7557
0.0232 17.0 306 0.0593 0.8125 0.7635 0.7725 0.7562

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0