Hugging Face's logo

Jsevisal
/
balanced-augmented-bert-large-gest-pred-seqeval-partialmatch-2

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
balanced-augmented-bert-large-gest-pred-seqeval-partialmatch-2 / README.md
Jsevisal's picture
Jsevisal
Update README.md
977683f
preview code
|
raw
history blame contribute delete
No virus
4.15 kB
metadata
license: other
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: balanced-augmented-bert-large-gest-pred-seqeval-partialmatch-2
    results: []
datasets:
  - Jsevisal/balanced_augmented_dataset_2
pipeline_tag: token-classification

balanced-augmented-bert-large-gest-pred-seqeval-partialmatch-2

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

  • Loss: 0.3427
  • Precision: 0.9361
  • Recall: 0.9389
  • F1: 0.9320
  • Accuracy: 0.9260

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
2.9298 1.0 52 2.3822 0.2363 0.1557 0.1575 0.3204
1.9949 2.0 104 1.5817 0.5566 0.5259 0.4978 0.5958
1.3242 3.0 156 1.0665 0.6572 0.6680 0.6417 0.7124
0.8143 4.0 208 0.7375 0.8047 0.8024 0.7876 0.7972
0.4744 5.0 260 0.5433 0.8598 0.8570 0.8434 0.8476
0.2876 6.0 312 0.4301 0.8945 0.9034 0.8911 0.8868
0.1784 7.0 364 0.5261 0.9056 0.8915 0.8866 0.8711
0.1103 8.0 416 0.4828 0.9169 0.9172 0.9066 0.8917
0.076 9.0 468 0.3915 0.9116 0.9075 0.9016 0.8956
0.053 10.0 520 0.3593 0.9167 0.9299 0.9177 0.9143
0.0364 11.0 572 0.3427 0.9361 0.9389 0.9320 0.9260
0.028 12.0 624 0.3638 0.9275 0.9327 0.9253 0.9162
0.0195 13.0 676 0.3486 0.9268 0.9416 0.9298 0.9216
0.0156 14.0 728 0.4049 0.9204 0.9256 0.9156 0.9030
0.0146 15.0 780 0.3894 0.9267 0.9311 0.9224 0.9152
0.01 16.0 832 0.3661 0.9268 0.9342 0.9248 0.9201
0.0082 17.0 884 0.3897 0.9243 0.9293 0.9197 0.9133
0.0076 18.0 936 0.3723 0.9254 0.9353 0.9250 0.9192
0.0069 19.0 988 0.3841 0.9277 0.9322 0.9236 0.9157
0.0075 20.0 1040 0.3825 0.9273 0.9325 0.9236 0.9157

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.1+cu116
  • Datasets 2.11.0
  • Tokenizers 0.13.2

LICENSE

Copyright (c) 2014, Universidad Carlos III de Madrid. Todos los derechos reservados. Este software es propiedad de la Universidad Carlos III de Madrid, grupo de investigaci贸n Robots Sociales. La Universidad Carlos III de Madrid es titular en exclusiva de los derechos de propiedad intelectual de este software. Queda prohibido cualquier uso indebido o no autorizado, entre estos, a t铆tulo enunciativo pero no limitativo, la reproducci贸n, fijaci贸n, distribuci贸n, comunicaci贸n p煤blica, ingenier铆a inversa y/o transformaci贸n sobre dicho software, ya sea total o parcialmente, siendo el responsable del uso indebido o no autorizado tambi茅n responsable de las consecuencias legales que pudieran derivarse de sus actos.