| --- |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: '5' |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # 5 |
|
|
| This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.2255 |
| - Precision: 0.6432 |
| - Recall: 0.595 |
| - F1: 0.6182 |
| - Accuracy: 0.9709 |
|
|
| ## 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: 5.5e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 32 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | No log | 1.0 | 29 | 0.3210 | 0.0 | 0.0 | 0.0 | 0.9324 | |
| | No log | 2.0 | 58 | 0.2694 | 0.0 | 0.0 | 0.0 | 0.9324 | |
| | No log | 3.0 | 87 | 0.2216 | 0.0 | 0.0 | 0.0 | 0.9316 | |
| | No log | 4.0 | 116 | 0.2115 | 0.25 | 0.035 | 0.0614 | 0.9403 | |
| | No log | 5.0 | 145 | 0.1740 | 0.3465 | 0.175 | 0.2326 | 0.9512 | |
| | No log | 6.0 | 174 | 0.1589 | 0.42 | 0.315 | 0.36 | 0.9566 | |
| | No log | 7.0 | 203 | 0.1514 | 0.4797 | 0.295 | 0.3653 | 0.9584 | |
| | No log | 8.0 | 232 | 0.1686 | 0.4576 | 0.405 | 0.4297 | 0.9624 | |
| | No log | 9.0 | 261 | 0.1840 | 0.5971 | 0.415 | 0.4897 | 0.9646 | |
| | No log | 10.0 | 290 | 0.1571 | 0.5505 | 0.545 | 0.5477 | 0.9646 | |
| | No log | 11.0 | 319 | 0.1809 | 0.6158 | 0.545 | 0.5782 | 0.9700 | |
| | No log | 12.0 | 348 | 0.1763 | 0.6129 | 0.57 | 0.5907 | 0.9681 | |
| | No log | 13.0 | 377 | 0.1902 | 0.5571 | 0.61 | 0.5823 | 0.9655 | |
| | No log | 14.0 | 406 | 0.1916 | 0.5842 | 0.555 | 0.5692 | 0.9673 | |
| | No log | 15.0 | 435 | 0.1895 | 0.6335 | 0.605 | 0.6189 | 0.9697 | |
| | No log | 16.0 | 464 | 0.1951 | 0.5880 | 0.635 | 0.6106 | 0.9667 | |
| | No log | 17.0 | 493 | 0.1918 | 0.6324 | 0.585 | 0.6078 | 0.9702 | |
| | 0.0838 | 18.0 | 522 | 0.1957 | 0.6020 | 0.605 | 0.6035 | 0.9699 | |
| | 0.0838 | 19.0 | 551 | 0.1886 | 0.6 | 0.6 | 0.6 | 0.9681 | |
| | 0.0838 | 20.0 | 580 | 0.1992 | 0.6158 | 0.585 | 0.6 | 0.9702 | |
| | 0.0838 | 21.0 | 609 | 0.2043 | 0.625 | 0.6 | 0.6122 | 0.9706 | |
| | 0.0838 | 22.0 | 638 | 0.2110 | 0.6243 | 0.59 | 0.6067 | 0.9707 | |
| | 0.0838 | 23.0 | 667 | 0.2121 | 0.6421 | 0.61 | 0.6256 | 0.9714 | |
| | 0.0838 | 24.0 | 696 | 0.2112 | 0.6455 | 0.61 | 0.6272 | 0.9713 | |
| | 0.0838 | 25.0 | 725 | 0.2150 | 0.6392 | 0.62 | 0.6294 | 0.9711 | |
| | 0.0838 | 26.0 | 754 | 0.2229 | 0.6264 | 0.57 | 0.5969 | 0.9702 | |
| | 0.0838 | 27.0 | 783 | 0.2219 | 0.6339 | 0.58 | 0.6057 | 0.9706 | |
| | 0.0838 | 28.0 | 812 | 0.2239 | 0.6429 | 0.585 | 0.6126 | 0.9707 | |
| | 0.0838 | 29.0 | 841 | 0.2211 | 0.6402 | 0.605 | 0.6221 | 0.9713 | |
| | 0.0838 | 30.0 | 870 | 0.2230 | 0.6364 | 0.595 | 0.6150 | 0.9709 | |
| | 0.0838 | 31.0 | 899 | 0.2244 | 0.6432 | 0.595 | 0.6182 | 0.9709 | |
| | 0.0838 | 32.0 | 928 | 0.2255 | 0.6432 | 0.595 | 0.6182 | 0.9709 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.28.1 |
| - Pytorch 2.0.0+cu118 |
| - Datasets 2.12.0 |
| - Tokenizers 0.13.3 |
|
|
