<!-- 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. -->
modelBeto6
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1808
- Precision: 0.6219
- Recall: 0.6545
- F1: 0.6378
- Accuracy: 0.9737
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: 6e-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 | 0.2309 | 0.0 | 0.0 | 0.0 | 0.9440 |
| No log | 2.0 | 58 | 0.2034 | 0.0 | 0.0 | 0.0 | 0.9440 |
| No log | 3.0 | 87 | 0.1685 | 0.1429 | 0.0157 | 0.0283 | 0.9476 |
| No log | 4.0 | 116 | 0.1425 | 0.3034 | 0.1414 | 0.1929 | 0.9546 |
| No log | 5.0 | 145 | 0.1285 | 0.3802 | 0.2408 | 0.2949 | 0.9589 |
| No log | 6.0 | 174 | 0.1283 | 0.5922 | 0.3194 | 0.4150 | 0.9696 |
| No log | 7.0 | 203 | 0.1337 | 0.5630 | 0.3979 | 0.4663 | 0.9715 |
| No log | 8.0 | 232 | 0.1184 | 0.5505 | 0.6283 | 0.5868 | 0.9686 |
| No log | 9.0 | 261 | 0.1308 | 0.5882 | 0.5759 | 0.5820 | 0.9729 |
| No log | 10.0 | 290 | 0.1329 | 0.5989 | 0.5550 | 0.5761 | 0.9729 |
| No log | 11.0 | 319 | 0.1549 | 0.6781 | 0.5183 | 0.5875 | 0.9742 |
| No log | 12.0 | 348 | 0.1578 | 0.6221 | 0.5602 | 0.5895 | 0.9732 |
| No log | 13.0 | 377 | 0.1505 | 0.6117 | 0.6021 | 0.6069 | 0.9716 |
| No log | 14.0 | 406 | 0.1671 | 0.6412 | 0.5707 | 0.6039 | 0.9729 |
| No log | 15.0 | 435 | 0.1684 | 0.5902 | 0.5654 | 0.5775 | 0.9710 |
| No log | 16.0 | 464 | 0.1707 | 0.6216 | 0.6021 | 0.6117 | 0.9727 |
| No log | 17.0 | 493 | 0.1715 | 0.6453 | 0.5812 | 0.6116 | 0.9737 |
| 0.0738 | 18.0 | 522 | 0.1729 | 0.5734 | 0.6545 | 0.6112 | 0.9701 |
| 0.0738 | 19.0 | 551 | 0.1815 | 0.5990 | 0.6021 | 0.6005 | 0.9716 |
| 0.0738 | 20.0 | 580 | 0.1746 | 0.6354 | 0.6387 | 0.6371 | 0.9732 |
| 0.0738 | 21.0 | 609 | 0.1654 | 0.6686 | 0.5916 | 0.6278 | 0.9749 |
| 0.0738 | 22.0 | 638 | 0.1678 | 0.6359 | 0.6492 | 0.6425 | 0.9741 |
| 0.0738 | 23.0 | 667 | 0.1704 | 0.6218 | 0.6283 | 0.625 | 0.9742 |
| 0.0738 | 24.0 | 696 | 0.1746 | 0.6685 | 0.6440 | 0.6560 | 0.9747 |
| 0.0738 | 25.0 | 725 | 0.1772 | 0.6224 | 0.6387 | 0.6305 | 0.9739 |
| 0.0738 | 26.0 | 754 | 0.1792 | 0.6484 | 0.6178 | 0.6327 | 0.9741 |
| 0.0738 | 27.0 | 783 | 0.1788 | 0.6383 | 0.6283 | 0.6332 | 0.9741 |
| 0.0738 | 28.0 | 812 | 0.1802 | 0.6281 | 0.6545 | 0.6410 | 0.9741 |
| 0.0738 | 29.0 | 841 | 0.1803 | 0.6443 | 0.6545 | 0.6494 | 0.9747 |
| 0.0738 | 30.0 | 870 | 0.1804 | 0.6495 | 0.6597 | 0.6545 | 0.9749 |
| 0.0738 | 31.0 | 899 | 0.1805 | 0.6443 | 0.6545 | 0.6494 | 0.9746 |
| 0.0738 | 32.0 | 928 | 0.1808 | 0.6219 | 0.6545 | 0.6378 | 0.9737 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
