<!-- 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. -->
spa-eng-pos-tagging-v6
This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3128
- Accuracy: 0.9056
- Precision: 0.9032
- Recall: 0.8293
- F1: 0.8345
- Hamming Loss: 0.0944
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 14
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming Loss |
|---|---|---|---|---|---|---|---|---|
| 1.0141 | 1.0 | 1744 | 0.7804 | 0.7158 | 0.7328 | 0.6183 | 0.6345 | 0.2842 |
| 0.6292 | 2.0 | 3488 | 0.5384 | 0.7973 | 0.8111 | 0.7029 | 0.7213 | 0.2027 |
| 0.4438 | 3.0 | 5232 | 0.4236 | 0.8462 | 0.8346 | 0.7762 | 0.7732 | 0.1538 |
| 0.3626 | 4.0 | 6976 | 0.3856 | 0.8651 | 0.8524 | 0.7933 | 0.7903 | 0.1349 |
| 0.3141 | 5.0 | 8720 | 0.3697 | 0.8712 | 0.8688 | 0.7998 | 0.8028 | 0.1288 |
| 0.2575 | 6.0 | 10464 | 0.3689 | 0.8751 | 0.8758 | 0.8003 | 0.8058 | 0.1249 |
| 0.2117 | 7.0 | 12208 | 0.3329 | 0.8890 | 0.8832 | 0.8169 | 0.8184 | 0.1110 |
| 0.1864 | 8.0 | 13952 | 0.3235 | 0.9010 | 0.8946 | 0.8278 | 0.8293 | 0.0990 |
| 0.1555 | 9.0 | 15696 | 0.3128 | 0.9056 | 0.9032 | 0.8293 | 0.8345 | 0.0944 |
| 0.1322 | 10.0 | 17440 | 0.3311 | 0.9088 | 0.9010 | 0.8376 | 0.8377 | 0.0912 |
| 0.1111 | 11.0 | 19184 | 0.3394 | 0.9101 | 0.9081 | 0.8319 | 0.8383 | 0.0899 |
| 0.0874 | 12.0 | 20928 | 0.3472 | 0.9148 | 0.9100 | 0.8407 | 0.8440 | 0.0852 |
| 0.0659 | 13.0 | 22672 | 0.3635 | 0.9131 | 0.9072 | 0.8400 | 0.8422 | 0.0869 |
| 0.0608 | 14.0 | 24416 | 0.3560 | 0.9187 | 0.9140 | 0.8452 | 0.8482 | 0.0813 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3
