|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: custom-ner-model2 |
|
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. --> |
|
|
|
# custom-ner-model2 |
|
|
|
This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2050 |
|
- Precision: 0.8542 |
|
- Recall: 0.8817 |
|
- F1: 0.8677 |
|
- Accuracy: 0.9595 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 105 | 0.5185 | 0.5840 | 0.5484 | 0.5656 | 0.8596 | |
|
| No log | 2.0 | 210 | 0.3212 | 0.7365 | 0.7312 | 0.7338 | 0.9050 | |
|
| No log | 3.0 | 315 | 0.2440 | 0.8123 | 0.8065 | 0.8094 | 0.9389 | |
|
| No log | 4.0 | 420 | 0.2186 | 0.8014 | 0.8100 | 0.8057 | 0.9431 | |
|
| 0.4107 | 5.0 | 525 | 0.1911 | 0.8481 | 0.8602 | 0.8541 | 0.9516 | |
|
| 0.4107 | 6.0 | 630 | 0.1931 | 0.8235 | 0.8530 | 0.8380 | 0.9546 | |
|
| 0.4107 | 7.0 | 735 | 0.1720 | 0.8368 | 0.8638 | 0.8501 | 0.9570 | |
|
| 0.4107 | 8.0 | 840 | 0.1858 | 0.8385 | 0.8746 | 0.8561 | 0.9583 | |
|
| 0.4107 | 9.0 | 945 | 0.1858 | 0.85 | 0.8530 | 0.8515 | 0.9552 | |
|
| 0.0667 | 10.0 | 1050 | 0.1961 | 0.8526 | 0.8710 | 0.8617 | 0.9564 | |
|
| 0.0667 | 11.0 | 1155 | 0.1970 | 0.8537 | 0.8781 | 0.8657 | 0.9589 | |
|
| 0.0667 | 12.0 | 1260 | 0.1865 | 0.8478 | 0.8781 | 0.8627 | 0.9619 | |
|
| 0.0667 | 13.0 | 1365 | 0.1994 | 0.8379 | 0.8710 | 0.8541 | 0.9583 | |
|
| 0.0667 | 14.0 | 1470 | 0.1913 | 0.8507 | 0.8781 | 0.8642 | 0.9613 | |
|
| 0.0274 | 15.0 | 1575 | 0.2064 | 0.8512 | 0.8817 | 0.8662 | 0.9595 | |
|
| 0.0274 | 16.0 | 1680 | 0.2053 | 0.8478 | 0.8781 | 0.8627 | 0.9601 | |
|
| 0.0274 | 17.0 | 1785 | 0.2037 | 0.8576 | 0.8853 | 0.8713 | 0.9601 | |
|
| 0.0274 | 18.0 | 1890 | 0.2056 | 0.8632 | 0.8817 | 0.8723 | 0.9595 | |
|
| 0.0274 | 19.0 | 1995 | 0.2066 | 0.8571 | 0.8817 | 0.8693 | 0.9601 | |
|
| 0.0162 | 20.0 | 2100 | 0.2050 | 0.8542 | 0.8817 | 0.8677 | 0.9595 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
