|
--- |
|
base_model: dccuchile/bert-base-spanish-wwm-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-spanish-wwm-uncased-ner |
|
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. --> |
|
|
|
# bert-base-spanish-wwm-uncased-ner |
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3905 |
|
- Precision: 0.8768 |
|
- Recall: 0.9067 |
|
- F1: 0.8915 |
|
- Accuracy: 0.9376 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 280 | 0.2690 | 0.8236 | 0.8578 | 0.8403 | 0.9268 | |
|
| 0.3996 | 2.0 | 560 | 0.2917 | 0.8116 | 0.8681 | 0.8389 | 0.9180 | |
|
| 0.3996 | 3.0 | 840 | 0.2715 | 0.8495 | 0.8696 | 0.8594 | 0.9319 | |
|
| 0.118 | 4.0 | 1120 | 0.2914 | 0.8567 | 0.9037 | 0.8796 | 0.9370 | |
|
| 0.118 | 5.0 | 1400 | 0.3040 | 0.8454 | 0.8993 | 0.8715 | 0.9330 | |
|
| 0.0608 | 6.0 | 1680 | 0.2979 | 0.8631 | 0.8963 | 0.8794 | 0.9359 | |
|
| 0.0608 | 7.0 | 1960 | 0.3376 | 0.8653 | 0.8948 | 0.8798 | 0.9322 | |
|
| 0.0353 | 8.0 | 2240 | 0.3283 | 0.8622 | 0.9081 | 0.8846 | 0.9370 | |
|
| 0.0236 | 9.0 | 2520 | 0.3584 | 0.8575 | 0.9007 | 0.8786 | 0.9351 | |
|
| 0.0236 | 10.0 | 2800 | 0.3891 | 0.8813 | 0.9022 | 0.8917 | 0.9346 | |
|
| 0.0155 | 11.0 | 3080 | 0.3678 | 0.8764 | 0.9037 | 0.8899 | 0.9381 | |
|
| 0.0155 | 12.0 | 3360 | 0.3736 | 0.8759 | 0.9096 | 0.8924 | 0.9386 | |
|
| 0.0123 | 13.0 | 3640 | 0.4030 | 0.8721 | 0.8993 | 0.8855 | 0.9349 | |
|
| 0.0123 | 14.0 | 3920 | 0.3890 | 0.8768 | 0.9067 | 0.8915 | 0.9373 | |
|
| 0.0123 | 15.0 | 4200 | 0.3905 | 0.8768 | 0.9067 | 0.8915 | 0.9376 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
