|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: spa-eng-pos-tagging-v5 |
|
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. --> |
|
|
|
# spa-eng-pos-tagging-v5 |
|
|
|
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3191 |
|
- Accuracy: 0.9175 |
|
- Precision: 0.9166 |
|
- Recall: 0.8431 |
|
- F1: 0.8483 |
|
- Hamming Loss: 0.0825 |
|
|
|
## 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: 12 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:------------:| |
|
| 1.0059 | 1.0 | 1744 | 0.8050 | 0.7117 | 0.7074 | 0.6280 | 0.6300 | 0.2883 | |
|
| 0.6286 | 2.0 | 3488 | 0.5338 | 0.8024 | 0.8121 | 0.7148 | 0.7270 | 0.1976 | |
|
| 0.4449 | 3.0 | 5232 | 0.4519 | 0.8435 | 0.8300 | 0.7747 | 0.7700 | 0.1565 | |
|
| 0.3647 | 4.0 | 6976 | 0.3849 | 0.8618 | 0.8551 | 0.7900 | 0.7907 | 0.1382 | |
|
| 0.2968 | 5.0 | 8720 | 0.3579 | 0.8772 | 0.8769 | 0.8053 | 0.8088 | 0.1228 | |
|
| 0.255 | 6.0 | 10464 | 0.3298 | 0.8868 | 0.8756 | 0.8179 | 0.8152 | 0.1132 | |
|
| 0.2025 | 7.0 | 12208 | 0.3245 | 0.8941 | 0.8917 | 0.8224 | 0.8251 | 0.1059 | |
|
| 0.176 | 8.0 | 13952 | 0.3324 | 0.8980 | 0.8970 | 0.8260 | 0.8293 | 0.1020 | |
|
| 0.1399 | 9.0 | 15696 | 0.3376 | 0.9038 | 0.9019 | 0.8280 | 0.8331 | 0.0962 | |
|
| 0.1198 | 10.0 | 17440 | 0.3251 | 0.9108 | 0.9075 | 0.8379 | 0.8412 | 0.0892 | |
|
| 0.0973 | 11.0 | 19184 | 0.3191 | 0.9175 | 0.9166 | 0.8431 | 0.8483 | 0.0825 | |
|
| 0.0763 | 12.0 | 20928 | 0.3262 | 0.9192 | 0.9166 | 0.8464 | 0.8501 | 0.0808 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Tokenizers 0.13.3 |
|
|
