|
--- |
|
base_model: dccuchile/bert-base-spanish-wwm-cased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-base-spanish-wwm-cased-2023-11-13-22-45 |
|
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-cased-2023-11-13-22-45 |
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9028 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.5609 | 0.59 | 500 | 1.4228 | |
|
| 1.3889 | 1.19 | 1000 | 1.2819 | |
|
| 1.2838 | 1.78 | 1500 | 1.1785 | |
|
| 1.2015 | 2.38 | 2000 | 1.1307 | |
|
| 1.1542 | 2.97 | 2500 | 1.0848 | |
|
| 1.1251 | 3.56 | 3000 | 1.0549 | |
|
| 1.0841 | 4.16 | 3500 | 1.0211 | |
|
| 1.0549 | 4.75 | 4000 | 0.9953 | |
|
| 1.049 | 5.34 | 4500 | 0.9839 | |
|
| 0.9989 | 5.94 | 5000 | 0.9600 | |
|
| 0.9805 | 6.53 | 5500 | 0.9512 | |
|
| 0.9366 | 7.13 | 6000 | 0.9383 | |
|
| 0.9645 | 7.72 | 6500 | 0.9214 | |
|
| 0.9623 | 8.31 | 7000 | 0.9157 | |
|
| 0.9237 | 8.91 | 7500 | 0.8967 | |
|
| 0.9507 | 9.5 | 8000 | 0.9003 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
