|
---
|
|
base_model: dccuchile/bert-base-spanish-wwm-cased
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
- f1
|
|
model-index:
|
|
- name: FNST_trad_2f
|
|
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. -->
|
|
|
|
# FNST_trad_2f
|
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.8298
|
|
- Accuracy: 0.6851
|
|
- F1: 0.6776
|
|
|
|
## 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-06
|
|
- 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: 12
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
|
| 0.9535 | 1.0 | 3125 | 0.9298 | 0.5950 | 0.5843 |
|
|
| 0.8929 | 2.0 | 6250 | 0.8737 | 0.6295 | 0.6198 |
|
|
| 0.8234 | 3.0 | 9375 | 0.8473 | 0.6410 | 0.6317 |
|
|
| 0.7857 | 4.0 | 12500 | 0.8264 | 0.6522 | 0.6455 |
|
|
| 0.7489 | 5.0 | 15625 | 0.8219 | 0.6506 | 0.6439 |
|
|
| 0.7072 | 6.0 | 18750 | 0.8138 | 0.6601 | 0.6546 |
|
|
| 0.7025 | 7.0 | 21875 | 0.8109 | 0.6641 | 0.6607 |
|
|
| 0.6646 | 8.0 | 25000 | 0.8130 | 0.6698 | 0.6643 |
|
|
| 0.6557 | 9.0 | 28125 | 0.8014 | 0.6745 | 0.6679 |
|
|
| 0.6114 | 10.0 | 31250 | 0.8153 | 0.6745 | 0.6681 |
|
|
| 0.6065 | 11.0 | 34375 | 0.8258 | 0.6815 | 0.6738 |
|
|
| 0.5733 | 12.0 | 37500 | 0.8298 | 0.6851 | 0.6776 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.37.2
|
|
- Pytorch 2.1.0+cu121
|
|
- Datasets 2.16.1
|
|
- Tokenizers 0.15.1
|
|
|
