|
---
|
|
base_model: dccuchile/bert-base-spanish-wwm-cased
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- accuracy
|
|
- f1
|
|
model-index:
|
|
- name: ABL_trad_2e
|
|
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. -->
|
|
|
|
# ABL_trad_2e
|
|
|
|
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: 0.6197
|
|
- Accuracy: 0.7492
|
|
- F1: 0.7480
|
|
|
|
## 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: 1e-05
|
|
- train_batch_size: 32
|
|
- 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 | F1 |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
|
| 0.8297 | 1.0 | 2342 | 0.8006 | 0.6318 | 0.6304 |
|
|
| 0.7468 | 2.0 | 4684 | 0.7369 | 0.6706 | 0.6685 |
|
|
| 0.6876 | 3.0 | 7026 | 0.6962 | 0.6913 | 0.6901 |
|
|
| 0.6548 | 4.0 | 9368 | 0.6739 | 0.7015 | 0.7009 |
|
|
| 0.61 | 5.0 | 11710 | 0.6597 | 0.7134 | 0.7111 |
|
|
| 0.5775 | 6.0 | 14052 | 0.6422 | 0.7219 | 0.7203 |
|
|
| 0.5592 | 7.0 | 16394 | 0.6298 | 0.7279 | 0.7264 |
|
|
| 0.5441 | 8.0 | 18736 | 0.6221 | 0.7346 | 0.7339 |
|
|
| 0.5191 | 9.0 | 21078 | 0.6182 | 0.7389 | 0.7373 |
|
|
| 0.4999 | 10.0 | 23420 | 0.6229 | 0.7442 | 0.7423 |
|
|
| 0.4797 | 11.0 | 25762 | 0.6259 | 0.7436 | 0.7426 |
|
|
| 0.4584 | 12.0 | 28104 | 0.6197 | 0.7492 | 0.7480 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.37.2
|
|
- Pytorch 2.1.0+cu121
|
|
- Datasets 2.16.1
|
|
- Tokenizers 0.15.1
|
|
|
