|
--- |
|
base_model: dccuchile/bert-base-spanish-wwm-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: roberta-academic |
|
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. --> |
|
|
|
# roberta-academic |
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1070 |
|
- Accuracy: 0.9692 |
|
- F1: 0.9687 |
|
- Precision: 0.9692 |
|
- Recall: 0.9692 |
|
|
|
## 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: 34 |
|
- eval_batch_size: 34 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.3143 | 1.0 | 10831 | 0.2892 | 0.9106 | 0.9070 | 0.9137 | 0.9106 | |
|
| 0.2042 | 2.0 | 21662 | 0.1880 | 0.9388 | 0.9366 | 0.9415 | 0.9388 | |
|
| 0.121 | 3.0 | 32493 | 0.1437 | 0.9552 | 0.9545 | 0.9560 | 0.9552 | |
|
| 0.0843 | 4.0 | 43324 | 0.1152 | 0.9655 | 0.9651 | 0.9658 | 0.9655 | |
|
| 0.049 | 5.0 | 54155 | 0.1070 | 0.9692 | 0.9687 | 0.9692 | 0.9692 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
