|
--- |
|
datasets: |
|
- antoniomenezes/go_emotions_ptbr |
|
language: |
|
- en |
|
metrics: |
|
- f1 |
|
tags: |
|
- generated_from_trainer |
|
--- |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-5 |
|
- 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: 3 |
|
- mixed_precision_training: Native AMP |
|
- warmup_ratio: 0.1 |
|
- weight_decay=1e-2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Validation Loss | F1 | F1 Macro | |
|
|:---------------:|:-----:|:-----------------:|:--------:|:--------:| |
|
| 1.238700 | 1.0 | 1.135360 | 0.238667 | 0.106812 | |
|
| 1.084500 | 2.0 | 1.103713 | 0.234572 | 0.105525 | |
|
| 1.009300 | 3.0 | 1.099275 | 0.290353 | 0.162856 | |
|
| 0.929300 | 4.0 | 1.159663 | 0.334926 | 0.208453 | |
