|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: Davlan/afro-xlmr-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: afro-xlmr-base-ptbr-MICRO |
|
|
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. --> |
|
|
|
|
|
# afro-xlmr-base-ptbr-MICRO |
|
|
|
|
|
This model is a fine-tuned version of [Davlan/afro-xlmr-base](https://huggingface.co/Davlan/afro-xlmr-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4871 |
|
|
- F1: 0.6841 |
|
|
- Roc Auc: 0.8187 |
|
|
- Accuracy: 0.5946 |
|
|
|
|
|
## 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: 2e-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: cosine |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- num_epochs: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:| |
|
|
| 0.2255 | 1.0 | 728 | 0.2284 | 0.6554 | 0.7738 | 0.6118 | |
|
|
| 0.1591 | 2.0 | 1456 | 0.2288 | 0.6718 | 0.8000 | 0.6183 | |
|
|
| 0.1038 | 3.0 | 2184 | 0.2640 | 0.6774 | 0.8045 | 0.6129 | |
|
|
| 0.0506 | 4.0 | 2912 | 0.3305 | 0.6603 | 0.8168 | 0.5570 | |
|
|
| 0.0459 | 5.0 | 3640 | 0.3809 | 0.6521 | 0.8088 | 0.5505 | |
|
|
| 0.0222 | 6.0 | 4368 | 0.3868 | 0.6463 | 0.7892 | 0.5720 | |
|
|
| 0.0179 | 7.0 | 5096 | 0.4026 | 0.6816 | 0.8139 | 0.6 | |
|
|
| 0.0087 | 8.0 | 5824 | 0.4520 | 0.6694 | 0.8083 | 0.5871 | |
|
|
| 0.0058 | 9.0 | 6552 | 0.4769 | 0.6703 | 0.8048 | 0.5882 | |
|
|
| 0.0064 | 10.0 | 7280 | 0.4871 | 0.6841 | 0.8187 | 0.5946 | |
|
|
| 0.0025 | 11.0 | 8008 | 0.5414 | 0.6611 | 0.8152 | 0.5688 | |
|
|
| 0.0042 | 12.0 | 8736 | 0.5374 | 0.6778 | 0.8154 | 0.5925 | |
|
|
| 0.0013 | 13.0 | 9464 | 0.5331 | 0.6744 | 0.8081 | 0.5968 | |
|
|
| 0.0048 | 14.0 | 10192 | 0.5573 | 0.6760 | 0.8141 | 0.5860 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
