|
--- |
|
license: apache-2.0 |
|
base_model: indolem/indobertweet-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: classification-hate-speech-2 |
|
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. --> |
|
|
|
# classification-hate-speech-2 |
|
|
|
This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9977 |
|
- F1 macro: 0.4920 |
|
- Weighted: 0.6769 |
|
- Balanced accuracy: 0.6391 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 macro | Weighted | Balanced accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:| |
|
| 1.0988 | 1.0 | 162 | 1.0121 | 0.4279 | 0.6869 | 0.5200 | |
|
| 0.7664 | 2.0 | 324 | 1.1188 | 0.4453 | 0.6992 | 0.5623 | |
|
| 0.2422 | 3.0 | 486 | 1.0945 | 0.5639 | 0.7549 | 0.6537 | |
|
| 0.0549 | 4.0 | 648 | 1.9487 | 0.4743 | 0.6351 | 0.6188 | |
|
| 0.0054 | 5.0 | 810 | 2.0377 | 0.4754 | 0.6601 | 0.6356 | |
|
| 0.0054 | 6.0 | 972 | 1.9811 | 0.4827 | 0.6734 | 0.6329 | |
|
| 0.0047 | 7.0 | 1134 | 1.9977 | 0.4920 | 0.6769 | 0.6391 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
