|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- hate_speech_filipino |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scenario-teacher-data-hate_speech_filipino-model-xlm-roberta-base |
|
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. --> |
|
|
|
# scenario-teacher-data-hate_speech_filipino-model-xlm-roberta-base |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the hate_speech_filipino dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0437 |
|
- Accuracy: 0.7817 |
|
- F1: 0.7687 |
|
|
|
## 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: 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: 6969 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.32 | 100 | 0.5923 | 0.6966 | 0.7200 | |
|
| No log | 0.64 | 200 | 0.5214 | 0.7450 | 0.7202 | |
|
| No log | 0.96 | 300 | 0.5052 | 0.7554 | 0.7372 | |
|
| No log | 1.28 | 400 | 0.5106 | 0.7649 | 0.7442 | |
|
| 0.5444 | 1.6 | 500 | 0.5499 | 0.7559 | 0.7564 | |
|
| 0.5444 | 1.92 | 600 | 0.4998 | 0.7566 | 0.6862 | |
|
| 0.5444 | 2.24 | 700 | 0.5269 | 0.7760 | 0.7653 | |
|
| 0.5444 | 2.56 | 800 | 0.5129 | 0.7836 | 0.7716 | |
|
| 0.5444 | 2.88 | 900 | 0.5132 | 0.7668 | 0.7070 | |
|
| 0.3971 | 3.19 | 1000 | 0.5680 | 0.7805 | 0.7510 | |
|
| 0.3971 | 3.51 | 1100 | 0.5999 | 0.7781 | 0.7696 | |
|
| 0.3971 | 3.83 | 1200 | 0.6097 | 0.7632 | 0.7674 | |
|
| 0.3971 | 4.15 | 1300 | 0.6476 | 0.7795 | 0.7573 | |
|
| 0.3971 | 4.47 | 1400 | 0.6461 | 0.7843 | 0.7629 | |
|
| 0.2704 | 4.79 | 1500 | 0.6329 | 0.7786 | 0.7634 | |
|
| 0.2704 | 5.11 | 1600 | 0.7783 | 0.7729 | 0.7396 | |
|
| 0.2704 | 5.43 | 1700 | 0.6963 | 0.7750 | 0.7285 | |
|
| 0.2704 | 5.75 | 1800 | 0.7857 | 0.7892 | 0.7680 | |
|
| 0.2704 | 6.07 | 1900 | 0.6921 | 0.7762 | 0.7655 | |
|
| 0.215 | 6.39 | 2000 | 0.7196 | 0.7722 | 0.7499 | |
|
| 0.215 | 6.71 | 2100 | 1.0259 | 0.7691 | 0.7671 | |
|
| 0.215 | 7.03 | 2200 | 1.1496 | 0.7767 | 0.7640 | |
|
| 0.215 | 7.35 | 2300 | 1.0437 | 0.7817 | 0.7687 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
