metadata
license: mit
base_model: indobenchmark/indobert-large-p2
tags:
- generated_from_trainer
model-index:
- name: classification-hate-speech-DE-7-lp2
results: []
classification-hate-speech-DE-7-lp2
This model is a fine-tuned version of indobenchmark/indobert-large-p2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6437
- F1 macro: 0.3699
- Weighted: 0.5424
- Balanced accuracy: 0.5126
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 |
|---|---|---|---|---|---|---|
| 0.0019 | 1.0 | 152 | 3.2735 | 0.3877 | 0.5591 | 0.5253 |
| 0.2688 | 2.0 | 304 | 3.5136 | 0.3514 | 0.5097 | 0.4996 |
| 0.0489 | 3.0 | 456 | 2.9516 | 0.3901 | 0.5839 | 0.5222 |
| 0.0002 | 4.0 | 608 | 3.6103 | 0.3636 | 0.5354 | 0.4996 |
| 0.0003 | 5.0 | 760 | 3.6417 | 0.3695 | 0.5374 | 0.5234 |
| 0.0001 | 6.0 | 912 | 3.6270 | 0.3699 | 0.5424 | 0.5126 |
| 0.0001 | 7.0 | 1064 | 3.6437 | 0.3699 | 0.5424 | 0.5126 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1