metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: classification-hate-speech
results: []
classification-hate-speech
This model is a fine-tuned version of indolem/indobertweet-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3971
- F1 macro: 0.3764
- Weighted: 0.5676
- Balanced accuracy: 0.5202
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 |
|---|---|---|---|---|---|---|
| 1.1881 | 1.0 | 98 | 1.2881 | 0.3632 | 0.5818 | 0.4714 |
| 0.9442 | 2.0 | 196 | 1.6041 | 0.3525 | 0.4977 | 0.5128 |
| 0.5045 | 3.0 | 294 | 2.1271 | 0.3236 | 0.4088 | 0.5040 |
| 0.111 | 4.0 | 392 | 1.9956 | 0.3627 | 0.5579 | 0.5034 |
| 0.0279 | 5.0 | 490 | 2.3665 | 0.3740 | 0.5627 | 0.5203 |
| 0.0203 | 6.0 | 588 | 2.4468 | 0.3662 | 0.5512 | 0.5170 |
| 0.006 | 7.0 | 686 | 2.3971 | 0.3764 | 0.5676 | 0.5202 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1