metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: nasiuduk2024_indobtwt_7_reprsample_2
results: []
nasiuduk2024_indobtwt_7_reprsample_2
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: 1.8928
- F1 macro: 0.4060
- Weighted: 0.6825
- Balanced accuracy: 0.4640
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 |
|---|---|---|---|---|---|---|
| 1.2738 | 1.0 | 206 | 0.9566 | 0.3914 | 0.6845 | 0.4444 |
| 1.1101 | 2.0 | 412 | 0.9996 | 0.4091 | 0.6819 | 0.4812 |
| 0.3331 | 3.0 | 618 | 1.3851 | 0.4014 | 0.6480 | 0.4958 |
| 0.2889 | 4.0 | 824 | 1.5148 | 0.4136 | 0.6882 | 0.4686 |
| 0.0132 | 5.0 | 1030 | 1.8454 | 0.3969 | 0.6668 | 0.4753 |
| 0.0822 | 6.0 | 1236 | 2.0285 | 0.4064 | 0.6664 | 0.4908 |
| 0.003 | 7.0 | 1442 | 1.8928 | 0.4060 | 0.6825 | 0.4640 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1