metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: buburayam2024_indobtwt_7_semimaxunder
results: []
buburayam2024_indobtwt_7_semimaxunder
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: 2.4954
- F1 macro: 0.3816
- Weighted: 0.5658
- Balanced accuracy: 0.5340
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 |
|---|---|---|---|---|---|---|
| 1.5536 | 1.0 | 124 | 1.2828 | 0.3767 | 0.5913 | 0.4981 |
| 0.7422 | 2.0 | 248 | 1.4454 | 0.3589 | 0.5519 | 0.5031 |
| 0.3782 | 3.0 | 372 | 1.6100 | 0.3865 | 0.5978 | 0.5151 |
| 0.1952 | 4.0 | 496 | 1.9570 | 0.3801 | 0.5943 | 0.4926 |
| 0.0398 | 5.0 | 620 | 2.3618 | 0.3680 | 0.5483 | 0.5315 |
| 0.0762 | 6.0 | 744 | 2.3435 | 0.3767 | 0.5805 | 0.5088 |
| 0.0149 | 7.0 | 868 | 2.4954 | 0.3816 | 0.5658 | 0.5340 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1