metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: buburayam2024_indobtwt_7_reprsample
results: []
buburayam2024_indobtwt_7_reprsample
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: 1.9512
- F1 macro: 0.4163
- Weighted: 0.6765
- Balanced accuracy: 0.4952
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 |
|---|---|---|---|---|---|---|
| 1.1941 | 1.0 | 186 | 0.9804 | 0.3927 | 0.6619 | 0.4570 |
| 0.8084 | 2.0 | 372 | 0.9803 | 0.4381 | 0.7056 | 0.4876 |
| 0.3287 | 3.0 | 558 | 1.3391 | 0.3943 | 0.6546 | 0.4784 |
| 0.1292 | 4.0 | 744 | 1.4696 | 0.4297 | 0.6830 | 0.5058 |
| 0.0639 | 5.0 | 930 | 1.8854 | 0.4131 | 0.6647 | 0.4981 |
| 0.0088 | 6.0 | 1116 | 1.9583 | 0.4109 | 0.6704 | 0.4882 |
| 0.0156 | 7.0 | 1302 | 1.9512 | 0.4163 | 0.6765 | 0.4952 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1