metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: sv1
results: []
sv1
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: 3.0499
- F1 macro: 0.3977
- Weighted: 0.6145
- Balanced accuracy: 0.5186
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: 14
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 macro | Weighted | Balanced accuracy |
|---|---|---|---|---|---|---|
| 1.2727 | 1.0 | 154 | 1.2213 | 0.3786 | 0.5827 | 0.4776 |
| 0.8729 | 2.0 | 308 | 1.4909 | 0.3204 | 0.5293 | 0.4454 |
| 0.3299 | 3.0 | 462 | 1.6163 | 0.3885 | 0.5956 | 0.5035 |
| 0.2233 | 4.0 | 616 | 1.9917 | 0.3709 | 0.5977 | 0.4661 |
| 0.1323 | 5.0 | 770 | 2.5400 | 0.3797 | 0.5718 | 0.4903 |
| 0.0014 | 6.0 | 924 | 3.0973 | 0.3555 | 0.5244 | 0.5040 |
| 0.0012 | 7.0 | 1078 | 2.8258 | 0.3961 | 0.6119 | 0.5142 |
| 0.0013 | 8.0 | 1232 | 2.8277 | 0.3864 | 0.6097 | 0.5067 |
| 0.0006 | 9.0 | 1386 | 2.9388 | 0.3911 | 0.6087 | 0.5121 |
| 0.0006 | 10.0 | 1540 | 2.9096 | 0.4015 | 0.6235 | 0.5205 |
| 0.0004 | 11.0 | 1694 | 3.2002 | 0.3856 | 0.5798 | 0.5138 |
| 0.0005 | 12.0 | 1848 | 3.1226 | 0.3945 | 0.6052 | 0.5185 |
| 0.0004 | 13.0 | 2002 | 3.0566 | 0.3968 | 0.6123 | 0.5181 |
| 0.0004 | 14.0 | 2156 | 3.0499 | 0.3977 | 0.6145 | 0.5186 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1