Update README.md
Browse files
README.md
CHANGED
|
@@ -1,69 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
base_model: Amadeus99/indonesia-election-topic-classification-undersampling-large-2
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
-
model-index:
|
| 7 |
-
- name: final
|
| 8 |
-
results: []
|
| 9 |
-
---
|
| 10 |
-
|
| 11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
-
|
| 14 |
-
# final
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [Amadeus99/indonesia-election-topic-classification-undersampling-large-2](https://huggingface.co/Amadeus99/indonesia-election-topic-classification-undersampling-large-2) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.3415
|
| 19 |
-
- F1 macro: 0.6715
|
| 20 |
-
- Weighted: 0.7528
|
| 21 |
-
- Balanced accuracy: 0.8185
|
| 22 |
-
|
| 23 |
-
## Model description
|
| 24 |
-
|
| 25 |
-
More information needed
|
| 26 |
-
|
| 27 |
-
## Intended uses & limitations
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
-
|
| 37 |
-
### Training hyperparameters
|
| 38 |
-
|
| 39 |
-
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate: 5e-05
|
| 41 |
-
- train_batch_size: 32
|
| 42 |
-
- eval_batch_size: 32
|
| 43 |
-
- seed: 42
|
| 44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
-
- lr_scheduler_type: cosine
|
| 46 |
-
- num_epochs: 10
|
| 47 |
-
|
| 48 |
-
### Training results
|
| 49 |
-
|
| 50 |
-
| Training Loss | Epoch | Step | Validation Loss | F1 macro | Weighted | Balanced accuracy |
|
| 51 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|
|
| 52 |
-
| 0.836 | 1.0 | 39 | 1.0747 | 0.5558 | 0.6819 | 0.7094 |
|
| 53 |
-
| 0.5943 | 2.0 | 78 | 0.8587 | 0.6173 | 0.7475 | 0.8326 |
|
| 54 |
-
| 0.3032 | 3.0 | 117 | 0.6988 | 0.7499 | 0.7999 | 0.8840 |
|
| 55 |
-
| 0.1264 | 4.0 | 156 | 0.8485 | 0.7286 | 0.7915 | 0.8797 |
|
| 56 |
-
| 0.0819 | 5.0 | 195 | 0.9576 | 0.7197 | 0.7812 | 0.8816 |
|
| 57 |
-
| 0.0084 | 6.0 | 234 | 1.0325 | 0.7060 | 0.7874 | 0.8264 |
|
| 58 |
-
| 0.037 | 7.0 | 273 | 1.0728 | 0.7098 | 0.7940 | 0.8261 |
|
| 59 |
-
| 0.0176 | 8.0 | 312 | 1.0690 | 0.7148 | 0.7961 | 0.8350 |
|
| 60 |
-
| 0.011 | 9.0 | 351 | 1.1196 | 0.7133 | 0.7913 | 0.8341 |
|
| 61 |
-
| 0.003 | 10.0 | 390 | 1.1165 | 0.7133 | 0.7913 | 0.8341 |
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
### Framework versions
|
| 65 |
-
|
| 66 |
-
- Transformers 4.41.2
|
| 67 |
-
- Pytorch 2.3.0+cu121
|
| 68 |
-
- Datasets 2.20.0
|
| 69 |
-
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|