|
--- |
|
license: apache-2.0 |
|
base_model: indolem/indobertweet-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: nasiuduk2024_indobtwt_7_u_o |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# nasiuduk2024_indobtwt_7_u_o |
|
|
|
This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.5305 |
|
- F1 macro: 0.3802 |
|
- Weighted: 0.5879 |
|
- Balanced accuracy: 0.5179 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:| |
|
| 1.4191 | 1.0 | 162 | 1.3702 | 0.3358 | 0.5319 | 0.4757 | |
|
| 0.6762 | 2.0 | 324 | 1.3777 | 0.3590 | 0.5807 | 0.4857 | |
|
| 0.4675 | 3.0 | 486 | 1.5368 | 0.4526 | 0.5879 | 0.5707 | |
|
| 0.1559 | 4.0 | 648 | 2.3060 | 0.3595 | 0.5416 | 0.4922 | |
|
| 0.0104 | 5.0 | 810 | 2.2064 | 0.3881 | 0.6050 | 0.5170 | |
|
| 0.0076 | 6.0 | 972 | 2.4857 | 0.3849 | 0.5892 | 0.5210 | |
|
| 0.0025 | 7.0 | 1134 | 2.5305 | 0.3802 | 0.5879 | 0.5179 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
