|
--- |
|
license: mit |
|
base_model: indolem/indobert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: sv1 |
|
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. --> |
|
|
|
# sv1 |
|
|
|
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3325 |
|
- F1 macro: 0.3954 |
|
- Weighted: 0.5529 |
|
- Balanced accuracy: 0.5398 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:| |
|
| 1.5316 | 1.0 | 154 | 1.5495 | 0.2252 | 0.3650 | 0.3588 | |
|
| 1.2625 | 2.0 | 308 | 1.4130 | 0.3021 | 0.4392 | 0.4393 | |
|
| 0.8381 | 3.0 | 462 | 1.4654 | 0.3616 | 0.5320 | 0.4578 | |
|
| 0.6723 | 4.0 | 616 | 1.4752 | 0.4154 | 0.5946 | 0.5237 | |
|
| 0.3447 | 5.0 | 770 | 1.6081 | 0.4057 | 0.6112 | 0.5217 | |
|
| 0.2433 | 6.0 | 924 | 2.2897 | 0.4023 | 0.5488 | 0.5463 | |
|
| 0.0404 | 7.0 | 1078 | 2.3325 | 0.3954 | 0.5529 | 0.5398 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|