best_berita_bert_model_fold_4
This model is a fine-tuned version of ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2443
- Accuracy: 0.9700
- Precision: 0.9703
- Recall: 0.9720
- F1: 0.9703
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5455 | 1.0 | 601 | 0.3023 | 0.9217 | 0.9239 | 0.9245 | 0.9220 |
| 0.223 | 2.0 | 1202 | 0.2608 | 0.9517 | 0.9517 | 0.9527 | 0.9521 |
| 0.1061 | 3.0 | 1803 | 0.2175 | 0.9650 | 0.9651 | 0.9668 | 0.9653 |
| 0.0728 | 4.0 | 2404 | 0.3553 | 0.9509 | 0.9524 | 0.9539 | 0.9511 |
| 0.0342 | 5.0 | 3005 | 0.3587 | 0.9584 | 0.9592 | 0.9611 | 0.9585 |
| 0.0209 | 6.0 | 3606 | 0.5005 | 0.9409 | 0.9436 | 0.9446 | 0.9408 |
| 0.0159 | 7.0 | 4207 | 0.2443 | 0.9700 | 0.9703 | 0.9720 | 0.9703 |
| 0.0003 | 8.0 | 4808 | 0.3148 | 0.9659 | 0.9664 | 0.9681 | 0.9661 |
| 0.0 | 9.0 | 5409 | 0.3239 | 0.9650 | 0.9655 | 0.9673 | 0.9652 |
| 0.0 | 10.0 | 6010 | 0.3287 | 0.9659 | 0.9663 | 0.9681 | 0.9661 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.