my-nergrit-model
This model is a fine-tuned version of indolem/indobert-base-uncased on the id_nergrit_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1792
- Precision: 0.8166
- Recall: 0.8424
- F1: 0.8293
- Accuracy: 0.9476
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4887 | 1.0 | 784 | 0.1891 | 0.7908 | 0.8305 | 0.8102 | 0.9427 |
| 0.1624 | 2.0 | 1568 | 0.1792 | 0.8166 | 0.8424 | 0.8293 | 0.9476 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 192
Model tree for bryanahusna/my-nergrit-model
Base model
indolem/indobert-base-uncasedDataset used to train bryanahusna/my-nergrit-model
Evaluation results
- Precision on id_nergrit_corpusvalidation set self-reported0.817
- Recall on id_nergrit_corpusvalidation set self-reported0.842
- F1 on id_nergrit_corpusvalidation set self-reported0.829
- Accuracy on id_nergrit_corpusvalidation set self-reported0.948