metadata
license: mit
base_model: indobenchmark/indobert-base-p1
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Zidan_model_output_v4
results: []
Zidan_model_output_v4
This model is a fine-tuned version of indobenchmark/indobert-base-p1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7156
- Accuracy: 0.7078
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: 1e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 220 | 0.9842 | 0.5909 |
No log | 2.0 | 440 | 0.8935 | 0.5714 |
0.9631 | 3.0 | 660 | 0.8081 | 0.6169 |
0.9631 | 4.0 | 880 | 0.7819 | 0.6299 |
0.7467 | 5.0 | 1100 | 0.7760 | 0.6299 |
0.7467 | 6.0 | 1320 | 0.7601 | 0.6558 |
0.6817 | 7.0 | 1540 | 0.7578 | 0.6494 |
0.6817 | 8.0 | 1760 | 0.7359 | 0.6753 |
0.6817 | 9.0 | 1980 | 0.7643 | 0.6494 |
0.621 | 10.0 | 2200 | 0.7156 | 0.7078 |
0.621 | 11.0 | 2420 | 0.7310 | 0.6948 |
0.576 | 12.0 | 2640 | 0.7199 | 0.7078 |
0.576 | 13.0 | 2860 | 0.7199 | 0.7143 |
0.5598 | 14.0 | 3080 | 0.7313 | 0.7013 |
0.5598 | 15.0 | 3300 | 0.7253 | 0.7013 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1