metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Zidan_model_output_80_10_10
results: []
Zidan_model_output_80_10_10
This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8090
- Accuracy: 0.7273
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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 | 0.6488 | 0.7455 |
No log | 2.0 | 440 | 0.7206 | 0.7364 |
0.6877 | 3.0 | 660 | 0.9170 | 0.7818 |
0.6877 | 4.0 | 880 | 1.2220 | 0.7455 |
0.2623 | 5.0 | 1100 | 1.6100 | 0.7364 |
0.2623 | 6.0 | 1320 | 1.8847 | 0.6818 |
0.0832 | 7.0 | 1540 | 1.8377 | 0.6909 |
0.0832 | 8.0 | 1760 | 1.6139 | 0.7182 |
0.0832 | 9.0 | 1980 | 1.9268 | 0.7 |
0.0502 | 10.0 | 2200 | 1.8679 | 0.7182 |
0.0502 | 11.0 | 2420 | 1.8020 | 0.7364 |
0.0311 | 12.0 | 2640 | 1.7905 | 0.7273 |
0.0311 | 13.0 | 2860 | 1.7716 | 0.7364 |
0.0252 | 14.0 | 3080 | 1.8070 | 0.7273 |
0.0252 | 15.0 | 3300 | 1.8090 | 0.7273 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1