Zidan_model_output_80_10_10_v2
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: 1.3927
- Accuracy: 0.7909
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: 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 | 0.6245 | 0.7455 |
No log | 2.0 | 440 | 0.6290 | 0.7909 |
0.7193 | 3.0 | 660 | 0.8884 | 0.7818 |
0.7193 | 4.0 | 880 | 1.1259 | 0.7364 |
0.3358 | 5.0 | 1100 | 1.3432 | 0.7455 |
0.3358 | 6.0 | 1320 | 1.3727 | 0.7636 |
0.0865 | 7.0 | 1540 | 1.4226 | 0.7727 |
0.0865 | 8.0 | 1760 | 1.3888 | 0.7909 |
0.0865 | 9.0 | 1980 | 1.3470 | 0.7909 |
0.0503 | 10.0 | 2200 | 1.3517 | 0.7818 |
0.0503 | 11.0 | 2420 | 1.3297 | 0.7909 |
0.0348 | 12.0 | 2640 | 1.3231 | 0.8182 |
0.0348 | 13.0 | 2860 | 1.3674 | 0.7818 |
0.0296 | 14.0 | 3080 | 1.3539 | 0.8091 |
0.0296 | 15.0 | 3300 | 1.3927 | 0.7909 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2