fine-tuned-DatasetQAS-Squad-ID-with-indobert-base-uncased-without-ITTL-without-freeze-LR-1e-05
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5081
- Exact Match: 48.0441
- F1: 64.5121
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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | Exact Match | F1 |
|---|---|---|---|---|---|
| 2.0164 | 0.5 | 463 | 1.8536 | 39.4212 | 54.9381 |
| 1.8356 | 1.0 | 926 | 1.6789 | 43.3667 | 59.1353 |
| 1.6492 | 1.5 | 1389 | 1.6111 | 45.0324 | 61.1553 |
| 1.6051 | 2.0 | 1852 | 1.5722 | 45.5119 | 62.1336 |
| 1.4925 | 2.5 | 2315 | 1.5679 | 46.5130 | 63.6738 |
| 1.5049 | 3.0 | 2778 | 1.5260 | 47.2197 | 64.2953 |
| 1.3868 | 3.5 | 3241 | 1.5213 | 47.6571 | 64.6843 |
| 1.3574 | 4.0 | 3704 | 1.5065 | 47.8758 | 64.3476 |
| 1.3199 | 4.5 | 4167 | 1.5169 | 47.6403 | 64.4273 |
| 1.3024 | 5.0 | 4630 | 1.5081 | 48.0441 | 64.5121 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
- Downloads last month
- 4