metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
fine-tuned-DatasetQAS-TYDI-QA-ID-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
results: []
fine-tuned-DatasetQAS-TYDI-QA-ID-with-indobert-base-uncased-with-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: 1.2740
- Exact Match: 56.0847
- F1: 70.6246
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- 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 |
---|---|---|---|---|---|
6.306 | 0.5 | 19 | 3.7982 | 6.5256 | 20.3655 |
6.306 | 1.0 | 38 | 2.8932 | 14.1093 | 26.0679 |
3.9254 | 1.5 | 57 | 2.4798 | 19.4004 | 32.1438 |
3.9254 | 2.0 | 76 | 2.2955 | 26.1023 | 37.6331 |
3.9254 | 2.5 | 95 | 2.1688 | 26.9841 | 39.2632 |
2.4328 | 3.0 | 114 | 2.0701 | 30.1587 | 41.3438 |
2.4328 | 3.5 | 133 | 1.9789 | 33.1570 | 45.0539 |
2.1127 | 4.0 | 152 | 1.8465 | 37.2134 | 48.9042 |
2.1127 | 4.5 | 171 | 1.7699 | 38.9771 | 50.9760 |
2.1127 | 5.0 | 190 | 1.6885 | 41.0935 | 54.1550 |
1.7875 | 5.5 | 209 | 1.5785 | 45.1499 | 58.6783 |
1.7875 | 6.0 | 228 | 1.4954 | 49.2063 | 62.7869 |
1.7875 | 6.5 | 247 | 1.4186 | 51.8519 | 65.7461 |
1.5267 | 7.0 | 266 | 1.3734 | 53.4392 | 67.6141 |
1.5267 | 7.5 | 285 | 1.3419 | 54.1446 | 68.2563 |
1.3317 | 8.0 | 304 | 1.3116 | 55.5556 | 69.1996 |
1.3317 | 8.5 | 323 | 1.2936 | 56.0847 | 69.9806 |
1.3317 | 9.0 | 342 | 1.2900 | 56.2610 | 70.1634 |
1.2556 | 9.5 | 361 | 1.2771 | 55.7319 | 70.1143 |
1.2556 | 10.0 | 380 | 1.2740 | 56.0847 | 70.6246 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2