metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
fine-tuned-DatasetQAS-Squad-ID-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
results: []
fine-tuned-DatasetQAS-Squad-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: 1.5296
- Exact Match: 48.5657
- F1: 64.5763
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- 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 |
|---|---|---|---|---|---|
| 2.0185 | 0.5 | 463 | 1.8556 | 39.4128 | 54.9486 |
| 1.8481 | 1.0 | 926 | 1.6794 | 43.1985 | 58.7955 |
| 1.6413 | 1.5 | 1389 | 1.6081 | 45.2091 | 61.6638 |
| 1.611 | 2.0 | 1852 | 1.5670 | 45.9241 | 62.7351 |
| 1.4929 | 2.5 | 2315 | 1.5571 | 46.5298 | 63.3878 |
| 1.5119 | 3.0 | 2778 | 1.5222 | 47.2785 | 64.2211 |
| 1.3955 | 3.5 | 3241 | 1.5285 | 47.6235 | 64.2546 |
| 1.3643 | 4.0 | 3704 | 1.5133 | 47.9179 | 64.1430 |
| 1.3277 | 4.5 | 4167 | 1.5223 | 47.8927 | 64.3061 |
| 1.3058 | 5.0 | 4630 | 1.5126 | 48.6498 | 64.5757 |
| 1.2847 | 5.5 | 5093 | 1.5154 | 48.4479 | 64.5972 |
| 1.1984 | 6.0 | 5556 | 1.5289 | 48.4815 | 64.4181 |
| 1.1817 | 6.5 | 6019 | 1.5277 | 48.4395 | 64.7923 |
| 1.2203 | 7.0 | 6482 | 1.5134 | 48.5404 | 64.5935 |
| 1.1492 | 7.5 | 6945 | 1.5412 | 48.6330 | 64.6696 |
| 1.1567 | 8.0 | 7408 | 1.5296 | 48.5657 | 64.5763 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2