<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuned-DatasetQAS-Squad-ID-with-indobert-large-p2-with-ITTL-with-freeze-LR-1e-05
This model is a fine-tuned version of indobenchmark/indobert-large-p2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5574
- Exact Match: 47.6371
- F1: 63.8727
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- 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 |
---|---|---|---|---|---|
1.8897 | 0.5 | 463 | 1.7933 | 39.8083 | 55.8203 |
1.6804 | 1.0 | 926 | 1.6326 | 44.1978 | 60.8018 |
1.5163 | 1.5 | 1389 | 1.5762 | 45.0303 | 60.8666 |
1.4687 | 2.0 | 1852 | 1.5214 | 46.6616 | 63.1627 |
1.3234 | 2.5 | 2315 | 1.5170 | 46.7793 | 63.1629 |
1.3221 | 3.0 | 2778 | 1.5037 | 47.2418 | 63.9784 |
1.1877 | 3.5 | 3241 | 1.5265 | 47.4773 | 63.7942 |
1.2091 | 4.0 | 3704 | 1.5262 | 47.3764 | 63.8722 |
1.0894 | 4.5 | 4167 | 1.5574 | 47.6371 | 63.8727 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2