<!-- 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-IDK-MRC-with-indobert-base-uncased-without-ITTL
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: 1.3953
- Exact Match: 57.0681
- F1: 60.6263
- Precision: 60.5659
- Recall: 61.6128
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 4.9796 | 0.49 | 72 | 2.7419 | 5.8901 | 10.4346 | 9.5399 | 14.3017 |
| 2.9811 | 0.98 | 144 | 1.9199 | 49.6073 | 52.8796 | 52.8599 | 52.9123 |
| 2.053 | 1.47 | 216 | 1.7355 | 49.2147 | 53.3398 | 53.1633 | 54.0246 |
| 1.9358 | 1.96 | 288 | 1.6560 | 49.6073 | 55.0960 | 54.6997 | 56.6932 |
| 1.6543 | 2.45 | 360 | 1.5563 | 53.5340 | 57.7517 | 57.4674 | 59.0722 |
| 1.6505 | 2.94 | 432 | 1.4367 | 56.6754 | 60.2111 | 60.1301 | 61.1952 |
| 1.4604 | 3.43 | 504 | 1.4737 | 54.3194 | 58.1394 | 58.0354 | 59.2380 |
| 1.4891 | 3.92 | 576 | 1.3953 | 57.0681 | 60.6263 | 60.5659 | 61.6128 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
