metadata
license: mit
tags:
- generated_from_trainer
datasets:
- tydiqa
model-index:
- name: indobert-finetune-tydiqa-transfer-indoqa
results: []
indobert-finetune-tydiqa-transfer-indoqa
This model is a fine-tuned version of indolem/indobert-base-uncased on the tydiqa dataset. It achieves the following results on the evaluation set:
- Loss: 2.4999
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
- 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 |
|---|---|---|---|
| 2.919 | 1.0 | 362 | 2.9060 |
| 1.691 | 2.0 | 724 | 2.3301 |
| 1.2875 | 3.0 | 1086 | 2.2975 |
| 1.0796 | 4.0 | 1448 | 2.2565 |
| 0.9246 | 5.0 | 1810 | 2.1829 |
| 0.7948 | 6.0 | 2172 | 2.2602 |
| 0.7139 | 7.0 | 2534 | 2.3786 |
| 0.6345 | 8.0 | 2896 | 2.3917 |
| 0.5932 | 9.0 | 3258 | 2.4541 |
| 0.5576 | 10.0 | 3620 | 2.4999 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1