metadata
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: indobert-base-uncased-indobert-risalah
results: []
indobert-base-uncased-indobert-risalah
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.3220
- Rouge1: 11.7321
- Rouge2: 3.6066
- Rougel: 8.8112
- Rougelsum: 10.6547
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 8.3353 | 1.0 | 3 | 7.5460 | 22.7692 | 0.1689 | 9.3485 | 15.7127 |
| 7.0296 | 2.0 | 6 | 7.2493 | 22.3096 | 0.0 | 9.382 | 14.236 |
| 6.6103 | 3.0 | 9 | 7.0117 | 12.6826 | 1.8426 | 8.7481 | 11.697 |
| 6.3049 | 4.0 | 12 | 6.7289 | 14.5775 | 1.7535 | 9.8504 | 13.8804 |
| 6.0559 | 5.0 | 15 | 6.5768 | 11.7647 | 2.8142 | 8.5973 | 10.9913 |
| 5.8119 | 6.0 | 18 | 6.4692 | 11.867 | 3.0472 | 8.3364 | 11.2776 |
| 5.6697 | 7.0 | 21 | 6.3714 | 11.6546 | 3.3681 | 8.3696 | 10.6424 |
| 5.5737 | 8.0 | 24 | 6.3220 | 11.7321 | 3.6066 | 8.8112 | 10.6547 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1