| --- |
| tags: |
| - summarization |
| - generated_from_trainer |
| model-index: |
| - name: led-risalah_data_v7 |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # led-risalah_data_v7 |
|
|
| This model was trained from scratch on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.8807 |
| - Rouge1 Precision: 0.6909 |
| - Rouge1 Recall: 0.1722 |
| - Rouge1 Fmeasure: 0.2753 |
|
|
| ## 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: 1 |
| - eval_batch_size: 1 |
| - 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 | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall | |
| |:-------------:|:-----:|:----:|:---------------:|:---------------:|:----------------:|:-------------:| |
| | 1.7531 | 1.0 | 70 | 1.7163 | 0.2707 | 0.6515 | 0.1714 | |
| | 1.4557 | 2.0 | 140 | 1.6342 | 0.2716 | 0.6745 | 0.1705 | |
| | 1.132 | 3.0 | 210 | 1.6420 | 0.2784 | 0.686 | 0.175 | |
| | 1.0552 | 4.0 | 280 | 1.6372 | 0.2828 | 0.6879 | 0.1786 | |
| | 1.0587 | 5.0 | 350 | 1.6587 | 0.2595 | 0.6314 | 0.1637 | |
| | 0.7863 | 6.0 | 420 | 1.6967 | 0.2871 | 0.7038 | 0.181 | |
| | 0.4577 | 7.0 | 490 | 1.7779 | 0.2717 | 0.6783 | 0.1703 | |
| | 0.6156 | 8.0 | 560 | 1.7964 | 0.2637 | 0.6474 | 0.1659 | |
| | 0.593 | 9.0 | 630 | 1.8699 | 0.2747 | 0.6797 | 0.1728 | |
| | 0.4265 | 10.0 | 700 | 1.8807 | 0.2753 | 0.6909 | 0.1722 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.35.2 |
| - Pytorch 2.1.1+cu121 |
| - Datasets 2.14.5 |
| - Tokenizers 0.15.1 |
|
|
