metadata
tags:
- summarization
- generated_from_trainer
model-index:
- name: led-risalah_data_v6
results: []
led-risalah_data_v6
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7883
- Rouge1 Precision: 0.7351
- Rouge1 Recall: 0.1832
- Rouge1 Fmeasure: 0.2927
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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 70 | 1.8476 | 0.2203 | 0.5271 | 0.1405 |
| 1.9578 | 2.0 | 140 | 1.6793 | 0.2711 | 0.6467 | 0.1733 |
| 1.3878 | 3.0 | 210 | 1.6549 | 0.261 | 0.6216 | 0.1666 |
| 1.3878 | 4.0 | 280 | 1.7038 | 0.2814 | 0.656 | 0.1804 |
| 1.1002 | 5.0 | 350 | 1.7134 | 0.2755 | 0.6577 | 0.1753 |
| 0.8629 | 6.0 | 420 | 1.7733 | 0.2683 | 0.6436 | 0.1711 |
| 0.8629 | 7.0 | 490 | 1.7755 | 0.2757 | 0.6489 | 0.1762 |
| 0.6881 | 8.0 | 560 | 1.8848 | 0.2747 | 0.6502 | 0.1758 |
| 0.5746 | 9.0 | 630 | 1.9318 | 0.2647 | 0.6305 | 0.1686 |
| 0.479 | 10.0 | 700 | 1.9675 | 0.2655 | 0.633 | 0.1692 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.15.1