|
--- |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
model-index: |
|
- name: led-risalah_data_v13 |
|
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_v13 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5198 |
|
- Rouge1 Precision: 0.4184 |
|
- Rouge1 Recall: 0.4032 |
|
- Rouge1 Fmeasure: 0.4092 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall | |
|
|:-------------:|:------:|:----:|:---------------:|:---------------:|:----------------:|:-------------:| |
|
| 3.1517 | 0.9714 | 17 | 2.3560 | 0.2698 | 0.277 | 0.2642 | |
|
| 2.2618 | 2.0 | 35 | 2.1487 | 0.3183 | 0.3295 | 0.3091 | |
|
| 1.9714 | 2.9714 | 52 | 2.0826 | 0.3383 | 0.358 | 0.3226 | |
|
| 1.8991 | 4.0 | 70 | 2.0284 | 0.34 | 0.3579 | 0.3248 | |
|
| 1.7713 | 4.9714 | 87 | 1.9871 | 0.3667 | 0.3744 | 0.3602 | |
|
| 1.7889 | 6.0 | 105 | 1.9714 | 0.3614 | 0.3729 | 0.3521 | |
|
| 1.6378 | 6.9714 | 122 | 1.9481 | 0.3589 | 0.3762 | 0.3461 | |
|
| 1.5649 | 8.0 | 140 | 1.9426 | 0.3657 | 0.3802 | 0.3545 | |
|
| 1.5157 | 8.9714 | 157 | 1.9349 | 0.3667 | 0.375 | 0.361 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
