|
--- |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
model-index: |
|
- name: led-risalah_data_v5 |
|
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_v5 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9222 |
|
- Rouge1 Precision: 0.4901 |
|
- Rouge1 Recall: 0.1294 |
|
- Rouge1 Fmeasure: 0.2036 |
|
|
|
## 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 | 1.6479 | 0.2556 | 0.6178 | 0.1618 | |
|
| 1.8512 | 2.0 | 140 | 1.5744 | 0.2745 | 0.6561 | 0.174 | |
|
| 1.4296 | 3.0 | 210 | 1.5595 | 0.2702 | 0.6617 | 0.1704 | |
|
| 1.4296 | 4.0 | 280 | 1.5402 | 0.274 | 0.685 | 0.1719 | |
|
| 1.1976 | 5.0 | 350 | 1.5242 | 0.2728 | 0.676 | 0.1721 | |
|
| 1.0638 | 6.0 | 420 | 1.5383 | 0.2873 | 0.6886 | 0.182 | |
|
| 1.0638 | 7.0 | 490 | 1.5652 | 0.2771 | 0.6636 | 0.1757 | |
|
| 0.9657 | 8.0 | 560 | 1.5797 | 0.2733 | 0.6788 | 0.172 | |
|
| 0.9215 | 9.0 | 630 | 1.5960 | 0.2715 | 0.6644 | 0.1715 | |
|
| 0.849 | 10.0 | 700 | 1.5943 | 0.2681 | 0.6581 | 0.1693 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.15.1 |
|
|
