Downloads · 30 days
36
15% of all-time downloads
led-risalah_data_v14
silmi224/led-risalah_data_v14
led-risalah_data_v14 is a summarization model from silmi224. Use it when you need a shorter version of a longer text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
239
Public
Parameters
162M
35.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors648 MB · 99%
At a glance
- Task
- Summarization
- Library
- transformers
- Model type
- led
- Access
- Public
- Created
- Jul 10, 2024
- Updated
- Jul 12, 2024
- SHA
- a6808e20
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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_v14
This model is a fine-tuned version of silmi224/finetune-led-35000 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7199
- Rouge1 Precision: 0.6769
- Rouge1 Recall: 0.1724
- Rouge1 Fmeasure: 0.2744
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 Precision | Rouge1 Recall | Rouge1 Fmeasure |
|---|---|---|---|---|---|---|
| 1.6706 | 0.9714 | 17 | 1.8400 | 0.6261 | 0.1547 | 0.2478 |
| 1.5177 | 2.0 | 35 | 1.7573 | 0.6586 | 0.1669 | 0.266 |
| 1.4016 | 2.9714 | 52 | 1.7266 | 0.6597 | 0.1689 | 0.2682 |
| 1.3182 | 4.0 | 70 | 1.7403 | 0.6564 | 0.1667 | 0.2653 |
| 1.217 | 4.9714 | 87 | 1.7272 | 0.657 | 0.1663 | 0.265 |
| 1.1559 | 6.0 | 105 | 1.7288 | 0.6493 | 0.1698 | 0.2687 |
| 1.1675 | 6.9714 | 122 | 1.7114 | 0.6727 | 0.1705 | 0.2717 |
| 1.1193 | 8.0 | 140 | 1.7118 | 0.6764 | 0.1734 | 0.2758 |
| 1.1101 | 8.9714 | 157 | 1.7232 | 0.6705 | 0.1726 | 0.2739 |
| 1.147 | 9.7143 | 170 | 1.7199 | 0.6769 | 0.1724 | 0.2744 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Summarization
- Library
- transformers
- Type
- led
- Created
- Jul 10, 2024
- Updated
- Jul 12, 2024