metadata
base_model: silmi224/finetune-led-35000
tags:
- summarization
- generated_from_trainer
model-index:
- name: led-risalah_data_v4.1
results: []
led-risalah_data_v4.1
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: 1.6280
- Rouge1 Precision: 0.6744
- Rouge1 Recall: 0.1777
- Rouge1 Fmeasure: 0.2803
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: 5e-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 |
|---|---|---|---|---|---|---|
| 2.3322 | 0.9714 | 17 | 1.7433 | 0.6164 | 0.1561 | 0.2485 |
| 1.5523 | 2.0 | 35 | 1.6294 | 0.6379 | 0.1588 | 0.2536 |
| 1.3282 | 2.9714 | 52 | 1.6077 | 0.6252 | 0.1561 | 0.2491 |
| 1.2231 | 4.0 | 70 | 1.5914 | 0.6599 | 0.1704 | 0.2706 |
| 1.1213 | 4.9714 | 87 | 1.6090 | 0.6771 | 0.1707 | 0.272 |
| 1.0491 | 6.0 | 105 | 1.6135 | 0.6656 | 0.17 | 0.2704 |
| 0.9272 | 6.9714 | 122 | 1.6004 | 0.6758 | 0.1755 | 0.2783 |
| 0.8667 | 8.0 | 140 | 1.6217 | 0.7048 | 0.1826 | 0.2896 |
| 0.884 | 8.9714 | 157 | 1.6185 | 0.7143 | 0.1856 | 0.294 |
| 0.8415 | 9.7143 | 170 | 1.6280 | 0.6744 | 0.1777 | 0.2803 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1