mt5-small-finetuned-persian-news-summarization-with-additional-hyperparameters-2
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0635
- Rouge1 Precision: 62.4589
- Rouge1 Recall: 62.5583
- Rouge1 F1: 62.4147
- Rouge2 Precision: 47.675
- Rouge2 Recall: 47.8652
- Rouge2 F1: 47.6954
- Rougel Precision: 56.6815
- Rougel Recall: 56.8183
- Rougel F1: 56.6653
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 Precision | Rouge1 Recall | Rouge1 F1 | Rouge2 Precision | Rouge2 Recall | Rouge2 F1 | Rougel Precision | Rougel Recall | Rougel F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 5.0516 | 1.0 | 1205 | 1.1929 | 59.7863 | 59.5963 | 59.5842 | 45.0261 | 44.9939 | 44.927 | 54.0853 | 53.9468 | 53.9196 |
| 1.4427 | 2.0 | 2410 | 1.0989 | 61.8195 | 61.8793 | 61.752 | 47.117 | 47.2719 | 47.1179 | 55.9932 | 56.0903 | 55.9544 |
| 1.3238 | 3.0 | 3615 | 1.0684 | 62.3185 | 62.3787 | 62.2513 | 47.481 | 47.6336 | 47.4809 | 56.5177 | 56.6169 | 56.4799 |
| 1.2959 | 4.0 | 4820 | 1.0635 | 62.4589 | 62.5583 | 62.4147 | 47.675 | 47.8652 | 47.6954 | 56.6815 | 56.8183 | 56.6653 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2