mt5-small-finetuned-persian-news-summarization
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: 0.8880
- Rouge1 Precision: 72.843
- Rouge1 Recall: 46.8371
- Rouge1 F1: 56.8651
- Rouge2 Precision: 61.0282
- Rouge2 Recall: 37.7478
- Rouge2 F1: 46.5048
- Rougel Precision: 69.1299
- Rougel Recall: 44.5254
- Rougel F1: 54.0245
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.4003 | 1.0 | 1205 | 1.0358 | 71.6709 | 45.8793 | 55.8031 | 59.5342 | 36.6628 | 45.248 | 68.0282 | 43.6204 | 53.0224 |
| 1.1605 | 2.0 | 2410 | 0.9247 | 72.8666 | 46.8982 | 56.9231 | 61.0197 | 37.7849 | 46.5365 | 69.2395 | 44.6295 | 54.1396 |
| 1.0493 | 3.0 | 3615 | 0.8921 | 73.0661 | 46.981 | 57.0429 | 61.258 | 37.8927 | 46.6847 | 69.4699 | 44.7446 | 54.293 |
| 0.9994 | 4.0 | 4820 | 0.8880 | 72.843 | 46.8371 | 56.8651 | 61.0282 | 37.7478 | 46.5048 | 69.1299 | 44.5254 | 54.0245 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2