mt5-small-news-final
This model is a fine-tuned version of google/mt5-small on the hebrew_news dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.4946
- Rouge2: 0.0432
- Rougel: 0.4922
- Rougelsum: 0.4919
- Gen Len: 6.0117
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 1029 | nan | 0.4946 | 0.0432 | 0.4922 | 0.4919 | 6.0117 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.11.0