t5_cnn_dailymail_model
This model is a fine-tuned version of t5-small on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.9434
- Rouge1: 41.0879
- Rouge2: 18.4262
- Rougel: 29.0974
- Rougelsum: 29.1279
- Gen Len: 72.75
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- 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: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.6278 | 1.0 | 250 | 1.9764 | 41.3399 | 18.5362 | 28.587 | 28.4475 | 75.925 |
| 1.7496 | 2.0 | 500 | 1.9653 | 40.965 | 18.1485 | 28.5241 | 28.4623 | 75.26 |
| 1.6318 | 3.0 | 750 | 1.9795 | 41.2934 | 18.333 | 28.3873 | 28.2784 | 74.985 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.11.0+cu128
- Datasets 2.14.7
- Tokenizers 0.21.4
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for MOUADchiali/t5_cnn_dailymail_model
Base model
google-t5/t5-smallDataset used to train MOUADchiali/t5_cnn_dailymail_model
Evaluation results
- Rouge1 on cnn_dailymailvalidation set self-reported41.088