mt5-small-finetuned-cnn_dailymail
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: 2.3254
- Rouge1: 27.84
- Rouge2: 12.76
- Rougel: 24.39
- Rougelsum: 25.91
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.5881 | 1.0 | 3510 | 2.4243 | 26.44 | 11.33 | 22.82 | 24.39 |
| 2.7944 | 2.0 | 7020 | 2.3306 | 27.77 | 12.64 | 24.29 | 25.84 |
| 2.6698 | 3.0 | 10530 | 2.3254 | 27.84 | 12.76 | 24.39 | 25.91 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1