mt5-small-FR-summary
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: 6.2028
- Rouge1: 0.0302
- Rouge2: 0.0
- Rougel: 0.0303
- Rougelsum: 0.0303
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: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
6.2364 | 1.0 | 1088 | 6.2497 | 0.0370 | 0.0 | 0.0369 | 0.0368 |
6.2188 | 2.0 | 2176 | 6.2375 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.206 | 3.0 | 3264 | 6.2273 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.1953 | 4.0 | 4352 | 6.2174 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.1882 | 5.0 | 5440 | 6.2104 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.1814 | 6.0 | 6528 | 6.2053 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.1799 | 7.0 | 7616 | 6.2032 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
6.1785 | 8.0 | 8704 | 6.2028 | 0.0302 | 0.0 | 0.0303 | 0.0303 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5