model
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6487
- Rouge1: 42.3336
- Rouge2: 20.7191
- Rougel: 35.3723
- Rougelsum: 36.6877
- Gen Len: 22.0905
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 4.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.8303 | 1.0 | 7366 | 1.6443 | 39.7314 | 18.4816 | 33.172 | 34.4741 | 20.1858 |
| 1.2425 | 2.0 | 14732 | 1.5719 | 41.4083 | 20.3324 | 35.0169 | 36.1426 | 21.3594 |
| 0.9629 | 3.0 | 22098 | 1.6487 | 42.3336 | 20.7191 | 35.3723 | 36.6877 | 22.0905 |
| 0.685 | 4.0 | 29464 | 1.8150 | 42.4421 | 19.9827 | 34.7409 | 36.2234 | 25.0416 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.4
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for redqueen01/french-summariser
Base model
facebook/mbart-large-50