metadata
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: camembert-base-finetuned-sentence-simplification-fr
results: []
camembert-base-finetuned-sentence-simplification-fr
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3512
- Rouge1: 71.7164
- Rouge2: 48.3026
- Rougel: 60.9741
- Rougelsum: 71.703
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 5.526 | 1.0 | 167 | 1.5778 | 20.8927 | 6.5549 | 19.8894 | 20.8757 |
| 1.2998 | 2.0 | 334 | 0.7396 | 47.1012 | 24.6065 | 42.5169 | 47.1201 |
| 0.8173 | 3.0 | 501 | 0.4854 | 63.0251 | 38.8258 | 53.3364 | 63.0153 |
| 0.6211 | 4.0 | 668 | 0.3797 | 70.1541 | 46.2974 | 59.4121 | 70.1327 |
| 0.5504 | 5.0 | 835 | 0.3512 | 71.7164 | 48.3026 | 60.9741 | 71.703 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1