<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_wikilingua_model_mbart50_sup
This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7616
- Rouge1: 0.2035
- Rouge2: 0.0521
- Rougel: 0.1625
- Rougelsum: 0.1625
- Gen Len: 56.88
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.6266 | 1.0 | 1600 | 2.4724 | 0.1425 | 0.0305 | 0.1236 | 0.1234 | 44.085 |
| 1.8764 | 2.0 | 3200 | 2.4293 | 0.1685 | 0.0392 | 0.1408 | 0.1404 | 59.895 |
| 1.3168 | 3.0 | 4800 | 2.5672 | 0.1966 | 0.0521 | 0.1587 | 0.1585 | 49.7175 |
| 0.9342 | 4.0 | 6400 | 2.7616 | 0.2035 | 0.0521 | 0.1625 | 0.1625 | 56.88 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
