my_wikilingua_model_mBart50_trans
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: 2.5850
- Rouge1: 0.3544
- Rouge2: 0.1276
- Rougel: 0.278
- Rougelsum: 0.2781
- Gen Len: 44.4625
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 |
|---|---|---|---|---|---|---|---|---|
| 2.2609 | 1.0 | 1600 | 2.1254 | 0.2502 | 0.0868 | 0.2162 | 0.2157 | 61.8925 |
| 1.5106 | 2.0 | 3200 | 2.1392 | 0.3321 | 0.1205 | 0.27 | 0.2696 | 42.615 |
| 1.2338 | 3.0 | 4800 | 2.3200 | 0.3496 | 0.128 | 0.2754 | 0.2753 | 42.3075 |
| 0.7157 | 4.0 | 6400 | 2.5850 | 0.3544 | 0.1276 | 0.278 | 0.2781 | 44.4625 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3