metadata
base_model: facebook/mbart-large-50-many-to-many-mmt
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-large-50-many-to-many-mmt-finetuned-pt-to-en
results: []
mbart-large-50-many-to-many-mmt-finetuned-pt-to-en
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.0116
- Bleu: 3.9795
- Gen Len: 46.1292
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: 0.0002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.981 | 1.0 | 989 | 2.6925 | 2.0264 | 53.1604 |
| 2.1381 | 2.0 | 1978 | 2.6576 | 2.6268 | 47.2153 |
| 1.6501 | 3.0 | 2967 | 2.7743 | 2.9549 | 45.5091 |
| 1.2518 | 4.0 | 3956 | 2.9517 | 3.1862 | 49.9585 |
| 0.9188 | 5.0 | 4945 | 3.1741 | 3.3758 | 46.0227 |
| 0.6615 | 6.0 | 5934 | 3.3934 | 3.4223 | 42.5911 |
| 0.4714 | 7.0 | 6923 | 3.6090 | 3.8522 | 48.1263 |
| 0.3283 | 8.0 | 7912 | 3.8027 | 3.7817 | 46.4619 |
| 0.2291 | 9.0 | 8901 | 3.9314 | 3.9939 | 47.2651 |
| 0.163 | 10.0 | 9890 | 4.0116 | 3.9795 | 46.1292 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1