<!-- 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. -->
tiny-mbart-length-128-learning_rate-2e-05-weight_decay-0.01-finetuned-en-to-ro
This model is a fine-tuned version of sshleifer/tiny-mbart on the wmt16_en_ro_pre_processed dataset. It achieves the following results on the evaluation set:
- Loss: 8.4656
- Bleu: 0.0
- Gen Len: 20.0
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 8.2268 | 1.0 | 76290 | 8.4656 | 0.0 | 20.0 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu102
- Datasets 1.15.1
- Tokenizers 0.10.3
