<!-- 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. -->
mBART_translator_json_sentence_split
This model is a fine-tuned version of facebook/mbart-large-cc25 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0769
- Bleu: 87.2405
- Gen Len: 27.425
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: 1e-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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.0011 | 1.0 | 2978 | 0.5458 | 63.8087 | 32.3819 |
| 1.1978 | 2.0 | 5956 | 0.1854 | 76.5291 | 27.6781 |
| 0.9276 | 3.0 | 8934 | 0.1123 | 84.7194 | 27.5773 |
| 0.776 | 4.0 | 11912 | 0.0845 | 87.505 | 27.2845 |
| 0.6889 | 5.0 | 14890 | 0.0769 | 87.2405 | 27.425 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
