<!-- 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_all_2
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: 0.1595
- Bleu: 76.137
- Gen Len: 11.966
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.914 | 1.0 | 2908 | 0.7158 | 26.1202 | 44.2761 |
| 0.948 | 2.0 | 5816 | 0.3113 | 74.3952 | 12.4625 |
| 0.5552 | 3.0 | 8724 | 0.1595 | 76.137 | 11.966 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.0
- Datasets 1.18.3
- Tokenizers 0.11.0
