<!-- 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_hyperparameter_1
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: 0.0871
- Bleu: 86.6567
- Gen Len: 43.0648
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 |
|---|---|---|---|---|---|
| 2.4912 | 1.0 | 1998 | 0.6319 | 66.5947 | 80.0315 |
| 1.4069 | 2.0 | 3996 | 0.2170 | 72.413 | 64.2111 |
| 1.0829 | 3.0 | 5994 | 0.1315 | 78.7786 | 40.3136 |
| 0.8977 | 4.0 | 7992 | 0.0979 | 84.3878 | 42.5152 |
| 0.8452 | 5.0 | 9990 | 0.0871 | 86.6567 | 43.0648 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.0
- Tokenizers 0.13.1
