mBART_slang_to_standard_1
This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0006
- Bleu: 88.9448
- Gen Len: 41.403
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: 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 |
|---|---|---|---|---|---|
| 0.7894 | 1.0 | 2266 | 0.1850 | 58.9932 | 61.974 |
| 0.0343 | 2.0 | 4532 | 0.0064 | 88.295 | 41.529 |
| 0.0051 | 3.0 | 6798 | 0.0006 | 88.9448 | 41.403 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 108
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.