<!-- 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_slang_to_standard_4
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: 1.9058
- Bleu: 60.5005
- Gen Len: 47.7251
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 |
|---|---|---|---|---|---|
| No log | 1.0 | 106 | 2.6704 | 60.4144 | 51.1659 |
| No log | 2.0 | 212 | 2.0665 | 60.2528 | 47.1848 |
| No log | 3.0 | 318 | 1.9058 | 60.5005 | 47.7251 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
