enko_mbartLarge_100p_run1
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6636
- Bleu: 55.7536
- Gen Len: 15.2192
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2500
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.8673 | 1.0 | 63586 | 0.7307 | 52.6771 | 15.2057 |
| 0.7184 | 2.0 | 127173 | 0.6737 | 55.1744 | 15.3621 |
| 0.6294 | 3.0 | 190759 | 0.6636 | 55.7536 | 15.2192 |
| 0.5313 | 4.0 | 254346 | 0.6860 | 55.9422 | 15.2674 |
| 0.4325 | 5.0 | 317932 | 0.7183 | 56.2388 | 15.235 |
| 0.3525 | 6.0 | 381519 | 0.7727 | 55.8867 | 15.2207 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 1