vit5-large-legal-lora
This model is a fine-tuned version of VietAI/vit5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4278
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: 3
- eval_batch_size: 6
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 6
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6407 | 1.0 | 11183 | 1.4850 |
| 1.5931 | 2.0 | 22366 | 1.4408 |
| 1.5619 | 3.0 | 33549 | 1.4278 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3