flan-t5-small-continued-pretrain-legal
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0051
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5548 | 0.125 | 500 | 0.0075 |
| 0.0171 | 0.25 | 1000 | 0.0048 |
| 0.0081 | 0.375 | 1500 | 0.0045 |
| 0.0058 | 0.5 | 2000 | 0.0047 |
| 0.0042 | 0.625 | 2500 | 0.0050 |
| 0.0038 | 0.75 | 3000 | 0.0052 |
| 0.0034 | 0.875 | 3500 | 0.0051 |
| 0.003 | 1.0 | 4000 | 0.0051 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Tokenizers 0.21.0