legal-modern-decoder-checkpoints
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.2547
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 23.6144 | 0.1638 | 1000 | 6.0602 |
| 20.1664 | 0.3277 | 2000 | 5.1520 |
| 18.0928 | 0.4915 | 3000 | 4.6943 |
| 17.2208 | 0.6554 | 4000 | 4.4395 |
| 16.3705 | 0.8192 | 5000 | 4.2925 |
| 16.2153 | 0.9830 | 6000 | 4.2547 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2