dense_dan_100m_mult
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.0855
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 11395
- training_steps: 113957
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.9371 | 0.8775 | 10000 | 5.8804 |
| 4.9934 | 1.7550 | 20000 | 5.0208 |
| 4.6476 | 2.6325 | 30000 | 4.7727 |
| 4.3166 | 3.5100 | 40000 | 4.6728 |
| 4.0181 | 4.3875 | 50000 | 4.6482 |
| 3.7146 | 5.2650 | 60000 | 4.6816 |
| 3.3834 | 6.1425 | 70000 | 4.7419 |
| 3.0504 | 7.0200 | 80000 | 4.8071 |
| 3.208 | 7.8975 | 90000 | 4.8842 |
| 2.9186 | 8.7750 | 100000 | 5.0045 |
| 2.6484 | 9.6525 | 110000 | 5.0833 |
Framework versions
- Transformers 4.51.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- -