classification-model-synthetic-no-balancing
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1667
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: 16
- eval_batch_size: 256
- seed: 42
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5843 | 1.0 | 296 | 0.3970 |
| 0.3252 | 2.0 | 592 | 0.2316 |
| 0.2374 | 3.0 | 888 | 0.1914 |
| 0.2063 | 4.0 | 1184 | 0.1816 |
| 0.1974 | 5.0 | 1480 | 0.1747 |
| 0.1898 | 6.0 | 1776 | 0.1712 |
| 0.1911 | 7.0 | 2072 | 0.1685 |
| 0.1835 | 8.0 | 2368 | 0.1678 |
| 0.1928 | 9.0 | 2664 | 0.1678 |
| 0.1728 | 10.0 | 2960 | 0.1667 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1