t5-small-toinf
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3495
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-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6007 | 0.9479 | 50 | 4.4553 |
| 4.3901 | 1.8910 | 100 | 3.8501 |
| 3.9927 | 2.8341 | 150 | 3.3790 |
| 3.6562 | 3.7773 | 200 | 3.1353 |
| 3.4484 | 4.7204 | 250 | 2.9598 |
| 3.352 | 5.6635 | 300 | 2.8255 |
| 3.1997 | 6.6066 | 350 | 2.7154 |
| 3.0431 | 7.5498 | 400 | 2.6390 |
| 3.0088 | 8.4929 | 450 | 2.5868 |
| 2.9281 | 9.4360 | 500 | 2.5419 |
| 2.8857 | 10.3791 | 550 | 2.5115 |
| 2.8598 | 11.3223 | 600 | 2.4742 |
| 2.828 | 12.2654 | 650 | 2.4441 |
| 2.7331 | 13.2085 | 700 | 2.4207 |
| 2.7396 | 14.1517 | 750 | 2.4025 |
| 2.7336 | 15.0948 | 800 | 2.3858 |
| 2.7193 | 16.0379 | 850 | 2.3726 |
| 2.7096 | 16.9858 | 900 | 2.3626 |
| 2.6839 | 17.9289 | 950 | 2.3562 |
| 2.6633 | 18.8720 | 1000 | 2.3512 |
| 2.6655 | 19.8152 | 1050 | 2.3495 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1