t5-small-f2inf
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3142
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 |
|---|---|---|---|
| 4.3447 | 0.9479 | 50 | 3.7401 |
| 4.1121 | 1.8910 | 100 | 3.5651 |
| 3.846 | 2.8341 | 150 | 3.3381 |
| 3.6293 | 3.7773 | 200 | 3.1652 |
| 3.3962 | 4.7204 | 250 | 3.0156 |
| 3.3365 | 5.6635 | 300 | 2.8887 |
| 3.1526 | 6.6066 | 350 | 2.7780 |
| 3.0013 | 7.5498 | 400 | 2.7001 |
| 2.9622 | 8.4929 | 450 | 2.6280 |
| 2.8684 | 9.4360 | 500 | 2.5671 |
| 2.8213 | 10.3791 | 550 | 2.5154 |
| 2.7491 | 11.3223 | 600 | 2.4698 |
| 2.7324 | 12.2654 | 650 | 2.4360 |
| 2.6397 | 13.2085 | 700 | 2.4080 |
| 2.6333 | 14.1517 | 750 | 2.3831 |
| 2.6342 | 15.0948 | 800 | 2.3621 |
| 2.606 | 16.0379 | 850 | 2.3462 |
| 2.587 | 16.9858 | 900 | 2.3318 |
| 2.5463 | 17.9289 | 950 | 2.3220 |
| 2.5925 | 18.8720 | 1000 | 2.3165 |
| 2.5653 | 19.8152 | 1050 | 2.3142 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1