t5-base-toform
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2052
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 |
|---|---|---|---|
| 4.0716 | 0.9479 | 50 | 3.9844 |
| 3.5782 | 1.8910 | 100 | 2.9484 |
| 2.8778 | 2.8341 | 150 | 2.2875 |
| 2.3024 | 3.7773 | 200 | 1.8902 |
| 2.0751 | 4.7204 | 250 | 1.7012 |
| 1.9331 | 5.6635 | 300 | 1.5802 |
| 1.7798 | 6.6066 | 350 | 1.4950 |
| 1.6744 | 7.5498 | 400 | 1.4344 |
| 1.6436 | 8.4929 | 450 | 1.3836 |
| 1.5647 | 9.4360 | 500 | 1.3451 |
| 1.5063 | 10.3791 | 550 | 1.3167 |
| 1.5014 | 11.3223 | 600 | 1.2906 |
| 1.445 | 12.2654 | 650 | 1.2705 |
| 1.4294 | 13.2085 | 700 | 1.2540 |
| 1.4056 | 14.1517 | 750 | 1.2411 |
| 1.4049 | 15.0948 | 800 | 1.2304 |
| 1.3582 | 16.0379 | 850 | 1.2209 |
| 1.3658 | 16.9858 | 900 | 1.2145 |
| 1.3381 | 17.9289 | 950 | 1.2097 |
| 1.3357 | 18.8720 | 1000 | 1.2066 |
| 1.3596 | 19.8152 | 1050 | 1.2052 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1