T5-PEFT-4
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1673
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.18 | 250 | 1.3037 |
| 1.6713 | 0.35 | 500 | 1.2525 |
| 1.6713 | 0.53 | 750 | 1.2217 |
| 1.3129 | 0.71 | 1000 | 1.2068 |
| 1.3129 | 0.89 | 1250 | 1.1978 |
| 1.292 | 1.06 | 1500 | 1.1856 |
| 1.292 | 1.24 | 1750 | 1.1794 |
| 1.253 | 1.42 | 2000 | 1.1769 |
| 1.253 | 1.6 | 2250 | 1.1725 |
| 1.2529 | 1.77 | 2500 | 1.1693 |
| 1.2529 | 1.95 | 2750 | 1.1673 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for jgibb/T5-PEFT-4
Base model
google-t5/t5-base