t5-end2end-questions-generation-full
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5588
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5811 | 0.34 | 100 | 1.8916 |
| 1.9668 | 0.68 | 200 | 1.7116 |
| 1.8274 | 1.02 | 300 | 1.6512 |
| 1.7424 | 1.36 | 400 | 1.6294 |
| 1.7076 | 1.69 | 500 | 1.6024 |
| 1.7001 | 2.03 | 600 | 1.5916 |
| 1.6266 | 2.37 | 700 | 1.5881 |
| 1.6275 | 2.71 | 800 | 1.5772 |
| 1.6146 | 3.05 | 900 | 1.5824 |
| 1.5699 | 3.39 | 1000 | 1.5776 |
| 1.5635 | 3.73 | 1100 | 1.5710 |
| 1.5484 | 4.07 | 1200 | 1.5698 |
| 1.5199 | 4.41 | 1300 | 1.5616 |
| 1.5352 | 4.75 | 1400 | 1.5661 |
| 1.5174 | 5.08 | 1500 | 1.5633 |
| 1.4955 | 5.42 | 1600 | 1.5603 |
| 1.4904 | 5.76 | 1700 | 1.5631 |
| 1.5033 | 6.1 | 1800 | 1.5572 |
| 1.4853 | 6.44 | 1900 | 1.5588 |
| 1.4679 | 6.78 | 2000 | 1.5588 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2