t5-base-end2end-questions-generation_squad_single
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0815
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: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9402 | 0.26 | 100 | 3.0330 |
| 1.7483 | 0.51 | 200 | 3.0355 |
| 1.7082 | 0.77 | 300 | 3.0535 |
| 1.6808 | 1.02 | 400 | 3.0741 |
| 1.6108 | 1.28 | 500 | 3.0716 |
| 1.5994 | 1.54 | 600 | 3.0707 |
| 1.586 | 1.79 | 700 | 3.0727 |
| 1.5731 | 2.05 | 800 | 3.0761 |
| 1.5377 | 2.3 | 900 | 3.0893 |
| 1.5326 | 2.56 | 1000 | 3.0896 |
| 1.5422 | 2.82 | 1100 | 3.0815 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3