t5-end2end-questions-generation
This model is a fine-tuned version of t5-base on the squad_modified_for_t5_qg dataset. It achieves the following results on the evaluation set:
- Loss: 1.9348
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: 0.01
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3469 | 0.34 | 100 | 2.4950 |
| 2.4544 | 0.68 | 200 | 2.2909 |
| 2.2343 | 1.02 | 300 | 2.1290 |
| 1.8746 | 1.35 | 400 | 2.0220 |
| 1.8029 | 1.69 | 500 | 1.9348 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3