t5-end2end-questions-generation_v4
This model is a fine-tuned version of t5-base on the eli5_subset_modified_for_t5_qg_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 2.8814
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2704 | 0.64 | 100 | 2.9474 |
| 3.0764 | 1.28 | 200 | 2.9067 |
| 3.0189 | 1.92 | 300 | 2.8866 |
| 2.9797 | 2.56 | 400 | 2.8814 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2