t5-base-end2end-questions-generation_eli_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: 2.7312
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 |
|---|---|---|---|
| 2.4834 | 0.26 | 100 | 2.7458 |
| 2.3191 | 0.51 | 200 | 2.7305 |
| 2.2773 | 0.77 | 300 | 2.7290 |
| 2.2385 | 1.02 | 400 | 2.7239 |
| 2.1703 | 1.28 | 500 | 2.7328 |
| 2.1666 | 1.54 | 600 | 2.7324 |
| 2.1551 | 1.79 | 700 | 2.7325 |
| 2.1437 | 2.05 | 800 | 2.7323 |
| 2.0951 | 2.3 | 900 | 2.7331 |
| 2.107 | 2.56 | 1000 | 2.7336 |
| 2.1107 | 2.82 | 1100 | 2.7312 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3