t5-base-end2end-questions-generation_eli_squad_aug_v1
This model is a fine-tuned version of t5-base on the eli5_cleaned_datav3_60k dataset. It achieves the following results on the evaluation set:
- Loss: 2.3264
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 |
|---|---|---|---|
| 2.2646 | 0.25 | 100 | 2.4396 |
| 2.1168 | 0.49 | 200 | 2.4056 |
| 2.0807 | 0.74 | 300 | 2.3825 |
| 2.0393 | 0.98 | 400 | 2.3653 |
| 1.9759 | 1.23 | 500 | 2.3547 |
| 1.9567 | 1.47 | 600 | 2.3453 |
| 1.9397 | 1.72 | 700 | 2.3405 |
| 1.9497 | 1.96 | 800 | 2.3349 |
| 1.8961 | 2.21 | 900 | 2.3318 |
| 1.9075 | 2.46 | 1000 | 2.3290 |
| 1.9056 | 2.7 | 1100 | 2.3269 |
| 1.8959 | 2.95 | 1200 | 2.3264 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3