t5-base-end2end-questions-generation_eli_squad_aug_exp
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: 2.3304
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 |
|---|---|---|---|
| 2.5828 | 0.25 | 100 | 2.4746 |
| 2.2459 | 0.51 | 200 | 2.4151 |
| 2.1638 | 0.76 | 300 | 2.3905 |
| 2.1028 | 1.01 | 400 | 2.3709 |
| 2.0406 | 1.27 | 500 | 2.3571 |
| 2.027 | 1.52 | 600 | 2.3495 |
| 2.0094 | 1.77 | 700 | 2.3445 |
| 1.9982 | 2.03 | 800 | 2.3371 |
| 1.9669 | 2.28 | 900 | 2.3357 |
| 1.9578 | 2.53 | 1000 | 2.3324 |
| 1.9658 | 2.78 | 1100 | 2.3304 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3