t5-small-end2end-questions-generation_eli_squad_aug_exp__
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5242
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 |
|---|---|---|---|
| 3.8266 | 0.25 | 100 | 2.9131 |
| 2.9641 | 0.51 | 200 | 2.7933 |
| 2.8628 | 0.76 | 300 | 2.7168 |
| 2.8042 | 1.01 | 400 | 2.6537 |
| 2.7292 | 1.27 | 500 | 2.6111 |
| 2.6952 | 1.52 | 600 | 2.5807 |
| 2.6677 | 1.77 | 700 | 2.5603 |
| 2.6553 | 2.03 | 800 | 2.5481 |
| 2.6339 | 2.28 | 900 | 2.5348 |
| 2.6246 | 2.53 | 1000 | 2.5286 |
| 2.6205 | 2.78 | 1100 | 2.5242 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3