t5-base-end2end-questions-generation_eli_squad_single_exp
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7241
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 |
|---|---|---|---|
| 2.4297 | 0.25 | 100 | 2.7250 |
| 2.2459 | 0.5 | 200 | 2.7337 |
| 2.2066 | 0.74 | 300 | 2.7301 |
| 2.1867 | 0.99 | 400 | 2.7186 |
| 2.1046 | 1.24 | 500 | 2.7268 |
| 2.1003 | 1.49 | 600 | 2.7269 |
| 2.0799 | 1.74 | 700 | 2.7222 |
| 2.0852 | 1.99 | 800 | 2.7238 |
| 2.0323 | 2.23 | 900 | 2.7258 |
| 2.0297 | 2.48 | 1000 | 2.7252 |
| 2.0451 | 2.73 | 1100 | 2.7230 |
| 2.0208 | 2.98 | 1200 | 2.7241 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3