t5-base-end2end-questions-generation_eli_squad_single_exp_imp
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3209
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 |
|---|---|---|---|
| 2.3631 | 0.25 | 100 | 2.4532 |
| 2.1765 | 0.49 | 200 | 2.4057 |
| 2.1516 | 0.74 | 300 | 2.3775 |
| 2.1037 | 0.98 | 400 | 2.3595 |
| 2.0402 | 1.23 | 500 | 2.3486 |
| 2.0185 | 1.47 | 600 | 2.3384 |
| 2.0031 | 1.72 | 700 | 2.3350 |
| 2.0344 | 1.96 | 800 | 2.3275 |
| 1.9459 | 2.21 | 900 | 2.3262 |
| 1.9789 | 2.46 | 1000 | 2.3235 |
| 1.9784 | 2.7 | 1100 | 2.3210 |
| 1.9592 | 2.95 | 1200 | 2.3209 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3