metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_modified_for_t5_qg
- wiselinjayajos/squad_modified_for_t5_qg
model-index:
- name: t5-end2end-questions-generation
results: []
metrics:
- bleu
- meteor
- rouge
t5-end2end-questions-generation
This model is a fine-tuned version of t5-base on the squad_modified_for_t5_qg dataset. It achieves the following results on the evaluation set:
- Loss: 1.5678
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: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.584 | 0.34 | 100 | 1.9108 |
| 1.9664 | 0.68 | 200 | 1.7275 |
| 1.842 | 1.02 | 300 | 1.6641 |
| 1.7417 | 1.35 | 400 | 1.6368 |
| 1.713 | 1.69 | 500 | 1.6219 |
| 1.6899 | 2.03 | 600 | 1.6046 |
| 1.6302 | 2.37 | 700 | 1.5961 |
| 1.6259 | 2.71 | 800 | 1.5946 |
| 1.6107 | 3.05 | 900 | 1.5879 |
| 1.5689 | 3.39 | 1000 | 1.5865 |
| 1.5688 | 3.73 | 1100 | 1.5722 |
| 1.5519 | 4.06 | 1200 | 1.5792 |
| 1.5343 | 4.4 | 1300 | 1.5737 |
| 1.5214 | 4.74 | 1400 | 1.5745 |
| 1.5169 | 5.08 | 1500 | 1.5736 |
| 1.4954 | 5.42 | 1600 | 1.5730 |
| 1.4827 | 5.76 | 1700 | 1.5680 |
| 1.5015 | 6.1 | 1800 | 1.5701 |
| 1.4769 | 6.44 | 1900 | 1.5732 |
| 1.4765 | 6.77 | 2000 | 1.5678 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2