metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_modified_for_t5_qg
model-index:
- name: t5-end2end-questions-generation_V1
results: []
t5-end2end-questions-generation_V1
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: 1.5671
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 |
|---|---|---|---|
| 1.787 | 0.34 | 100 | 1.7580 |
| 1.8565 | 0.68 | 200 | 1.6773 |
| 1.7969 | 1.02 | 300 | 1.6396 |
| 1.6961 | 1.35 | 400 | 1.6202 |
| 1.6777 | 1.69 | 500 | 1.6101 |
| 1.6584 | 2.03 | 600 | 1.5956 |
| 1.6032 | 2.37 | 700 | 1.5908 |
| 1.5995 | 2.71 | 800 | 1.5870 |
| 1.5876 | 3.05 | 900 | 1.5834 |
| 1.5467 | 3.39 | 1000 | 1.5820 |
| 1.5486 | 3.73 | 1100 | 1.5696 |
| 1.5313 | 4.06 | 1200 | 1.5761 |
| 1.514 | 4.4 | 1300 | 1.5713 |
| 1.5024 | 4.74 | 1400 | 1.5727 |
| 1.4984 | 5.08 | 1500 | 1.5722 |
| 1.4769 | 5.42 | 1600 | 1.5700 |
| 1.4652 | 5.76 | 1700 | 1.5670 |
| 1.4835 | 6.1 | 1800 | 1.5684 |
| 1.4589 | 6.44 | 1900 | 1.5711 |
| 1.459 | 6.77 | 2000 | 1.5671 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2