|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- squad_modified_for_t5_qg |
|
model-index: |
|
- name: t5-end2end-questions-generation |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# t5-end2end-questions-generation |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the squad_modified_for_t5_qg dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5670 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.5856 | 0.34 | 100 | 1.9106 | |
|
| 1.9634 | 0.68 | 200 | 1.7226 | |
|
| 1.8421 | 1.02 | 300 | 1.6633 | |
|
| 1.742 | 1.35 | 400 | 1.6343 | |
|
| 1.7129 | 1.69 | 500 | 1.6129 | |
|
| 1.69 | 2.03 | 600 | 1.6110 | |
|
| 1.6315 | 2.37 | 700 | 1.5964 | |
|
| 1.6273 | 2.71 | 800 | 1.5902 | |
|
| 1.6109 | 3.05 | 900 | 1.5900 | |
|
| 1.571 | 3.39 | 1000 | 1.5849 | |
|
| 1.566 | 3.73 | 1100 | 1.5687 | |
|
| 1.5501 | 4.06 | 1200 | 1.5797 | |
|
| 1.5347 | 4.4 | 1300 | 1.5795 | |
|
| 1.5242 | 4.74 | 1400 | 1.5679 | |
|
| 1.5173 | 5.08 | 1500 | 1.5752 | |
|
| 1.4966 | 5.42 | 1600 | 1.5698 | |
|
| 1.484 | 5.76 | 1700 | 1.5689 | |
|
| 1.5008 | 6.1 | 1800 | 1.5684 | |
|
| 1.4754 | 6.44 | 1900 | 1.5680 | |
|
| 1.479 | 6.77 | 2000 | 1.5670 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|