|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- t5_squad |
|
model-index: |
|
- name: t5-simple-qg-eng |
|
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-simple-qg-eng |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the t5_squad dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5682 |
|
|
|
## 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 | |
|
| 1.8466 | 1.02 | 300 | 1.6634 | |
|
| 1.7412 | 1.36 | 400 | 1.6383 | |
|
| 1.7134 | 1.69 | 500 | 1.6202 | |
|
| 1.694 | 2.03 | 600 | 1.6049 | |
|
| 1.6297 | 2.37 | 700 | 1.5975 | |
|
| 1.6261 | 2.71 | 800 | 1.5932 | |
|
| 1.6149 | 3.05 | 900 | 1.5875 | |
|
| 1.569 | 3.39 | 1000 | 1.5893 | |
|
| 1.5683 | 3.73 | 1100 | 1.5740 | |
|
| 1.5569 | 4.07 | 1200 | 1.5785 | |
|
| 1.5331 | 4.41 | 1300 | 1.5733 | |
|
| 1.5216 | 4.75 | 1400 | 1.5705 | |
|
| 1.5226 | 5.08 | 1500 | 1.5735 | |
|
| 1.4933 | 5.42 | 1600 | 1.5703 | |
|
| 1.4845 | 5.76 | 1700 | 1.5683 | |
|
| 1.5077 | 6.1 | 1800 | 1.5684 | |
|
| 1.4749 | 6.44 | 1900 | 1.5727 | |
|
| 1.4757 | 6.78 | 2000 | 1.5682 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
