|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: t5_Question_Generation_2 |
|
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_Question_Generation_2 |
|
|
|
This model is a fine-tuned version of [Gayathri142214002/t5_Question_Generation](https://huggingface.co/Gayathri142214002/t5_Question_Generation) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5549 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0256 | 0.25 | 100 | 0.7578 | |
|
| 0.7848 | 0.5 | 200 | 0.6872 | |
|
| 0.6682 | 0.75 | 300 | 0.6440 | |
|
| 0.6444 | 1.0 | 400 | 0.5939 | |
|
| 0.4903 | 1.25 | 500 | 0.5944 | |
|
| 0.4894 | 1.5 | 600 | 0.5675 | |
|
| 0.5001 | 1.75 | 700 | 0.5546 | |
|
| 0.4891 | 2.0 | 800 | 0.5469 | |
|
| 0.3779 | 2.25 | 900 | 0.5523 | |
|
| 0.3802 | 2.5 | 1000 | 0.5609 | |
|
| 0.395 | 2.74 | 1100 | 0.5483 | |
|
| 0.3916 | 2.99 | 1200 | 0.5482 | |
|
| 0.3383 | 3.24 | 1300 | 0.5634 | |
|
| 0.3391 | 3.49 | 1400 | 0.5629 | |
|
| 0.3294 | 3.74 | 1500 | 0.5573 | |
|
| 0.3363 | 3.99 | 1600 | 0.5413 | |
|
| 0.2851 | 4.24 | 1700 | 0.5533 | |
|
| 0.3032 | 4.49 | 1800 | 0.5575 | |
|
| 0.2995 | 4.74 | 1900 | 0.5548 | |
|
| 0.3091 | 4.99 | 2000 | 0.5396 | |
|
| 0.2606 | 5.24 | 2100 | 0.5420 | |
|
| 0.2622 | 5.49 | 2200 | 0.5468 | |
|
| 0.2817 | 5.74 | 2300 | 0.5460 | |
|
| 0.2743 | 5.99 | 2400 | 0.5473 | |
|
| 0.2501 | 6.24 | 2500 | 0.5542 | |
|
| 0.2484 | 6.49 | 2600 | 0.5558 | |
|
| 0.2388 | 6.74 | 2700 | 0.5542 | |
|
| 0.2414 | 6.99 | 2800 | 0.5549 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
