|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: peft-finetune-flan-t5-mc-question-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. --> |
|
|
|
# peft-finetune-flan-t5-mc-question-generation |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1553 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2947 | 0.13 | 100 | 1.7430 | |
|
| 1.8174 | 0.25 | 200 | 1.3561 | |
|
| 1.5218 | 0.38 | 300 | 1.2409 | |
|
| 1.4277 | 0.51 | 400 | 1.2068 | |
|
| 1.3855 | 0.64 | 500 | 1.1918 | |
|
| 1.3648 | 0.76 | 600 | 1.1808 | |
|
| 1.3438 | 0.89 | 700 | 1.1744 | |
|
| 1.3408 | 1.02 | 800 | 1.1685 | |
|
| 1.3357 | 1.15 | 900 | 1.1658 | |
|
| 1.3258 | 1.27 | 1000 | 1.1620 | |
|
| 1.3187 | 1.4 | 1100 | 1.1597 | |
|
| 1.3195 | 1.53 | 1200 | 1.1577 | |
|
| 1.3168 | 1.65 | 1300 | 1.1572 | |
|
| 1.3167 | 1.78 | 1400 | 1.1559 | |
|
| 1.311 | 1.91 | 1500 | 1.1553 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|