|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: t5-ost |
|
|
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-ost |
|
|
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0581 |
|
|
|
|
|
## 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: 0.0005 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 1000 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.5695 | 0.39 | 500 | 0.0591 | |
|
|
| 0.0606 | 0.77 | 1000 | 0.0588 | |
|
|
| 0.0575 | 1.16 | 1500 | 0.0588 | |
|
|
| 0.0551 | 1.55 | 2000 | 0.0586 | |
|
|
| 0.0549 | 1.93 | 2500 | 0.0581 | |
|
|
| 0.0487 | 2.32 | 3000 | 0.0597 | |
|
|
| 0.0478 | 2.71 | 3500 | 0.0594 | |
|
|
| 0.0463 | 3.1 | 4000 | 0.0624 | |
|
|
| 0.0404 | 3.48 | 4500 | 0.0625 | |
|
|
| 0.041 | 3.87 | 5000 | 0.0617 | |
|
|
| 0.0366 | 4.26 | 5500 | 0.0656 | |
|
|
| 0.0347 | 4.64 | 6000 | 0.0658 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.22.1 |
|
|
- Pytorch 1.12.0 |
|
|
- Datasets 2.5.1 |
|
|
- Tokenizers 0.12.1 |
|
|
|
