|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google-t5/t5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: t5-small-ft-tr |
|
|
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-small-ft-tr |
|
|
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.3199 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 4.2085 | 1.0 | 1393 | 3.8282 | |
|
|
| 3.9976 | 2.0 | 2786 | 3.7173 | |
|
|
| 3.892 | 3.0 | 4179 | 3.6482 | |
|
|
| 3.8259 | 4.0 | 5572 | 3.5999 | |
|
|
| 3.7951 | 5.0 | 6965 | 3.5604 | |
|
|
| 3.7541 | 6.0 | 8358 | 3.5299 | |
|
|
| 3.7037 | 7.0 | 9751 | 3.5021 | |
|
|
| 3.6603 | 8.0 | 11144 | 3.4786 | |
|
|
| 3.6617 | 9.0 | 12537 | 3.4590 | |
|
|
| 3.6191 | 10.0 | 13930 | 3.4417 | |
|
|
| 3.6184 | 11.0 | 15323 | 3.4273 | |
|
|
| 3.592 | 12.0 | 16716 | 3.4128 | |
|
|
| 3.5782 | 13.0 | 18109 | 3.4017 | |
|
|
| 3.5506 | 14.0 | 19502 | 3.3899 | |
|
|
| 3.5519 | 15.0 | 20895 | 3.3798 | |
|
|
| 3.5262 | 16.0 | 22288 | 3.3715 | |
|
|
| 3.5087 | 17.0 | 23681 | 3.3651 | |
|
|
| 3.509 | 18.0 | 25074 | 3.3558 | |
|
|
| 3.5004 | 19.0 | 26467 | 3.3503 | |
|
|
| 3.4775 | 20.0 | 27860 | 3.3449 | |
|
|
| 3.4817 | 21.0 | 29253 | 3.3405 | |
|
|
| 3.484 | 22.0 | 30646 | 3.3352 | |
|
|
| 3.473 | 23.0 | 32039 | 3.3313 | |
|
|
| 3.4625 | 24.0 | 33432 | 3.3292 | |
|
|
| 3.4513 | 25.0 | 34825 | 3.3267 | |
|
|
| 3.4564 | 26.0 | 36218 | 3.3239 | |
|
|
| 3.4507 | 27.0 | 37611 | 3.3221 | |
|
|
| 3.4385 | 28.0 | 39004 | 3.3211 | |
|
|
| 3.452 | 29.0 | 40397 | 3.3202 | |
|
|
| 3.4528 | 30.0 | 41790 | 3.3199 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.43.4 |
|
|
- Pytorch 1.13.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
