|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: tiny_focal_ckpt |
|
|
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. --> |
|
|
|
|
|
# tiny_focal_ckpt |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0561 |
|
|
- Precision: 0.6529 |
|
|
- Recall: 0.6366 |
|
|
- F1: 0.6446 |
|
|
- Accuracy: 0.9516 |
|
|
|
|
|
## 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: 3e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.058 | 1.0 | 5561 | 0.0583 | 0.6327 | 0.5945 | 0.6130 | 0.9484 | |
|
|
| 0.0566 | 2.0 | 11122 | 0.0570 | 0.6401 | 0.5985 | 0.6186 | 0.9492 | |
|
|
| 0.0564 | 3.0 | 16683 | 0.0567 | 0.6364 | 0.6241 | 0.6302 | 0.9496 | |
|
|
| 0.053 | 4.0 | 22244 | 0.0561 | 0.6416 | 0.6312 | 0.6364 | 0.9503 | |
|
|
| 0.052 | 5.0 | 27805 | 0.0558 | 0.6501 | 0.6239 | 0.6367 | 0.9510 | |
|
|
| 0.0507 | 6.0 | 33366 | 0.0555 | 0.6555 | 0.6208 | 0.6377 | 0.9514 | |
|
|
| 0.0497 | 7.0 | 38927 | 0.0552 | 0.6559 | 0.6256 | 0.6404 | 0.9515 | |
|
|
| 0.0485 | 8.0 | 44488 | 0.0561 | 0.6485 | 0.6397 | 0.6440 | 0.9513 | |
|
|
| 0.0481 | 9.0 | 50049 | 0.0558 | 0.6531 | 0.6344 | 0.6436 | 0.9515 | |
|
|
| 0.0469 | 10.0 | 55610 | 0.0561 | 0.6529 | 0.6366 | 0.6446 | 0.9516 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.20.0 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.3.2 |
|
|
- Tokenizers 0.12.1 |
|
|
|
