|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
- recall |
|
|
model-index: |
|
|
- name: profesor_MViT_B_RWF2000 |
|
|
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. --> |
|
|
|
|
|
# profesor_MViT_B_RWF2000 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2639 |
|
|
- Accuracy: 0.9225 |
|
|
- F1: 0.9225 |
|
|
- Precision: 0.9225 |
|
|
- Recall: 0.9225 |
|
|
- Roc Auc: 0.9782 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 20 |
|
|
- eval_batch_size: 20 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 240 |
|
|
- training_steps: 2400 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------:| |
|
|
| 0.5302 | 2.0333 | 240 | 0.4018 | 0.895 | 0.895 | 0.895 | 0.895 | 0.9609 | |
|
|
| 0.2816 | 5.0333 | 480 | 0.2559 | 0.9125 | 0.9125 | 0.9126 | 0.9125 | 0.9782 | |
|
|
| 0.1884 | 8.0333 | 720 | 0.2456 | 0.91 | 0.9099 | 0.9115 | 0.91 | 0.9799 | |
|
|
| 0.1991 | 11.0333 | 960 | 0.2289 | 0.9225 | 0.9225 | 0.9225 | 0.9225 | 0.9815 | |
|
|
| 0.1298 | 14.0333 | 1200 | 0.2186 | 0.9275 | 0.9275 | 0.9275 | 0.9275 | 0.9834 | |
|
|
| 0.1518 | 17.0333 | 1440 | 0.2484 | 0.9275 | 0.9275 | 0.9276 | 0.9275 | 0.9798 | |
|
|
| 0.107 | 20.0333 | 1680 | 0.2442 | 0.93 | 0.9300 | 0.9300 | 0.93 | 0.9834 | |
|
|
| 0.1021 | 23.0333 | 1920 | 0.2653 | 0.925 | 0.9250 | 0.9252 | 0.925 | 0.9813 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 3.0.2 |
|
|
- Tokenizers 0.20.1 |
|
|
|
