metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: vit-fire-detection
results: []
vit-fire-detection
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0524
- Precision: 0.9803
- Recall: 0.9802
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: 0.002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|
| 0.5087 | 1.0 | 190 | 0.5356 | 0.8054 | 0.7421 |
| 0.2943 | 2.0 | 380 | 0.1430 | 0.9536 | 0.9524 |
| 0.2409 | 3.0 | 570 | 0.1360 | 0.9541 | 0.9537 |
| 0.1722 | 4.0 | 760 | 0.1265 | 0.9557 | 0.9550 |
| 0.1726 | 5.0 | 950 | 0.1011 | 0.9633 | 0.9630 |
| 0.1563 | 6.0 | 1140 | 0.0946 | 0.9695 | 0.9696 |
| 0.1181 | 7.0 | 1330 | 0.0961 | 0.9643 | 0.9630 |
| 0.1288 | 8.0 | 1520 | 0.0616 | 0.9765 | 0.9762 |
| 0.0858 | 9.0 | 1710 | 0.0699 | 0.9765 | 0.9762 |
| 0.0539 | 10.0 | 1900 | 0.0524 | 0.9803 | 0.9802 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.14.0.dev20221111
- Datasets 2.8.0
- Tokenizers 0.12.1