metadata
license: apache-2.0
base_model: gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CGIAR-Crop-disease
results: []
CGIAR-Crop-disease
This model is a fine-tuned version of gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7668
- Accuracy: 0.6726
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: 0.001
- train_batch_size: 32
- 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: 50
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.047 | 1.0 | 652 | 0.9302 | 0.5817 |
0.899 | 2.0 | 1304 | 0.8669 | 0.6285 |
0.8656 | 3.0 | 1956 | 0.8434 | 0.6385 |
0.8514 | 4.0 | 2608 | 0.8421 | 0.6277 |
0.8395 | 5.0 | 3260 | 0.8275 | 0.6506 |
0.832 | 6.0 | 3912 | 0.8444 | 0.6415 |
0.8065 | 7.0 | 4564 | 0.8204 | 0.6494 |
0.8031 | 8.0 | 5216 | 0.8271 | 0.6438 |
0.7954 | 9.0 | 5868 | 0.8025 | 0.6632 |
0.7939 | 10.0 | 6520 | 0.7917 | 0.6592 |
0.7893 | 11.0 | 7172 | 0.8043 | 0.6515 |
0.7731 | 12.0 | 7824 | 0.7878 | 0.6695 |
0.7759 | 13.0 | 8476 | 0.7806 | 0.6657 |
0.7676 | 14.0 | 9128 | 0.7816 | 0.6653 |
0.7605 | 15.0 | 9780 | 0.7882 | 0.6550 |
0.7566 | 16.0 | 10432 | 0.7881 | 0.6548 |
0.7554 | 17.0 | 11084 | 0.7824 | 0.6619 |
0.7384 | 18.0 | 11736 | 0.7668 | 0.6726 |
0.7442 | 19.0 | 12388 | 0.7830 | 0.6594 |
0.7296 | 20.0 | 13040 | 0.7709 | 0.6667 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0