vit-base-patch16-224-in21k-FINALLaneClassifier-VIT30epochsAUGMENTEDWITHTEST
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Accuracy: {'accuracy': 1.0}
- F1: {'f1': 1.0}
- Precision: {'precision': 1.0}
- Recall: {'recall': 1.0}
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0229 | 0.9973 | 274 | 0.0166 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0083 | 1.9982 | 549 | 0.0062 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0055 | 2.9991 | 824 | 0.0032 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0025 | 4.0 | 1099 | 0.0019 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.004 | 4.9973 | 1373 | 0.0013 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.001 | 5.9982 | 1648 | 0.0009 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0032 | 6.9991 | 1923 | 0.0014 | {'accuracy': 0.9998862343572241} | {'f1': 0.9998861783406705} | {'precision': 0.9998887157801024} | {'recall': 0.9998836668217777} |
| 0.0011 | 8.0 | 2198 | 0.0005 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0035 | 8.9973 | 2472 | 0.0004 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0004 | 9.9982 | 2747 | 0.0003 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0003 | 10.9991 | 3022 | 0.0003 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0004 | 12.0 | 3297 | 0.0003 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0002 | 12.9973 | 3571 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0005 | 13.9982 | 3846 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.006 | 14.9991 | 4121 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 16.0 | 4396 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 16.9973 | 4670 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 17.9982 | 4945 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0004 | 18.9991 | 5220 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 20.0 | 5495 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 20.9973 | 5769 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0012 | 21.9982 | 6044 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 22.9991 | 6319 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 24.0 | 6594 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 24.9973 | 6868 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0002 | 25.9982 | 7143 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 26.9991 | 7418 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 28.0 | 7693 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 28.9973 | 7967 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0001 | 29.9181 | 8220 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1