vit-base-patch16-224-in21k-laneclassifierasphaltconcrete-detectorVITmain50epochs
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: 0.0004
- 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0576 | 0.9933 | 111 | 0.0139 | {'accuracy': 0.9977628635346756} | {'f1': 0.9966709613995368} | {'precision': 0.9985795454545454} | {'recall': 0.9947916666666667} |
| 0.0365 | 1.9955 | 223 | 0.0012 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0009 | 2.9978 | 335 | 0.0008 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0007 | 4.0 | 447 | 0.0007 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0006 | 4.9933 | 558 | 0.0005 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0005 | 5.9955 | 670 | 0.0005 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0005 | 6.9978 | 782 | 0.0004 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0005 | 7.9463 | 888 | 0.0004 | {'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