vit-base-patch16-224-in21k-FINALLaneClassifier-VIT50AUGMENTED
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: 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.013 | 1.0 | 2098 | 0.0503 | {'accuracy': 0.9872512808292625} | {'f1': 0.9872500637993007} | {'precision': 0.9875320438126312} | {'recall': 0.9872891423140888} |
| 0.0202 | 2.0 | 4196 | 0.0034 | {'accuracy': 0.9991659716430359} | {'f1': 0.9991659678069054} | {'precision': 0.999164877117633} | {'recall': 0.999168448562604} |
| 0.0007 | 3.0 | 6294 | 0.0340 | {'accuracy': 0.9864172524722984} | {'f1': 0.9864157249694355} | {'precision': 0.986738017682643} | {'recall': 0.9864575908766928} |
| 0.0002 | 4.0 | 8392 | 0.0078 | {'accuracy': 0.9972596211128322} | {'f1': 0.9972596209572226} | {'precision': 0.9972664606608035} | {'recall': 0.9972677595628415} |
| 0.0001 | 5.0 | 10490 | 0.0051 | {'accuracy': 0.9986893840104849} | {'f1': 0.9986893803637995} | {'precision': 0.998688915375447} | {'recall': 0.9986932763126634} |
| 0.0001 | 6.0 | 12588 | 0.0122 | {'accuracy': 0.9965447396640057} | {'f1': 0.9965447388791924} | {'precision': 0.9965582720151911} | {'recall': 0.9965550011879306} |
| 0.0002 | 7.0 | 14686 | 0.0019 | {'accuracy': 0.999523412367449} | {'f1': 0.9995234093837869} | {'precision': 0.9995224450811844} | {'recall': 0.9995248277500595} |
| 0.0002 | 8.0 | 16784 | 0.0089 | {'accuracy': 0.9979745025616585} | {'f1': 0.9979744996862612} | {'precision': 0.9979755665421167} | {'recall': 0.9979798081321687} |
| 0.0413 | 9.0 | 18882 | 0.0082 | {'accuracy': 0.9971404742046944} | {'f1': 0.9971404741641006} | {'precision': 0.997148288973384} | {'recall': 0.9971489665003563} |
| 0.0001 | 10.0 | 20980 | 0.0451 | {'accuracy': 0.9908256880733946} | {'f1': 0.9908253358952392} | {'precision': 0.9909645623093171} | {'recall': 0.9908529341886434} |
| 0.0 | 11.0 | 23078 | 0.0075 | {'accuracy': 0.998212796377934} | {'f1': 0.9982127634963612} | {'precision': 0.998220079886156} | {'recall': 0.9982088765901349} |
| 0.0 | 12.0 | 25176 | 0.0039 | {'accuracy': 0.9991659716430359} | {'f1': 0.9991659678069054} | {'precision': 0.999164877117633} | {'recall': 0.999168448562604} |
| 0.013 | 13.0 | 27274 | 0.0107 | {'accuracy': 0.997736208745383} | {'f1': 0.9977362066886293} | {'precision': 0.9977383781306159} | {'recall': 0.9977422220071985} |
| 0.0537 | 14.0 | 29372 | 0.0013 | {'accuracy': 0.9996425592755868} | {'f1': 0.9996425558453789} | {'precision': 0.9996429388720207} | {'recall': 0.9996422012013773} |
| 0.0018 | 15.0 | 31470 | 0.0115 | {'accuracy': 0.9973787680209698} | {'f1': 0.997378766197631} | {'precision': 0.997381574328435} | {'recall': 0.9973851330141593} |
| 0.0049 | 16.0 | 33568 | 0.0040 | {'accuracy': 0.9986893840104849} | {'f1': 0.9986893803637995} | {'precision': 0.998688915375447} | {'recall': 0.9986932763126634} |
| 0.0032 | 17.0 | 35666 | 0.0002 | {'accuracy': 0.9998808530918623} | {'f1': 0.9998808519484597} | {'precision': 0.9998812351543943} | {'recall': 0.9998804971319312} |
| 0.0002 | 18.0 | 37764 | 0.0018 | {'accuracy': 0.9994042654593114} | {'f1': 0.9994042620764765} | {'precision': 0.9994031988541419} | {'recall': 0.9994060346875742} |
| 0.0003 | 19.0 | 39862 | 0.0028 | {'accuracy': 0.9986893840104849} | {'f1': 0.9986893803637995} | {'precision': 0.998688915375447} | {'recall': 0.9986932763126634} |
| 0.0 | 20.0 | 41960 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 21.0 | 44058 | 0.0013 | {'accuracy': 0.9996425592755868} | {'f1': 0.9996425568196459} | {'precision': 0.99964174826845} | {'recall': 0.9996436208125445} |
| 0.0005 | 22.0 | 46156 | 0.0032 | {'accuracy': 0.9990468247348981} | {'f1': 0.9990468198500874} | {'precision': 0.9990457151585668} | {'recall': 0.9990489456945351} |
| 0.0 | 23.0 | 48254 | 0.0030 | {'accuracy': 0.999523412367449} | {'f1': 0.9995234087884033} | {'precision': 0.9995228131486541} | {'recall': 0.9995241179444757} |
| 0.0 | 24.0 | 50352 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 25.0 | 52450 | 0.0039 | {'accuracy': 0.9990468247348981} | {'f1': 0.9990468208243473} | {'precision': 0.9990458015267176} | {'recall': 0.9990496555001188} |
| 0.0 | 26.0 | 54548 | 0.0028 | {'accuracy': 0.9992851185511736} | {'f1': 0.9992851148875656} | {'precision': 0.9992840095465394} | {'recall': 0.9992872416250891} |
| 0.0 | 27.0 | 56646 | 0.0010 | {'accuracy': 0.9996425592755868} | {'f1': 0.9996425568196459} | {'precision': 0.99964174826845} | {'recall': 0.9996436208125445} |
| 0.0002 | 28.0 | 58744 | 0.0004 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 29.0 | 60842 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 30.0 | 62940 | 0.0018 | {'accuracy': 0.999523412367449} | {'f1': 0.9995234093837869} | {'precision': 0.9995224450811844} | {'recall': 0.9995248277500595} |
| 0.0001 | 31.0 | 65038 | 0.0020 | {'accuracy': 0.9996425592755868} | {'f1': 0.9996425558453789} | {'precision': 0.9996429388720207} | {'recall': 0.9996422012013773} |
| 0.0002 | 32.0 | 67136 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 33.0 | 69234 | 0.0014 | {'accuracy': 0.9996425592755868} | {'f1': 0.9996425568196459} | {'precision': 0.99964174826845} | {'recall': 0.9996436208125445} |
| 0.0 | 34.0 | 71332 | 0.0110 | {'accuracy': 0.9984510901942094} | {'f1': 0.9984510584424513} | {'precision': 0.9984604452865941} | {'recall': 0.9984464627151052} |
| 0.0004 | 35.0 | 73430 | 0.0009 | {'accuracy': 0.9998808530918623} | {'f1': 0.9998808521176034} | {'precision': 0.9998805256869773} | {'recall': 0.9998812069375149} |
| 0.0 | 36.0 | 75528 | 0.0009 | {'accuracy': 0.9998808530918623} | {'f1': 0.9998808521176034} | {'precision': 0.9998805256869773} | {'recall': 0.9998812069375149} |
| 0.0 | 37.0 | 77626 | 0.0002 | {'accuracy': 0.9998808530918623} | {'f1': 0.9998808521176034} | {'precision': 0.9998805256869773} | {'recall': 0.9998812069375149} |
| 0.0 | 38.0 | 79724 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 39.0 | 81822 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 40.0 | 83920 | 0.0024 | {'accuracy': 0.9994042654593114} | {'f1': 0.999404257847879} | {'precision': 0.999406739439962} | {'recall': 0.9994024856596558} |
| 0.0 | 41.0 | 86018 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 42.0 | 88116 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 43.0 | 90214 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 44.0 | 92312 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 45.0 | 94410 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 46.0 | 96508 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 47.0 | 98606 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 48.0 | 100704 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 49.0 | 102802 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
| 0.0 | 50.0 | 104900 | 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