metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- recall
- f1
- precision
model-index:
- name: vit-base-patch16-224-finetuned-ind-17-imbalanced-aadhaarmask
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.848446147296722
- name: Recall
type: recall
value: 0.848446147296722
- name: F1
type: f1
value: 0.8477849036950597
- name: Precision
type: precision
value: 0.8513434130555053
vit-base-patch16-224-finetuned-ind-17-imbalanced-aadhaarmask
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3494
- Accuracy: 0.8484
- Recall: 0.8484
- F1: 0.8478
- Precision: 0.8513
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
---|---|---|---|---|---|---|---|
0.5792 | 0.9974 | 293 | 0.5989 | 0.7969 | 0.7969 | 0.7829 | 0.7897 |
0.42 | 1.9983 | 587 | 0.5251 | 0.8046 | 0.8046 | 0.7960 | 0.7985 |
0.3501 | 2.9991 | 881 | 0.4299 | 0.8335 | 0.8335 | 0.8312 | 0.8363 |
0.3187 | 4.0 | 1175 | 0.4302 | 0.8169 | 0.8169 | 0.8144 | 0.8182 |
0.3873 | 4.9974 | 1468 | 0.4246 | 0.8250 | 0.8250 | 0.8238 | 0.8326 |
0.3786 | 5.9983 | 1762 | 0.3881 | 0.8306 | 0.8306 | 0.8303 | 0.8394 |
0.337 | 6.9991 | 2056 | 0.3803 | 0.8306 | 0.8306 | 0.8304 | 0.8351 |
0.2717 | 8.0 | 2350 | 0.3785 | 0.8395 | 0.8395 | 0.8361 | 0.8482 |
0.2753 | 8.9974 | 2643 | 0.3805 | 0.8327 | 0.8327 | 0.8314 | 0.8346 |
0.2814 | 9.9745 | 2930 | 0.3362 | 0.8480 | 0.8480 | 0.8467 | 0.8499 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.0a0+81ea7a4
- Datasets 2.19.0
- Tokenizers 0.19.1