metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emikes-classifier
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: 1
emikes-classifier
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: 0.0253
- Accuracy: 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: 16
- eval_batch_size: 16
- seed: 69
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3954 | 1.25 | 10 | 0.3092 | 0.8571 |
| 0.1249 | 2.5 | 20 | 0.1407 | 1.0 |
| 0.046 | 3.75 | 30 | 0.0666 | 1.0 |
| 0.034 | 5.0 | 40 | 0.1060 | 0.9286 |
| 0.0255 | 6.25 | 50 | 0.0295 | 1.0 |
| 0.0198 | 7.5 | 60 | 0.0274 | 1.0 |
| 0.0209 | 8.75 | 70 | 0.1060 | 0.9286 |
| 0.02 | 10.0 | 80 | 0.0253 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0