metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_classification
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: 0.4375
image_classification
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: 1.5566
- Accuracy: 0.4375
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: 1e-05
- train_batch_size: 15
- eval_batch_size: 15
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 43 | 2.0423 | 0.2562 |
| No log | 2.0 | 86 | 1.9764 | 0.2812 |
| No log | 3.0 | 129 | 1.8803 | 0.3125 |
| No log | 4.0 | 172 | 1.7690 | 0.3187 |
| No log | 5.0 | 215 | 1.6910 | 0.375 |
| No log | 6.0 | 258 | 1.6397 | 0.3688 |
| No log | 7.0 | 301 | 1.6053 | 0.4688 |
| No log | 8.0 | 344 | 1.5674 | 0.4875 |
| No log | 9.0 | 387 | 1.5714 | 0.4625 |
| No log | 10.0 | 430 | 1.5394 | 0.4938 |
| No log | 11.0 | 473 | 1.5183 | 0.4375 |
| 1.6941 | 12.0 | 516 | 1.5211 | 0.4938 |
| 1.6941 | 13.0 | 559 | 1.4997 | 0.4562 |
| 1.6941 | 14.0 | 602 | 1.5191 | 0.4375 |
| 1.6941 | 15.0 | 645 | 1.4892 | 0.4875 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3