metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-gecko
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.988479262672811
vit-base-patch16-224-in21k-finetuned-gecko
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: 0.1890
- Accuracy: 0.9885
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| No log | 0.97 | 21 | 3.2699 | 0.6210 |
| No log | 1.98 | 43 | 2.0011 | 0.8468 |
| 3.1155 | 2.99 | 65 | 1.2851 | 0.8641 |
| 3.1155 | 4.0 | 87 | 0.7751 | 0.9389 |
| 1.1003 | 4.97 | 108 | 0.6060 | 0.9274 |
| 1.1003 | 5.98 | 130 | 0.4584 | 0.9378 |
| 0.5229 | 6.99 | 152 | 0.3417 | 0.9585 |
| 0.5229 | 8.0 | 174 | 0.2415 | 0.9816 |
| 0.5229 | 8.97 | 195 | 0.2014 | 0.9873 |
| 0.3249 | 9.66 | 210 | 0.1890 | 0.9885 |
Framework versions
- Transformers 4.34.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.6
- Tokenizers 0.14.1