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: 0.53125
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: 1.3935
- Accuracy: 0.5312
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-07
- train_batch_size: 27
- eval_batch_size: 27
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 27
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 24 | 1.3599 | 0.5188 |
| No log | 2.0 | 48 | 1.4076 | 0.475 |
| No log | 3.0 | 72 | 1.3638 | 0.5375 |
| No log | 4.0 | 96 | 1.4062 | 0.5375 |
| No log | 5.0 | 120 | 1.3665 | 0.5563 |
| No log | 6.0 | 144 | 1.3475 | 0.575 |
| No log | 7.0 | 168 | 1.3814 | 0.525 |
| No log | 8.0 | 192 | 1.3791 | 0.5437 |
| No log | 9.0 | 216 | 1.3692 | 0.5125 |
| No log | 10.0 | 240 | 1.4024 | 0.5188 |
| No log | 11.0 | 264 | 1.3544 | 0.5687 |
| No log | 12.0 | 288 | 1.4049 | 0.5375 |
| No log | 13.0 | 312 | 1.3539 | 0.5687 |
| No log | 14.0 | 336 | 1.3936 | 0.5062 |
| No log | 15.0 | 360 | 1.3643 | 0.5375 |
| No log | 16.0 | 384 | 1.3618 | 0.5563 |
| No log | 17.0 | 408 | 1.3669 | 0.5687 |
| No log | 18.0 | 432 | 1.4041 | 0.5188 |
| No log | 19.0 | 456 | 1.3679 | 0.5312 |
| No log | 20.0 | 480 | 1.3489 | 0.5563 |
| 1.1227 | 21.0 | 504 | 1.3575 | 0.575 |
| 1.1227 | 22.0 | 528 | 1.3721 | 0.55 |
| 1.1227 | 23.0 | 552 | 1.3985 | 0.4938 |
| 1.1227 | 24.0 | 576 | 1.3924 | 0.5062 |
| 1.1227 | 25.0 | 600 | 1.3760 | 0.55 |
| 1.1227 | 26.0 | 624 | 1.3767 | 0.5125 |
| 1.1227 | 27.0 | 648 | 1.3627 | 0.5563 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3