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: 0.5375
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: 1.2847
- Accuracy: 0.5375
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: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.856 | 1.0 | 10 | 1.9048 | 0.3063 |
| 1.81 | 2.0 | 20 | 1.8399 | 0.3063 |
| 1.7131 | 3.0 | 30 | 1.7206 | 0.3375 |
| 1.5894 | 4.0 | 40 | 1.6192 | 0.375 |
| 1.4919 | 5.0 | 50 | 1.5405 | 0.4688 |
| 1.4037 | 6.0 | 60 | 1.4735 | 0.4625 |
| 1.2923 | 7.0 | 70 | 1.4350 | 0.4688 |
| 1.2228 | 8.0 | 80 | 1.4562 | 0.4188 |
| 1.1275 | 9.0 | 90 | 1.3757 | 0.4875 |
| 1.0461 | 10.0 | 100 | 1.3880 | 0.45 |
| 0.9891 | 11.0 | 110 | 1.3440 | 0.5 |
| 0.9058 | 12.0 | 120 | 1.3576 | 0.4813 |
| 0.8835 | 13.0 | 130 | 1.3420 | 0.5188 |
| 0.8274 | 14.0 | 140 | 1.3294 | 0.4938 |
| 0.7686 | 15.0 | 150 | 1.2996 | 0.525 |
| 0.7181 | 16.0 | 160 | 1.2817 | 0.5437 |
| 0.6822 | 17.0 | 170 | 1.2726 | 0.5312 |
| 0.6398 | 18.0 | 180 | 1.3250 | 0.5062 |
| 0.6009 | 19.0 | 190 | 1.3224 | 0.5312 |
| 0.5892 | 20.0 | 200 | 1.3125 | 0.4875 |
| 0.5528 | 21.0 | 210 | 1.3334 | 0.4938 |
| 0.5699 | 22.0 | 220 | 1.2408 | 0.5563 |
| 0.5209 | 23.0 | 230 | 1.3150 | 0.525 |
| 0.5011 | 24.0 | 240 | 1.3601 | 0.4938 |
| 0.5123 | 25.0 | 250 | 1.2566 | 0.5563 |
| 0.4768 | 26.0 | 260 | 1.2542 | 0.5188 |
| 0.4812 | 27.0 | 270 | 1.2753 | 0.525 |
| 0.474 | 28.0 | 280 | 1.2961 | 0.5125 |
| 0.5015 | 29.0 | 290 | 1.2658 | 0.5437 |
| 0.4685 | 30.0 | 300 | 1.2562 | 0.55 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1