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-crop-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: 0.7472190257000384
vit-base-patch16-224-in21k-finetuned-crop-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: 0.6450
- Accuracy: 0.7472
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: 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 |
|---|---|---|---|---|
| 0.8031 | 1.0 | 183 | 0.7603 | 0.7050 |
| 0.7311 | 2.0 | 367 | 0.7047 | 0.7250 |
| 0.7144 | 3.0 | 550 | 0.6968 | 0.7211 |
| 0.6516 | 4.0 | 734 | 0.6569 | 0.7376 |
| 0.6371 | 5.0 | 917 | 0.6483 | 0.7376 |
| 0.6246 | 6.0 | 1101 | 0.6492 | 0.7365 |
| 0.5659 | 7.0 | 1284 | 0.6481 | 0.7411 |
| 0.533 | 8.0 | 1468 | 0.6450 | 0.7472 |
| 0.5416 | 9.0 | 1651 | 0.6382 | 0.7453 |
| 0.5062 | 9.97 | 1830 | 0.6395 | 0.7461 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0