metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-ethos-25
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: 0.9170896785109983
vit-base-patch16-224-ethos-25
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2803
- Accuracy: 0.9171
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: 0.0002
- 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 |
|---|---|---|---|---|
| 1.606 | 0.99 | 43 | 1.3384 | 0.6387 |
| 0.6334 | 1.99 | 86 | 0.5900 | 0.8519 |
| 0.3928 | 2.98 | 129 | 0.4637 | 0.8739 |
| 0.2361 | 4.0 | 173 | 0.3965 | 0.8909 |
| 0.1816 | 4.99 | 216 | 0.4107 | 0.8782 |
| 0.1253 | 5.99 | 259 | 0.3433 | 0.8976 |
| 0.1255 | 6.98 | 302 | 0.3334 | 0.9069 |
| 0.1009 | 8.0 | 346 | 0.3042 | 0.9154 |
| 0.0812 | 8.99 | 389 | 0.2809 | 0.9146 |
| 0.0698 | 9.94 | 430 | 0.2803 | 0.9171 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2