metadata
license: apache-2.0
base_model: google/vit-base-patch32-224-in21k
tags:
- generated_from_trainer
datasets:
- snacks
metrics:
- accuracy
model-index:
- name: vit-model-rob-vilchis
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: snacks
type: snacks
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8607329842931937
vit-model-rob-vilchis
This model is a fine-tuned version of google/vit-base-patch32-224-in21k on the snacks dataset. It achieves the following results on the evaluation set:
- Loss: 0.5765
- Accuracy: 0.8607
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2646 | 0.83 | 500 | 0.9471 | 0.7361 |
| 0.4485 | 1.65 | 1000 | 0.6931 | 0.8084 |
| 0.179 | 2.48 | 1500 | 0.7448 | 0.8157 |
| 0.052 | 3.31 | 2000 | 0.5765 | 0.8607 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3