metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- fashion_mnist
metrics:
- accuracy
model-index:
- name: my_awesome_fashion_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: fashion_mnist
type: fashion_mnist
config: fashion_mnist
split: train[:5000]
args: fashion_mnist
metrics:
- name: Accuracy
type: accuracy
value: 0.796
my_awesome_fashion_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the fashion_mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.8182
- Accuracy: 0.796
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3152 | 0.99 | 62 | 1.2059 | 0.75 |
| 0.9175 | 2.0 | 125 | 0.8880 | 0.784 |
| 0.8417 | 2.98 | 186 | 0.8182 | 0.796 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3