metadata
license: apache-2.0
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: roman_numerals-digit-classification-2022-09-04
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: farleyknight/roman_numerals
type: imagefolder
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.8333333333333334
name: Accuracy
roman_numerals-digit-classification-2022-09-04
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the farleyknight/roman_numerals dataset. It achieves the following results on the evaluation set:
- Loss: 0.7018
- Accuracy: 0.8333
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: 2e-05
- 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: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9053 | 1.0 | 289 | 1.3680 | 0.7132 |
| 1.2788 | 2.0 | 578 | 0.9499 | 0.7966 |
| 1.1232 | 3.0 | 867 | 0.8679 | 0.7279 |
| 1.0373 | 4.0 | 1156 | 0.7324 | 0.8088 |
| 0.9658 | 5.0 | 1445 | 0.7018 | 0.8333 |
Framework versions
- Transformers 4.22.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1