metadata

license: apache-2.0
tags:
  - masked-image-modeling
  - generated_from_trainer
base_model: google/vit-base-patch16-224-in21k
model-index:
  - name: vit-base-patch16-224-in21k-base-manuscripts
    results: []

vit-base-patch16-224-in21k-base-manuscripts

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the davanstrien/iiif_manuscripts_label_ge_50 dataset. It achieves the following results on the evaluation set:

Loss: 0.5210

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: 32
eval_batch_size: 32
seed: 1333
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5198	1.0	32	0.5208

Framework versions

Transformers 4.18.0.dev0
Pytorch 1.10.0+cu111
Datasets 1.18.4
Tokenizers 0.11.6