metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: vit-base-patch16-224-in21k-finetuned-eurosat
    results: []

vit-base-patch16-224-in21k-finetuned-eurosat

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

eval_loss: 0.2695
eval_accuracy: 0.9022
eval_runtime: 195.5267
eval_samples_per_second: 21.486
eval_steps_per_second: 0.675
epoch: 51.76
step: 10196

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: 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: 200

Framework versions

Transformers 4.20.1
Pytorch 1.12.1+cu102
Datasets 2.3.2
Tokenizers 0.12.1