Payoto's picture
update model card README.md
883e50a
|
raw
history blame
1.75 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
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:

  • Loss: 0.0618
  • Accuracy: 0.9878

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: IPU
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • 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 precision: Mixed Precision

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.1366 1.0 759 0.1417 0.9730
0.0374 2.0 1518 0.0793 0.9830
0.0237 3.0 2277 0.0618 0.9878

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.10.0+cpu
  • Datasets 2.7.1
  • Tokenizers 0.12.1