swinv2_zindi / README.md
DazMashaly's picture
DazMashaly/swinv2
ad7ef44
metadata
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12-192-22k
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: swinv2_zindi
    results: []

swinv2_zindi

This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12-192-22k on the zindi dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.6328
  • eval_accuracy: 0.7434
  • eval_runtime: 234.8425
  • eval_samples_per_second: 16.492
  • eval_steps_per_second: 0.519
  • epoch: 3.0
  • step: 520

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: 5

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.0
  • Tokenizers 0.15.0