aiornot_eman / README.md
emanehab's picture
Update README.md
2386483
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: aiornot_eman
    results: []
datasets:
  - competitions/aiornot
language:
  - en
library_name: transformers
pipeline_tag: image-classification

aiornot_eman

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0863
  • Accuracy: 0.9726

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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 results

Training Loss Epoch Step Validation Loss Accuracy
0.1235 1.0 248 0.1117 0.9547
0.0512 2.0 497 0.0866 0.9690
0.0175 2.99 744 0.0863 0.9726

Framework versions

  • Transformers 4.27.3
  • Pytorch 1.10.2
  • Datasets 2.10.1
  • Tokenizers 0.13.2