Edit model card

agusg6/img_classifier_4CLA

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

  • Train Loss: 1.2902
  • Validation Loss: 1.2999
  • Train Accuracy: 0.368
  • Epoch: 4

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 5620, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
1.3609 1.3373 0.384 0
1.3299 1.3047 0.4 1
1.3223 1.3236 0.392 2
1.3101 1.3079 0.384 3
1.2902 1.2999 0.368 4

Framework versions

  • Transformers 4.39.3
  • TensorFlow 2.16.1
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
3

Finetuned from