Hugging Face's logo

hafizurUMaine
/
cifar10_m

Image Classification
Transformers
TensorFlow
mobilevit
generated_from_keras_callback
Inference Endpoints
Model card Files Community
cifar10_m / README.md
hafizurUMaine's picture
hafizurUMaine
Training in progress epoch 17
c4f9b67
preview code
|
raw
history blame
3.11 kB
metadata
license: other
base_model: apple/mobilevit-xx-small
tags:
  - generated_from_keras_callback
model-index:
  - name: hafizurUMaine/cifar10_m
    results: []

hafizurUMaine/cifar10_m

This model is a fine-tuned version of apple/mobilevit-xx-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.3505
  • Train Accuracy: 0.8859
  • Validation Loss: 0.6268
  • Validation Accuracy: 0.8195
  • Epoch: 17

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': 400000, '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 Train Accuracy Validation Loss Validation Accuracy Epoch
5.5748 0.1482 3.1655 0.4160 0
2.4468 0.5135 1.7772 0.6195 1
1.5927 0.6389 1.3152 0.6770 2
1.2333 0.7001 1.1226 0.7265 3
1.0094 0.7334 0.9668 0.7490 4
0.8748 0.7591 0.9140 0.7510 5
0.7714 0.7846 0.7881 0.7845 6
0.6977 0.7999 0.8075 0.7745 7
0.6524 0.8096 0.8417 0.7675 8
0.5904 0.8254 0.7763 0.7850 9
0.5525 0.8321 0.7367 0.7955 10
0.5083 0.8459 0.7343 0.7990 11
0.4695 0.8559 0.6768 0.8075 12
0.4432 0.8615 0.6830 0.8095 13
0.4125 0.8704 0.6891 0.7980 14
0.3995 0.875 0.6482 0.8155 15
0.3723 0.8781 0.6653 0.8095 16
0.3505 0.8859 0.6268 0.8195 17

Framework versions

  • Transformers 4.37.2
  • TensorFlow 2.15.0
  • Datasets 2.16.1
  • Tokenizers 0.15.1