Edit model card

msislam123/cifar10

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: 1.4844
  • Train Accuracy: 0.5160
  • Validation Loss: 1.8361
  • Validation Accuracy: 0.3676
  • Epoch: 19

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': 59840, '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
2.7038 0.1213 2.5039 0.1698 0
2.4263 0.1935 2.3429 0.2179 1
2.2970 0.2343 2.1942 0.2901 2
2.2132 0.2694 2.1083 0.3115 3
2.1136 0.2998 2.0528 0.3102 4
2.0533 0.3145 2.0046 0.3182 5
2.0016 0.3292 1.9495 0.3356 6
1.9511 0.3463 1.9589 0.3182 7
1.9106 0.3636 1.9360 0.3249 8
1.8807 0.3700 1.9207 0.3396 9
1.8368 0.3790 1.8890 0.3556 10
1.8118 0.3951 1.8834 0.3489 11
1.7714 0.3967 1.8410 0.3730 12
1.7185 0.4225 1.8576 0.3396 13
1.6796 0.4439 1.8087 0.3743 14
1.6593 0.4519 1.8192 0.3543 15
1.6208 0.4539 1.8129 0.3650 16
1.5826 0.4826 1.8316 0.3663 17
1.5399 0.4913 1.7991 0.3650 18
1.4844 0.5160 1.8361 0.3676 19

Framework versions

  • Transformers 4.38.2
  • TensorFlow 2.15.0
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
6

Finetuned from