arieg/bw_spec_cls_4_01_noise_200_confirm

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: 0.0143
• Train Sparse Categorical Accuracy: 1.0
• Validation Loss: 0.0140
• Validation Sparse Categorical Accuracy: 1.0
• 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', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 14400, '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 Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
0.6064	0.9569	0.2224	1.0	0
0.1543	1.0	0.1168	1.0	1
0.0979	1.0	0.0858	1.0	2
0.0769	1.0	0.0709	1.0	3
0.0647	1.0	0.0603	1.0	4
0.0558	1.0	0.0528	1.0	5
0.0490	1.0	0.0465	1.0	6
0.0434	1.0	0.0414	1.0	7
0.0387	1.0	0.0369	1.0	8
0.0347	1.0	0.0332	1.0	9
0.0312	1.0	0.0300	1.0	10
0.0282	1.0	0.0272	1.0	11
0.0256	1.0	0.0248	1.0	12
0.0234	1.0	0.0226	1.0	13
0.0214	1.0	0.0207	1.0	14
0.0196	1.0	0.0190	1.0	15
0.0181	1.0	0.0176	1.0	16
0.0167	1.0	0.0162	1.0	17
0.0155	1.0	0.0150	1.0	18
0.0143	1.0	0.0140	1.0	19

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1