Xanadu00/galaxy_classifier_mobilevit_2

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

• Train Loss: 0.1727
• Train Accuracy: 0.9423
• Validation Loss: 0.4766
• Validation Accuracy: 0.8565
• 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': 'AdamW', 'weight_decay': 0.004, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.002, 'decay_steps': 10000, 'decay_rate': 0.01, 'staircase': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.9904	0.6535	0.7897	0.7269	0
0.6759	0.7662	0.5772	0.8030	1
0.5845	0.7979	0.5967	0.8010	2
0.5166	0.8232	0.5613	0.8030	3
0.4819	0.8330	0.5049	0.8253	4
0.4432	0.8516	0.5894	0.7993	5
0.4113	0.8580	0.4722	0.8354	6
0.3802	0.8704	0.4730	0.8444	7
0.3529	0.8750	0.4391	0.8543	8
0.3255	0.8836	0.4380	0.8563	9
0.3053	0.8953	0.4468	0.8532	10
0.2821	0.9027	0.5082	0.8368	11
0.2690	0.9071	0.4380	0.8588	12
0.2460	0.9132	0.4668	0.8540	13
0.2184	0.9247	0.4684	0.8557	14
0.2017	0.9273	0.4880	0.8546	15
0.1930	0.9311	0.4934	0.8582	16
0.1727	0.9423	0.4766	0.8565	17

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3