DownwardSpiral33/hands_palms_classifier

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: 0.4367
• Validation Loss: 0.7459
• Train Accuracy: 0.5806
• Epoch: 38

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': 'Adam', 'weight_decay': None, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 17400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6873	0.6761	0.6129	0
0.6720	0.6625	0.6452	1
0.6638	0.6577	0.6452	2
0.6634	0.6547	0.6774	3
0.6547	0.6507	0.6774	4
0.6556	0.6423	0.6774	5
0.6433	0.6346	0.6774	6
0.6394	0.6293	0.7097	7
0.6344	0.6239	0.7419	8
0.6205	0.6206	0.7742	9
0.6047	0.6115	0.7097	10
0.6163	0.5970	0.7419	11
0.6022	0.6069	0.7097	12
0.5958	0.6009	0.7419	13
0.5789	0.5971	0.6774	14
0.5758	0.5962	0.6774	15
0.5662	0.5976	0.6774	16
0.5579	0.5926	0.6774	17
0.5577	0.5811	0.6452	18
0.5474	0.5880	0.6452	19
0.5249	0.5921	0.6774	20
0.5412	0.6075	0.6774	21
0.5154	0.6266	0.7097	22
0.5199	0.6063	0.6129	23
0.5150	0.6054	0.5806	24
0.5199	0.6107	0.6774	25
0.4823	0.5959	0.6129	26
0.4800	0.6581	0.6452	27
0.4732	0.6620	0.6129	28
0.4766	0.6284	0.6129	29
0.4889	0.6978	0.5806	30
0.4530	0.6636	0.5806	31
0.4320	0.6348	0.6129	32
0.4704	0.6326	0.6774	33
0.4487	0.6937	0.6774	34
0.4382	0.6423	0.5806	35
0.4035	0.6926	0.5806	36
0.4330	0.7225	0.5484	37
0.4367	0.7459	0.5806	38

Framework versions

• Transformers 4.35.2
• TensorFlow 2.14.0
• Datasets 2.15.0
• Tokenizers 0.15.0