DownwardSpiral33/hands_palms_classifier_wd

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: 0.3103
• Validation Loss: 0.6071
• Train Accuracy: 0.6774
• Epoch: 49

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': 1e-05, 'decay_steps': 17400, '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	Validation Loss	Train Accuracy	Epoch
0.6957	0.6682	0.5806	0
0.6842	0.6571	0.6452	1
0.6734	0.6509	0.6452	2
0.6644	0.6421	0.6452	3
0.6585	0.6328	0.6129	4
0.6490	0.6303	0.6452	5
0.6531	0.6279	0.7419	6
0.6381	0.6177	0.7419	7
0.6290	0.6110	0.6774	8
0.6220	0.6163	0.6774	9
0.6197	0.6053	0.7097	10
0.6127	0.6111	0.7097	11
0.6075	0.6126	0.7097	12
0.5984	0.5985	0.6774	13
0.5957	0.5833	0.7097	14
0.5927	0.5927	0.6129	15
0.5779	0.5764	0.7097	16
0.5609	0.5824	0.6452	17
0.5569	0.5876	0.7097	18
0.5597	0.5883	0.6774	19
0.5424	0.5897	0.6774	20
0.5420	0.5780	0.7097	21
0.5413	0.5812	0.6774	22
0.5327	0.6057	0.6774	23
0.5362	0.5907	0.6452	24
0.5191	0.6090	0.6129	25
0.4838	0.6038	0.6452	26
0.5049	0.5659	0.7419	27
0.4900	0.5874	0.6774	28
0.4980	0.5805	0.6774	29
0.4809	0.5775	0.6774	30
0.4708	0.5575	0.7097	31
0.4652	0.5569	0.6774	32
0.4326	0.6339	0.6452	33
0.4600	0.5935	0.6452	34
0.4514	0.5497	0.7097	35
0.4137	0.5883	0.6774	36
0.3975	0.5795	0.7097	37
0.4113	0.6108	0.6774	38
0.4169	0.6087	0.6452	39
0.3860	0.6026	0.6774	40
0.4146	0.6108	0.6452	41
0.4226	0.7029	0.6774	42
0.4039	0.6176	0.6774	43
0.3793	0.5920	0.6452	44
0.3516	0.5921	0.7097	45
0.3382	0.6763	0.5806	46
0.3818	0.7219	0.6774	47
0.3428	0.6276	0.6452	48
0.3103	0.6071	0.6774	49

Framework versions

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