leaves

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the defect dataset. It achieves the following results on the evaluation set:

• Loss: 0.0012
• Accuracy: 1.0

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:

• learning_rate: 0.0002
• train_batch_size: 10
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2249	1.25	10	0.0323	1.0
0.0177	2.5	20	0.0112	1.0
0.0086	3.75	30	0.0075	1.0
0.0063	5.0	40	0.0059	1.0
0.0051	6.25	50	0.0050	1.0
0.0045	7.5	60	0.0044	1.0
0.004	8.75	70	0.0040	1.0
0.0036	10.0	80	0.0036	1.0
0.0033	11.25	90	0.0034	1.0
0.0031	12.5	100	0.0031	1.0
0.0028	13.75	110	0.0029	1.0
0.0026	15.0	120	0.0027	1.0
0.0025	16.25	130	0.0025	1.0
0.0023	17.5	140	0.0024	1.0
0.0022	18.75	150	0.0023	1.0
0.0021	20.0	160	0.0021	1.0
0.002	21.25	170	0.0020	1.0
0.0019	22.5	180	0.0019	1.0
0.0018	23.75	190	0.0019	1.0
0.0017	25.0	200	0.0018	1.0
0.0016	26.25	210	0.0017	1.0
0.0016	27.5	220	0.0017	1.0
0.0015	28.75	230	0.0016	1.0
0.0015	30.0	240	0.0015	1.0
0.0014	31.25	250	0.0015	1.0
0.0014	32.5	260	0.0015	1.0
0.0013	33.75	270	0.0014	1.0
0.0013	35.0	280	0.0014	1.0
0.0013	36.25	290	0.0014	1.0
0.0013	37.5	300	0.0013	1.0
0.0012	38.75	310	0.0013	1.0
0.0012	40.0	320	0.0013	1.0
0.0012	41.25	330	0.0013	1.0
0.0012	42.5	340	0.0013	1.0
0.0012	43.75	350	0.0012	1.0
0.0012	45.0	360	0.0012	1.0
0.0011	46.25	370	0.0012	1.0
0.0012	47.5	380	0.0012	1.0
0.0011	48.75	390	0.0012	1.0
0.0011	50.0	400	0.0012	1.0

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3