segmentation_model_50ep

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0063
• Mean Iou: 0.9981
• Mean Accuracy: 1.0
• Overall Accuracy: 1.0
• Per Category Iou: [0.9980539089681099]
• Per Category 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: 6e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.049	1.2195	100	0.0429	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.029	2.4390	200	0.0274	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0171	3.6585	300	0.0192	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0158	4.8780	400	0.0187	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.019	6.0976	500	0.0169	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.013	7.3171	600	0.0125	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0131	8.5366	700	0.0124	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0111	9.7561	800	0.0101	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0089	10.9756	900	0.0102	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0106	12.1951	1000	0.0088	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0093	13.4146	1100	0.0084	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0088	14.6341	1200	0.0079	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0084	15.8537	1300	0.0080	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0089	17.0732	1400	0.0077	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0087	18.2927	1500	0.0069	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0072	19.5122	1600	0.0075	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0087	20.7317	1700	0.0068	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0094	21.9512	1800	0.0070	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0074	23.1707	1900	0.0070	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0075	24.3902	2000	0.0069	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.007	25.6098	2100	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0053	26.8293	2200	0.0065	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0072	28.0488	2300	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0082	29.2683	2400	0.0065	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0065	30.4878	2500	0.0066	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0054	31.7073	2600	0.0065	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0079	32.9268	2700	0.0066	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.006	34.1463	2800	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0053	35.3659	2900	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0059	36.5854	3000	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0061	37.8049	3100	0.0066	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.007	39.0244	3200	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0058	40.2439	3300	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0055	41.4634	3400	0.0062	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0068	42.6829	3500	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0058	43.9024	3600	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0061	45.1220	3700	0.0064	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.003	46.3415	3800	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0058	47.5610	3900	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.0087	48.7805	4000	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]
0.006	50.0	4100	0.0063	0.9981	1.0	1.0	[0.9980539089681099]	[1.0]

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.0
• Datasets 2.4.0
• Tokenizers 0.20.3