test_os_counties

This model is a fine-tuned version of nvidia/mit-b0 on the rwood-97/os_counties dataset. It achieves the following results on the evaluation set:

• Loss: 1.8997
• Mean Iou: 0.1075
• Mean Accuracy: 0.4992
• Overall Accuracy: 0.2118
• Accuracy Non-map: 0.9899
• Accuracy Map: 0.0084
• Iou Non-map: 0.2065
• Iou Map: 0.0084

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Non-map	Accuracy Map	Iou Non-map	Iou Map
0.4081	0.41	20	0.8267	0.2101	0.4981	0.3478	0.7548	0.2414	0.1934	0.2268
0.3939	0.82	40	0.8190	0.2387	0.4978	0.3898	0.6821	0.3134	0.1881	0.2894
0.3319	1.22	60	0.9487	0.1579	0.4976	0.2759	0.8762	0.1191	0.2005	0.1153
0.3234	1.63	80	0.9275	0.1847	0.4974	0.3120	0.8138	0.1809	0.1969	0.1725
0.3932	2.04	100	0.9053	0.1892	0.4974	0.3183	0.8031	0.1916	0.1962	0.1822
0.3412	2.45	120	0.8265	0.2385	0.4973	0.3895	0.6814	0.3132	0.1878	0.2891
0.2976	2.86	140	1.3713	0.1127	0.4987	0.2182	0.9778	0.0197	0.2058	0.0195
0.2803	3.27	160	1.6436	0.1095	0.4993	0.2143	0.9860	0.0126	0.2064	0.0125
0.3686	3.67	180	1.2379	0.1221	0.4982	0.2298	0.9564	0.0399	0.2047	0.0395
0.3434	4.08	200	1.1857	0.1385	0.4978	0.2507	0.9197	0.0758	0.2028	0.0743
0.2951	4.49	220	1.3947	0.1160	0.4986	0.2223	0.9704	0.0268	0.2054	0.0266
0.2333	4.9	240	1.5480	0.1170	0.4988	0.2236	0.9687	0.0288	0.2054	0.0286
0.2491	5.31	260	1.6563	0.1136	0.4990	0.2194	0.9764	0.0215	0.2058	0.0214
0.2706	5.71	280	1.9766	0.1058	0.4995	0.2098	0.9942	0.0048	0.2068	0.0048
0.2171	6.12	300	1.6191	0.1117	0.4989	0.2170	0.9804	0.0175	0.2060	0.0174
0.2352	6.53	320	1.8075	0.1102	0.4992	0.2151	0.9842	0.0141	0.2062	0.0141
0.2953	6.94	340	1.4709	0.1178	0.4986	0.2245	0.9667	0.0305	0.2053	0.0303
0.2799	7.35	360	1.3843	0.1300	0.4982	0.2399	0.9392	0.0571	0.2038	0.0562
0.2285	7.76	380	1.7799	0.1101	0.4991	0.2150	0.9842	0.0140	0.2062	0.0139
0.3461	8.16	400	1.7282	0.1106	0.4989	0.2157	0.9826	0.0153	0.2061	0.0152
0.1867	8.57	420	2.3356	0.1042	0.4997	0.2079	0.9981	0.0014	0.2070	0.0014
0.1731	8.98	440	2.1465	0.1050	0.4996	0.2089	0.9959	0.0032	0.2069	0.0032
0.224	9.39	460	2.3467	0.1047	0.4996	0.2084	0.9969	0.0024	0.2070	0.0024
0.2199	9.8	480	1.8997	0.1075	0.4992	0.2118	0.9899	0.0084	0.2065	0.0084

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0
• Datasets 2.14.5
• Tokenizers 0.14.1