Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
7.7174	0.9874	59	7.7848	0.0037
7.6016	1.9916	119	7.7339	0.0037
7.4761	2.9958	179	7.6441	0.0037
7.2852	4.0	239	7.5057	0.0037
7.083	4.9874	298	7.3286	0.0037
6.8119	5.9916	358	7.1090	0.0037
6.5497	6.9958	418	6.8711	0.0037
6.1656	8.0	478	6.6169	0.0037
5.8334	8.9874	537	6.3286	0.0037
5.3878	9.9916	597	6.0292	0.0037
5.0134	10.9958	657	5.7486	0.0037
4.6087	12.0	717	5.4834	0.0037
4.2544	12.9874	776	5.2186	0.0037
3.8669	13.9916	836	4.9842	0.0037
3.5993	14.9958	896	4.7566	0.0037
3.2331	16.0	956	4.5623	0.0037
2.9124	16.9874	1015	4.3663	0.0037
2.6122	17.9916	1075	4.1944	0.0037
2.466	18.9958	1135	4.0160	0.0037
2.2074	20.0	1195	3.8582	0.0037
2.0851	20.9874	1254	3.7160	0.0037
1.8354	21.9916	1314	3.5740	0.0037
1.7343	22.9958	1374	3.4548	0.0037
1.5804	24.0	1434	3.3600	0.0037
1.3193	24.9874	1493	3.2336	0.0037
1.328	25.9916	1553	3.1294	0.0037
1.163	26.9958	1613	3.0355	0.0037
1.0761	28.0	1673	2.9737	0.0037
0.9834	28.9874	1732	2.8952	0.0037
0.9141	29.9916	1792	2.7900	0.0037
0.8862	30.9958	1852	2.7381	0.0037
0.7757	32.0	1912	2.6868	0.0037
0.7475	32.9874	1971	2.6134	0.0037
0.6518	33.9916	2031	2.5770	0.0037
0.6766	34.9958	2091	2.5278	0.0037
0.5741	36.0	2151	2.5009	0.0037
0.5877	36.9874	2210	2.4436	0.0037
0.4996	37.9916	2270	2.4148	0.0037
0.5316	38.9958	2330	2.3809	0.0037
0.4896	40.0	2390	2.3330	0.0037
0.501	40.9874	2449	2.3055	0.0037
0.4052	41.9916	2509	2.3000	0.0037
0.398	42.9958	2569	2.2854	0.0037
0.3702	44.0	2629	2.2536	0.0037
0.3629	44.9874	2688	2.2342	0.0037
0.3729	45.9916	2748	2.2190	0.0037
0.3206	46.9958	2808	2.2078	0.0037
0.38	48.0	2868	2.1726	0.0037
0.3379	48.9874	2927	2.1600	0.0037
0.3248	49.9916	2987	2.1453	0.0037
0.3577	50.9958	3047	2.1153	0.0037
0.2946	52.0	3107	2.1232	0.0037
0.2938	52.9874	3166	2.1076	0.0037
0.289	53.9916	3226	2.0892	0.0037
0.3044	54.9958	3286	2.0692	0.0037
0.277	56.0	3346	2.0667	0.0037
0.2774	56.9874	3405	2.0554	0.0037
0.2717	57.9916	3465	2.0369	0.0037
0.2722	58.9958	3525	2.0261	0.0037
0.2325	60.0	3585	2.0419	0.0037
0.2387	60.9874	3644	2.0073	0.0037
0.2343	61.9916	3704	2.0230	0.0037
0.2281	62.9958	3764	2.0228	0.0037
0.2597	64.0	3824	1.9956	0.0037
0.223	64.9874	3883	1.9902	0.0037
0.2213	65.9916	3943	1.9778	0.0037
0.1835	66.9958	4003	1.9945	0.0037
0.2247	68.0	4063	1.9703	0.0037
0.1819	68.9874	4122	1.9623	0.0037
0.2096	69.9916	4182	1.9686	0.0037
0.186	70.9958	4242	1.9764	0.0037
0.1956	72.0	4302	1.9606	0.0037
0.197	72.9874	4361	1.9432	0.0037
0.1867	73.9916	4421	1.9461	0.0037
0.1994	74.9958	4481	1.9547	0.0037
0.1631	76.0	4541	1.9373	0.0037
0.184	76.9874	4600	1.9329	0.0037
0.1518	77.9916	4660	1.9355	0.0037
0.1774	78.9958	4720	1.9367	0.0037
0.1558	80.0	4780	1.9211	0.0037
0.1859	80.9874	4839	1.9256	0.0037
0.1673	81.9916	4899	1.9271	0.0037
0.1531	82.9958	4959	1.9332	0.0037
0.1763	84.0	5019	1.9154	0.0037
0.1594	84.9874	5078	1.9143	0.0037
0.17	85.9916	5138	1.9098	0.0037
0.1246	86.9958	5198	1.9123	0.0037
0.1699	88.0	5258	1.9066	0.0037
0.1627	88.9874	5317	1.9054	0.0037
0.1663	89.9916	5377	1.9040	0.0037
0.1349	90.9958	5437	1.9031	0.0037
0.1578	92.0	5497	1.9065	0.0037
0.1553	92.9874	5556	1.8997	0.0037
0.1393	93.9916	5616	1.8972	0.0037
0.1652	94.9958	5676	1.8960	0.0037
0.1677	96.0	5736	1.9002	0.0037
0.1544	96.9874	5795	1.8966	0.0037
0.1359	97.9916	5855	1.8966	0.0037
0.1495	98.7448	5900	1.8965	0.0037

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

viniFiedler/vit-base-patch16-224-finetuned-eurosat

vit-base-patch16-224-finetuned-eurosat

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

viniFiedler/
vit-base-patch16-224-finetuned-eurosat