ebayes/tree-crown-latest

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

• Loss: 0.1368
• Accuracy: 0.95

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: 2e-05
• train_batch_size: 10
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	17	2.0491	0.45
No log	2.0	34	1.7960	0.45
No log	3.0	51	1.6265	0.5
No log	4.0	68	1.4328	0.6
No log	5.0	85	1.3004	0.7
No log	6.0	102	1.1381	0.8
No log	7.0	119	1.0114	0.9
No log	8.0	136	0.9116	0.9
No log	9.0	153	0.8490	0.9
No log	10.0	170	0.7989	0.9
No log	11.0	187	0.7392	0.9
No log	12.0	204	0.6834	0.9
No log	13.0	221	0.6688	0.9
No log	14.0	238	0.6311	0.9
No log	15.0	255	0.5847	0.9
No log	16.0	272	0.5544	0.9
No log	17.0	289	0.5521	0.9
No log	18.0	306	0.5319	0.9
No log	19.0	323	0.5228	0.9
No log	20.0	340	0.4746	0.95
No log	21.0	357	0.4913	0.95
No log	22.0	374	0.4453	0.9
No log	23.0	391	0.4333	0.95
No log	24.0	408	0.4124	0.95
No log	25.0	425	0.4303	0.95
No log	26.0	442	0.4094	0.95
No log	27.0	459	0.3597	0.95
No log	28.0	476	0.3644	0.95
No log	29.0	493	0.3723	0.95
0.6158	30.0	510	0.3200	0.95
0.6158	31.0	527	0.3223	0.95
0.6158	32.0	544	0.3119	0.95
0.6158	33.0	561	0.3002	0.95
0.6158	34.0	578	0.2867	0.95
0.6158	35.0	595	0.3419	0.9
0.6158	36.0	612	0.3020	0.9
0.6158	37.0	629	0.2393	0.95
0.6158	38.0	646	0.3202	0.95
0.6158	39.0	663	0.2727	0.95
0.6158	40.0	680	0.2691	0.95
0.6158	41.0	697	0.3346	0.9
0.6158	42.0	714	0.2446	0.95
0.6158	43.0	731	0.3373	0.9
0.6158	44.0	748	0.2904	0.95
0.6158	45.0	765	0.2307	0.95
0.6158	46.0	782	0.2346	0.95
0.6158	47.0	799	0.2314	0.95
0.6158	48.0	816	0.2209	0.95
0.6158	49.0	833	0.2233	0.95
0.6158	50.0	850	0.2225	0.95
0.6158	51.0	867	0.2326	0.95
0.6158	52.0	884	0.2233	0.95
0.6158	53.0	901	0.2248	0.95
0.6158	54.0	918	0.2268	0.95
0.6158	55.0	935	0.2130	0.95
0.6158	56.0	952	0.2164	0.95
0.6158	57.0	969	0.1972	0.95
0.6158	58.0	986	0.2374	0.95
0.1237	59.0	1003	0.2425	0.95
0.1237	60.0	1020	0.1907	0.95
0.1237	61.0	1037	0.3103	0.9
0.1237	62.0	1054	0.2309	0.95
0.1237	63.0	1071	0.1982	0.95
0.1237	64.0	1088	0.2661	0.9
0.1237	65.0	1105	0.1739	0.95
0.1237	66.0	1122	0.1958	0.95
0.1237	67.0	1139	0.1729	0.95
0.1237	68.0	1156	0.1884	0.95
0.1237	69.0	1173	0.1958	0.95
0.1237	70.0	1190	0.1949	0.95
0.1237	71.0	1207	0.1700	0.95
0.1237	72.0	1224	0.1770	0.95
0.1237	73.0	1241	0.1789	0.95
0.1237	74.0	1258	0.2202	0.95
0.1237	75.0	1275	0.2005	0.95
0.1237	76.0	1292	0.1734	0.95
0.1237	77.0	1309	0.1633	0.95
0.1237	78.0	1326	0.1468	0.95
0.1237	79.0	1343	0.1619	0.95
0.1237	80.0	1360	0.1706	0.95
0.1237	81.0	1377	0.1745	0.95
0.1237	82.0	1394	0.2146	0.95
0.1237	83.0	1411	0.1990	0.95
0.1237	84.0	1428	0.1682	0.95
0.1237	85.0	1445	0.1891	0.95
0.1237	86.0	1462	0.1646	0.95
0.1237	87.0	1479	0.2234	0.95
0.1237	88.0	1496	0.2469	0.9
0.0723	89.0	1513	0.1513	0.95
0.0723	90.0	1530	0.1638	0.95
0.0723	91.0	1547	0.1706	0.95
0.0723	92.0	1564	0.1578	0.95
0.0723	93.0	1581	0.1465	0.95
0.0723	94.0	1598	0.1433	0.95
0.0723	95.0	1615	0.1438	0.95
0.0723	96.0	1632	0.1543	0.95
0.0723	97.0	1649	0.1528	0.95
0.0723	98.0	1666	0.1807	0.95
0.0723	99.0	1683	0.2142	0.95
0.0723	100.0	1700	0.2056	0.95
0.0723	101.0	1717	0.1817	0.95
0.0723	102.0	1734	0.2271	0.95
0.0723	103.0	1751	0.2560	0.9
0.0723	104.0	1768	0.1631	0.95
0.0723	105.0	1785	0.1828	0.95
0.0723	106.0	1802	0.2608	0.95
0.0723	107.0	1819	0.2562	0.95
0.0723	108.0	1836	0.1666	0.95
0.0723	109.0	1853	0.1619	0.95
0.0723	110.0	1870	0.1504	0.95
0.0723	111.0	1887	0.1433	0.95
0.0723	112.0	1904	0.1457	0.95
0.0723	113.0	1921	0.1288	1.0
0.0723	114.0	1938	0.1401	1.0
0.0723	115.0	1955	0.1281	0.95
0.0723	116.0	1972	0.1267	0.95
0.0723	117.0	1989	0.1288	0.95
0.051	118.0	2006	0.1473	0.95
0.051	119.0	2023	0.1106	1.0
0.051	120.0	2040	0.1097	1.0
0.051	121.0	2057	0.1379	1.0
0.051	122.0	2074	0.1347	1.0
0.051	123.0	2091	0.1302	0.95
0.051	124.0	2108	0.1599	0.95
0.051	125.0	2125	0.1574	0.95
0.051	126.0	2142	0.1541	0.95
0.051	127.0	2159	0.1517	0.95
0.051	128.0	2176	0.1462	0.95
0.051	129.0	2193	0.1574	0.95
0.051	130.0	2210	0.1598	0.95
0.051	131.0	2227	0.1520	0.95
0.051	132.0	2244	0.1595	0.95
0.051	133.0	2261	0.1555	0.95
0.051	134.0	2278	0.1515	0.95
0.051	135.0	2295	0.1686	0.95
0.051	136.0	2312	0.1670	0.95
0.051	137.0	2329	0.1533	0.95
0.051	138.0	2346	0.1472	0.95
0.051	139.0	2363	0.1530	0.95
0.051	140.0	2380	0.1563	0.95
0.051	141.0	2397	0.1500	0.95
0.051	142.0	2414	0.1462	0.95
0.051	143.0	2431	0.1432	0.95
0.051	144.0	2448	0.1417	0.95
0.051	145.0	2465	0.1414	0.95
0.051	146.0	2482	0.1362	0.95
0.051	147.0	2499	0.1358	0.95
0.0491	148.0	2516	0.1366	0.95
0.0491	149.0	2533	0.1367	0.95
0.0491	150.0	2550	0.1368	0.95

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1