ebayes/amazonas-fern-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: 1.2619
• Accuracy: 0.7969

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
4.9425	1.0	516	4.6442	0.2450
4.4394	2.0	1032	4.1936	0.3271
4.0242	3.0	1548	3.8147	0.3891
3.6368	4.0	2064	3.4881	0.4403
3.3168	5.0	2580	3.1849	0.4760
2.9583	6.0	3096	2.9087	0.5054
2.6652	7.0	3612	2.6435	0.5271
2.3696	8.0	4128	2.4352	0.5442
2.1322	9.0	4644	2.2335	0.5814
1.8776	10.0	5160	2.0674	0.5922
1.6773	11.0	5676	1.9474	0.6093
1.5136	12.0	6192	1.8081	0.6264
1.3341	13.0	6708	1.6931	0.6419
1.2215	14.0	7224	1.5986	0.6481
1.0886	15.0	7740	1.5309	0.6744
0.9762	16.0	8256	1.4605	0.6760
0.8322	17.0	8772	1.4038	0.6946
0.7767	18.0	9288	1.3404	0.6961
0.6943	19.0	9804	1.3143	0.7085
0.6011	20.0	10320	1.2708	0.7256
0.5585	21.0	10836	1.2777	0.7101
0.5014	22.0	11352	1.2744	0.7147
0.4704	23.0	11868	1.1907	0.7302
0.3934	24.0	12384	1.1748	0.7442
0.3616	25.0	12900	1.1897	0.7364
0.3274	26.0	13416	1.1648	0.7426
0.3062	27.0	13932	1.1899	0.7333
0.2726	28.0	14448	1.1192	0.7488
0.2425	29.0	14964	1.0887	0.7643
0.2316	30.0	15480	1.0957	0.7674
0.2321	31.0	15996	1.1206	0.7504
0.1828	32.0	16512	1.1901	0.7426
0.1675	33.0	17028	1.1317	0.7566
0.1572	34.0	17544	1.1530	0.7380
0.1453	35.0	18060	1.1519	0.7550
0.1385	36.0	18576	1.1358	0.7690
0.138	37.0	19092	1.1481	0.7628
0.1244	38.0	19608	1.1959	0.7442
0.1376	39.0	20124	1.1581	0.7659
0.107	40.0	20640	1.1979	0.7628
0.1219	41.0	21156	1.1915	0.7566
0.1105	42.0	21672	1.2247	0.7550
0.127	43.0	22188	1.1439	0.7736
0.1022	44.0	22704	1.1729	0.7535
0.1158	45.0	23220	1.2010	0.7535
0.1045	46.0	23736	1.2051	0.7519
0.103	47.0	24252	1.2006	0.7643
0.0967	48.0	24768	1.1888	0.7581
0.0963	49.0	25284	1.1814	0.7690
0.0923	50.0	25800	1.1566	0.7705
0.1071	51.0	26316	1.2239	0.7566
0.081	52.0	26832	1.2263	0.7581
0.0922	53.0	27348	1.1442	0.7628
0.0787	54.0	27864	1.2122	0.7705
0.0952	55.0	28380	1.3165	0.7504
0.1057	56.0	28896	1.2726	0.7550
0.1123	57.0	29412	1.2554	0.7597
0.0703	58.0	29928	1.1242	0.7752
0.094	59.0	30444	1.1734	0.7767
0.0699	60.0	30960	1.2493	0.7550
0.0731	61.0	31476	1.2414	0.7643
0.0888	62.0	31992	1.3430	0.7473
0.0737	63.0	32508	1.3174	0.7566
0.0825	64.0	33024	1.3129	0.7597
0.0821	65.0	33540	1.2509	0.7736
0.0817	66.0	34056	1.2020	0.7736
0.0754	67.0	34572	1.2447	0.7721
0.0854	68.0	35088	1.2626	0.7767
0.0755	69.0	35604	1.2202	0.7814
0.0847	70.0	36120	1.2525	0.7612
0.068	71.0	36636	1.2940	0.7674
0.0648	72.0	37152	1.2585	0.7736
0.0768	73.0	37668	1.2878	0.7597
0.0771	74.0	38184	1.2685	0.7659
0.0749	75.0	38700	1.2860	0.7721
0.0615	76.0	39216	1.3085	0.7643
0.0677	77.0	39732	1.3011	0.7674
0.0673	78.0	40248	1.2077	0.7814
0.0696	79.0	40764	1.2118	0.7860
0.0714	80.0	41280	1.1952	0.7767
0.0624	81.0	41796	1.2575	0.7690
0.0604	82.0	42312	1.2816	0.7736
0.0641	83.0	42828	1.3230	0.7643
0.0574	84.0	43344	1.2876	0.7752
0.0621	85.0	43860	1.2576	0.7845
0.0639	86.0	44376	1.2486	0.7705
0.0538	87.0	44892	1.2192	0.7845
0.0518	88.0	45408	1.2171	0.7674
0.0563	89.0	45924	1.3201	0.7581
0.0531	90.0	46440	1.2414	0.7736
0.0431	91.0	46956	1.3059	0.7736
0.0655	92.0	47472	1.3307	0.7566
0.0595	93.0	47988	1.2927	0.7659
0.0707	94.0	48504	1.2667	0.7628
0.0517	95.0	49020	1.2957	0.7597
0.0579	96.0	49536	1.3340	0.7643
0.0492	97.0	50052	1.3588	0.7535
0.0472	98.0	50568	1.3074	0.7612
0.0542	99.0	51084	1.2657	0.7705
0.0689	100.0	51600	1.2943	0.7752
0.0464	101.0	52116	1.2386	0.7953
0.0589	102.0	52632	1.2717	0.7767
0.0488	103.0	53148	1.2678	0.7814
0.0554	104.0	53664	1.2711	0.7783
0.0502	105.0	54180	1.2746	0.7721
0.0383	106.0	54696	1.3002	0.7798
0.0531	107.0	55212	1.2636	0.7891
0.0379	108.0	55728	1.3156	0.7721
0.042	109.0	56244	1.3668	0.7674
0.0543	110.0	56760	1.2883	0.7783
0.0522	111.0	57276	1.2913	0.7783
0.0469	112.0	57792	1.2847	0.7767
0.0598	113.0	58308	1.2642	0.7876
0.0472	114.0	58824	1.3264	0.7752
0.0405	115.0	59340	1.2648	0.7891
0.0434	116.0	59856	1.3059	0.7798
0.0481	117.0	60372	1.3373	0.7736
0.0454	118.0	60888	1.3237	0.7736
0.0504	119.0	61404	1.2956	0.7736
0.0495	120.0	61920	1.3504	0.7705
0.0424	121.0	62436	1.2852	0.7891
0.0493	122.0	62952	1.2621	0.7891
0.0421	123.0	63468	1.2755	0.7752
0.0339	124.0	63984	1.2914	0.7891
0.0415	125.0	64500	1.2959	0.7876
0.035	126.0	65016	1.2724	0.7891
0.0342	127.0	65532	1.2564	0.7798
0.0411	128.0	66048	1.2493	0.7798
0.0345	129.0	66564	1.2490	0.7891
0.0365	130.0	67080	1.2560	0.7969
0.0304	131.0	67596	1.2466	0.7876
0.0361	132.0	68112	1.2691	0.7953
0.0387	133.0	68628	1.2849	0.7860
0.0361	134.0	69144	1.2731	0.7891
0.0334	135.0	69660	1.2649	0.7907
0.0368	136.0	70176	1.2562	0.7953
0.0395	137.0	70692	1.2851	0.7891
0.0397	138.0	71208	1.2767	0.7891
0.0433	139.0	71724	1.2383	0.8031
0.031	140.0	72240	1.2429	0.7984
0.0326	141.0	72756	1.2389	0.8047
0.0369	142.0	73272	1.2475	0.8
0.0436	143.0	73788	1.2762	0.7907
0.031	144.0	74304	1.2772	0.7891
0.0278	145.0	74820	1.2513	0.7984
0.0345	146.0	75336	1.2639	0.7969
0.034	147.0	75852	1.2679	0.7953
0.0331	148.0	76368	1.2682	0.7938
0.028	149.0	76884	1.2634	0.7953
0.0356	150.0	77400	1.2619	0.7969

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1