meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_7

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: 0.1612
• Accuracy: 0.9533

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1056	1.0	21	1.0902	0.4206
1.0884	2.0	42	1.0625	0.4766
1.0199	3.0	63	1.0114	0.5202
0.9636	4.0	84	0.9735	0.5234
0.8789	5.0	105	0.9093	0.5701
0.8625	6.0	126	0.8850	0.6044
0.7607	7.0	147	0.8773	0.6106
0.7615	8.0	168	0.8370	0.5950
0.7052	9.0	189	0.8290	0.6231
0.6378	10.0	210	0.6312	0.7508
0.5741	11.0	231	0.6255	0.7508
0.5034	12.0	252	0.7393	0.6511
0.5886	13.0	273	0.6083	0.7664
0.4313	14.0	294	0.5113	0.7975
0.4542	15.0	315	0.5826	0.7632
0.3551	16.0	336	0.6452	0.7664
0.3613	17.0	357	0.5993	0.7601
0.3627	18.0	378	0.4192	0.8536
0.2659	19.0	399	0.4967	0.8131
0.2783	20.0	420	0.4777	0.8287
0.2618	21.0	441	0.5573	0.7850
0.2962	22.0	462	0.4956	0.7975
0.3321	23.0	483	0.3398	0.8723
0.3306	24.0	504	0.4910	0.8224
0.2813	25.0	525	0.3536	0.8536
0.189	26.0	546	0.2645	0.8910
0.2114	27.0	567	0.5280	0.8224
0.2027	28.0	588	0.5607	0.8100
0.204	29.0	609	0.3179	0.8879
0.1844	30.0	630	0.2999	0.8972
0.1655	31.0	651	0.3656	0.8785
0.3034	32.0	672	0.2920	0.8941
0.1617	33.0	693	0.3290	0.8847
0.1588	34.0	714	0.2659	0.8972
0.1263	35.0	735	0.4091	0.8505
0.145	36.0	756	0.3294	0.8785
0.1413	37.0	777	0.2408	0.9128
0.1309	38.0	798	0.2980	0.8910
0.1316	39.0	819	0.3839	0.8723
0.1508	40.0	840	0.2546	0.9034
0.1078	41.0	861	0.2317	0.9221
0.1263	42.0	882	0.3212	0.8910
0.142	43.0	903	0.3513	0.8660
0.108	44.0	924	0.2291	0.9034
0.1297	45.0	945	0.3755	0.8692
0.1195	46.0	966	0.2830	0.9065
0.1029	47.0	987	0.3560	0.8785
0.0988	48.0	1008	0.4380	0.8536
0.0931	49.0	1029	0.1965	0.9283
0.0787	50.0	1050	0.3069	0.9003
0.0925	51.0	1071	0.3059	0.9065
0.0999	52.0	1092	0.2761	0.9097
0.1079	53.0	1113	0.4334	0.8598
0.0967	54.0	1134	0.2761	0.9097
0.2187	55.0	1155	0.3166	0.8941
0.2928	56.0	1176	0.1629	0.9377
0.0813	57.0	1197	0.2661	0.9159
0.0898	58.0	1218	0.1690	0.9315
0.0741	59.0	1239	0.2331	0.9190
0.0646	60.0	1260	0.1978	0.9221
0.0576	61.0	1281	0.2079	0.9377
0.0676	62.0	1302	0.2102	0.9315
0.0716	63.0	1323	0.2085	0.9315
0.1935	64.0	1344	0.2461	0.9315
0.0633	65.0	1365	0.1748	0.9346
0.062	66.0	1386	0.2004	0.9315
0.0757	67.0	1407	0.2812	0.9034
0.0548	68.0	1428	0.1503	0.9502
0.0583	69.0	1449	0.3126	0.9097
0.2111	70.0	1470	0.2005	0.9470
0.0648	71.0	1491	0.1651	0.9533
0.0477	72.0	1512	0.2301	0.9346
0.0438	73.0	1533	0.2156	0.9252
0.0631	74.0	1554	0.2343	0.9283
0.0498	75.0	1575	0.2876	0.9065
0.0605	76.0	1596	0.2125	0.9283
0.0604	77.0	1617	0.1966	0.9408
0.0509	78.0	1638	0.2012	0.9470
0.0452	79.0	1659	0.2409	0.9315
0.0419	80.0	1680	0.2316	0.9283
0.0306	81.0	1701	0.2379	0.9346
0.0403	82.0	1722	0.2128	0.9346
0.0484	83.0	1743	0.1239	0.9502
0.0523	84.0	1764	0.2109	0.9408
0.0445	85.0	1785	0.2261	0.9283
0.0442	86.0	1806	0.1753	0.9564
0.0274	87.0	1827	0.1932	0.9408
0.0395	88.0	1848	0.1622	0.9439
0.0587	89.0	1869	0.2000	0.9408
0.0299	90.0	1890	0.2348	0.9221
0.033	91.0	1911	0.1726	0.9439
0.032	92.0	1932	0.1737	0.9470
0.0275	93.0	1953	0.1737	0.9470
0.0324	94.0	1974	0.2660	0.9159
0.0256	95.0	1995	0.1639	0.9408
0.0289	96.0	2016	0.1312	0.9502
0.0304	97.0	2037	0.1784	0.9439
0.0411	98.0	2058	0.1326	0.9626
0.0256	99.0	2079	0.1724	0.9470
0.0382	100.0	2100	0.1612	0.9533

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1