meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_4

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: 0.2286
• Accuracy: 0.9315

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: 64
• 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
1.0983	1.0	21	1.0790	0.4517
1.0782	2.0	42	1.0505	0.4891
1.0069	3.0	63	0.9886	0.5639
0.9347	4.0	84	0.9224	0.5794
0.8519	5.0	105	0.8643	0.6324
0.7989	6.0	126	0.7891	0.6667
0.695	7.0	147	0.8411	0.5919
0.6872	8.0	168	0.7448	0.6978
0.5872	9.0	189	0.7257	0.6854
0.6367	10.0	210	0.6716	0.7227
0.5617	11.0	231	0.6554	0.7321
0.5104	12.0	252	0.6906	0.7134
0.4581	13.0	273	0.6179	0.7601
0.5126	14.0	294	0.6726	0.7321
0.5078	15.0	315	0.5767	0.7819
0.3308	16.0	336	0.5843	0.7632
0.3396	17.0	357	0.5064	0.8287
0.3137	18.0	378	0.7024	0.7414
0.2981	19.0	399	0.4692	0.8411
0.2593	20.0	420	0.7424	0.7352
0.5048	21.0	441	0.4293	0.8411
0.2252	22.0	462	0.5090	0.7975
0.261	23.0	483	0.4810	0.8505
0.2575	24.0	504	0.4389	0.8442
0.176	25.0	525	0.4528	0.8287
0.2075	26.0	546	0.4764	0.8349
0.2069	27.0	567	0.5269	0.8162
0.2306	28.0	588	0.4180	0.8536
0.1564	29.0	609	0.3936	0.8505
0.1632	30.0	630	0.4111	0.8474
0.1923	31.0	651	0.3862	0.8629
0.1708	32.0	672	0.4155	0.8474
0.1744	33.0	693	0.4346	0.8505
0.1381	34.0	714	0.3908	0.8660
0.1668	35.0	735	0.5195	0.8255
0.146	36.0	756	0.4954	0.8255
0.1288	37.0	777	0.4273	0.8505
0.1595	38.0	798	0.3274	0.9034
0.107	39.0	819	0.4688	0.8380
0.1437	40.0	840	0.4269	0.8692
0.1432	41.0	861	0.5034	0.8224
0.1512	42.0	882	0.4046	0.8629
0.1156	43.0	903	0.3166	0.8941
0.1173	44.0	924	0.4023	0.8598
0.1366	45.0	945	0.3869	0.8692
0.1361	46.0	966	0.5182	0.8349
0.2102	47.0	987	0.5841	0.8069
0.1504	48.0	1008	0.4403	0.8598
0.1272	49.0	1029	0.3771	0.8754
0.113	50.0	1050	0.3809	0.8785
0.0884	51.0	1071	0.4446	0.8629
0.0951	52.0	1092	0.3689	0.8847
0.0822	53.0	1113	0.4412	0.8629
0.0999	54.0	1134	0.3758	0.8785
0.1321	55.0	1155	0.3982	0.8598
0.0877	56.0	1176	0.3068	0.9034
0.0736	57.0	1197	0.3981	0.8910
0.0903	58.0	1218	0.2888	0.8972
0.0842	59.0	1239	0.3552	0.8816
0.0911	60.0	1260	0.4368	0.8536
0.0847	61.0	1281	0.3188	0.9065
0.066	62.0	1302	0.3727	0.8910
0.059	63.0	1323	0.3373	0.8910
0.0755	64.0	1344	0.3241	0.9003
0.0598	65.0	1365	0.3641	0.9003
0.0561	66.0	1386	0.3889	0.8847
0.0796	67.0	1407	0.3633	0.9065
0.0736	68.0	1428	0.3682	0.8816
0.0723	69.0	1449	0.4165	0.8723
0.0625	70.0	1470	0.2747	0.9159
0.0714	71.0	1491	0.3374	0.8972
0.0723	72.0	1512	0.3534	0.9003
0.0551	73.0	1533	0.3764	0.8785
0.0417	74.0	1554	0.2348	0.9252
0.0513	75.0	1575	0.3214	0.9190
0.0534	76.0	1596	0.2440	0.9346
0.046	77.0	1617	0.3385	0.9159
0.0539	78.0	1638	0.3516	0.9003
0.055	79.0	1659	0.2836	0.9221
0.0686	80.0	1680	0.3542	0.8910
0.0589	81.0	1701	0.2077	0.9315
0.0505	82.0	1722	0.3094	0.9034
0.0332	83.0	1743	0.2678	0.9252
0.0504	84.0	1764	0.3099	0.9159
0.0523	85.0	1785	0.1953	0.9315
0.0291	86.0	1806	0.2377	0.9283
0.0499	87.0	1827	0.2891	0.9221
0.038	88.0	1848	0.2898	0.9159
0.0597	89.0	1869	0.2722	0.9190
0.0367	90.0	1890	0.3110	0.9221
0.0647	91.0	1911	0.2432	0.9346
0.0371	92.0	1932	0.2276	0.9377
0.0286	93.0	1953	0.2281	0.9346
0.0271	94.0	1974	0.2766	0.9221
0.0339	95.0	1995	0.2637	0.9283
0.0211	96.0	2016	0.2434	0.9315
0.0441	97.0	2037	0.3146	0.8941
0.0516	98.0	2058	0.2273	0.9439
0.0311	99.0	2079	0.2151	0.9377
0.0269	100.0	2100	0.2286	0.9315

Framework versions

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