meat_calssify_fresh_crop_fixed_epoch100_V_0_3

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: 0.8015
• Accuracy: 0.7595

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
1.1038	1.0	10	1.1003	0.3165
1.0874	2.0	20	1.0824	0.4367
1.0699	3.0	30	1.0695	0.4051
1.0363	4.0	40	1.0423	0.4620
0.9912	5.0	50	0.9911	0.5253
0.9378	6.0	60	0.9630	0.5380
0.8829	7.0	70	0.9239	0.5696
0.8168	8.0	80	0.9127	0.5759
0.758	9.0	90	0.8583	0.6392
0.7032	10.0	100	0.7911	0.6772
0.6348	11.0	110	0.8342	0.5949
0.6082	12.0	120	0.8187	0.6203
0.5936	13.0	130	0.6830	0.7468
0.5726	14.0	140	0.8194	0.6962
0.5774	15.0	150	0.7164	0.6709
0.4617	16.0	160	0.8145	0.6456
0.4399	17.0	170	0.6810	0.7215
0.4065	18.0	180	0.7049	0.7089
0.4012	19.0	190	0.7462	0.6962
0.3553	20.0	200	0.7550	0.6835
0.419	21.0	210	0.9119	0.5886
0.3862	22.0	220	0.7467	0.6646
0.3218	23.0	230	0.7734	0.7025
0.2856	24.0	240	0.7714	0.6772
0.2853	25.0	250	0.7505	0.7215
0.3005	26.0	260	0.8128	0.7152
0.3128	27.0	270	0.8520	0.6456
0.3146	28.0	280	0.8034	0.6962
0.3091	29.0	290	0.8961	0.6835
0.3128	30.0	300	0.8976	0.6772
0.2696	31.0	310	0.7489	0.7089
0.286	32.0	320	0.6697	0.7532
0.3084	33.0	330	0.8061	0.7089
0.2527	34.0	340	0.6714	0.7658
0.2239	35.0	350	0.6858	0.7595
0.2251	36.0	360	0.7142	0.7405
0.2049	37.0	370	0.6644	0.7785
0.2141	38.0	380	0.6722	0.7532
0.2265	39.0	390	0.8172	0.7089
0.1847	40.0	400	0.5876	0.7848
0.1692	41.0	410	0.7485	0.7468
0.1759	42.0	420	0.6973	0.7468
0.2126	43.0	430	0.7180	0.7468
0.2217	44.0	440	0.8617	0.6772
0.1662	45.0	450	0.7264	0.7468
0.1168	46.0	460	0.6226	0.7848
0.1737	47.0	470	0.7201	0.7658
0.1673	48.0	480	0.7411	0.7658
0.1992	49.0	490	0.6667	0.7722
0.1327	50.0	500	0.8436	0.6962
0.1409	51.0	510	0.8467	0.6899
0.1325	52.0	520	0.8331	0.7278
0.1247	53.0	530	0.6017	0.7722
0.1215	54.0	540	0.5934	0.8038
0.1556	55.0	550	0.8121	0.7215
0.1615	56.0	560	0.5814	0.7911
0.1268	57.0	570	0.6809	0.7468
0.1258	58.0	580	0.5749	0.7975
0.1128	59.0	590	0.6332	0.8101
0.1519	60.0	600	0.7176	0.7785
0.1303	61.0	610	0.6800	0.7405
0.1256	62.0	620	0.7101	0.7468
0.1139	63.0	630	0.7587	0.7532
0.0914	64.0	640	0.6320	0.8038
0.1314	65.0	650	0.7287	0.7658
0.1402	66.0	660	0.9050	0.7025
0.0947	67.0	670	0.5996	0.7785
0.0902	68.0	680	0.6142	0.8038
0.1101	69.0	690	0.8431	0.7405
0.1138	70.0	700	0.6796	0.7658
0.0875	71.0	710	0.8089	0.7405
0.1006	72.0	720	0.6522	0.7532
0.0811	73.0	730	0.7060	0.7975
0.0919	74.0	740	0.7761	0.7658
0.0717	75.0	750	0.8626	0.7089
0.0961	76.0	760	0.6235	0.7975
0.0869	77.0	770	0.6554	0.7975
0.096	78.0	780	0.6839	0.7658
0.0926	79.0	790	0.6482	0.8038
0.0702	80.0	800	0.8970	0.7405
0.0802	81.0	810	0.7076	0.7785
0.0631	82.0	820	0.5784	0.8228
0.0874	83.0	830	0.6042	0.8038
0.092	84.0	840	0.6569	0.8038
0.0827	85.0	850	0.7801	0.7848
0.0796	86.0	860	0.7321	0.7975
0.0731	87.0	870	0.6231	0.7911
0.0731	88.0	880	0.6244	0.8038
0.0694	89.0	890	0.6433	0.7975
0.0601	90.0	900	0.7026	0.7785
0.0715	91.0	910	0.5609	0.8165
0.0782	92.0	920	0.5387	0.8481
0.0685	93.0	930	0.5740	0.8165
0.0508	94.0	940	0.6352	0.8291
0.0871	95.0	950	0.6687	0.8038
0.0533	96.0	960	0.5791	0.8165
0.0525	97.0	970	0.8043	0.7532
0.0884	98.0	980	0.7164	0.7911
0.0619	99.0	990	0.7417	0.7785
0.0703	100.0	1000	0.8015	0.7595

Framework versions

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