meat_calssify_fresh_crop_fixed_epoch100_V_0_8

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: 0.5407
• Accuracy: 0.8481

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
1.0983	1.0	10	1.0923	0.3861
1.0837	2.0	20	1.0603	0.4937
1.0593	3.0	30	1.0236	0.5633
1.0323	4.0	40	0.9905	0.5696
0.991	5.0	50	0.9442	0.5759
0.9535	6.0	60	0.9318	0.5506
0.8994	7.0	70	0.8444	0.6139
0.847	8.0	80	0.8550	0.6266
0.8083	9.0	90	0.8252	0.6456
0.7465	10.0	100	0.7622	0.6646
0.6872	11.0	110	0.7461	0.6329
0.6664	12.0	120	0.7210	0.6899
0.5655	13.0	130	0.6896	0.6962
0.5541	14.0	140	0.6891	0.6962
0.5162	15.0	150	0.6646	0.7468
0.531	16.0	160	0.6972	0.6962
0.4662	17.0	170	0.5651	0.7658
0.4806	18.0	180	0.7426	0.6709
0.405	19.0	190	0.6764	0.7089
0.3897	20.0	200	0.5832	0.7658
0.327	21.0	210	0.5591	0.7532
0.3542	22.0	220	0.6793	0.7278
0.3309	23.0	230	0.5890	0.7532
0.3384	24.0	240	0.5595	0.7722
0.2867	25.0	250	0.5669	0.7975
0.2651	26.0	260	0.6369	0.7468
0.2659	27.0	270	0.7925	0.6709
0.3057	28.0	280	0.7006	0.7405
0.2606	29.0	290	0.5800	0.7658
0.2145	30.0	300	0.4187	0.8418
0.1951	31.0	310	0.7022	0.7342
0.2658	32.0	320	0.6902	0.7342
0.2329	33.0	330	0.5709	0.7595
0.1807	34.0	340	0.5226	0.7911
0.1602	35.0	350	0.5418	0.7911
0.2104	36.0	360	0.6453	0.7658
0.2009	37.0	370	0.4814	0.8291
0.2059	38.0	380	0.6135	0.7595
0.2203	39.0	390	0.5581	0.7785
0.1864	40.0	400	0.5939	0.7911
0.1564	41.0	410	0.6002	0.7848
0.1229	42.0	420	0.6470	0.7658
0.1867	43.0	430	0.6545	0.7975
0.1679	44.0	440	0.6079	0.7658
0.1752	45.0	450	0.6666	0.7468
0.1256	46.0	460	0.6651	0.7595
0.188	47.0	470	0.6574	0.7532
0.1695	48.0	480	0.5883	0.7975
0.1797	49.0	490	0.7344	0.7595
0.1913	50.0	500	0.5662	0.8101
0.1483	51.0	510	0.5385	0.8038
0.1502	52.0	520	0.5101	0.8165
0.1142	53.0	530	0.5263	0.8228
0.0839	54.0	540	0.4852	0.8038
0.1432	55.0	550	0.5651	0.8101
0.1327	56.0	560	0.6218	0.7911
0.0948	57.0	570	0.6101	0.7722
0.1387	58.0	580	0.5350	0.8101
0.0957	59.0	590	0.7503	0.7722
0.1243	60.0	600	0.5468	0.7911
0.1179	61.0	610	0.5851	0.8038
0.128	62.0	620	0.5167	0.8291
0.1018	63.0	630	0.5119	0.8481
0.0987	64.0	640	0.6415	0.7911
0.0901	65.0	650	0.6031	0.8038
0.1457	66.0	660	0.6773	0.7848
0.1247	67.0	670	0.5563	0.7975
0.127	68.0	680	0.7763	0.7595
0.0841	69.0	690	0.4934	0.8544
0.0914	70.0	700	0.6510	0.8228
0.0982	71.0	710	0.5742	0.8101
0.0945	72.0	720	0.4954	0.8481
0.077	73.0	730	0.6194	0.8101
0.0936	74.0	740	0.5301	0.8228
0.0641	75.0	750	0.5673	0.8165
0.0646	76.0	760	0.5055	0.8291
0.0794	77.0	770	0.5444	0.8228
0.0774	78.0	780	0.5511	0.8228
0.0674	79.0	790	0.5688	0.8354
0.0731	80.0	800	0.5594	0.8291
0.0839	81.0	810	0.6970	0.7785
0.0857	82.0	820	0.5651	0.7975
0.0729	83.0	830	0.7003	0.7848
0.074	84.0	840	0.5293	0.8165
0.0505	85.0	850	0.5051	0.8544
0.0669	86.0	860	0.6459	0.8101
0.0614	87.0	870	0.5474	0.8291
0.0659	88.0	880	0.4981	0.8291
0.0702	89.0	890	0.5611	0.8291
0.0635	90.0	900	0.6273	0.7975
0.0698	91.0	910	0.4314	0.8734
0.0671	92.0	920	0.5471	0.8291
0.057	93.0	930	0.4922	0.8481
0.0563	94.0	940	0.5463	0.8418
0.0638	95.0	950	0.5177	0.8291
0.0545	96.0	960	0.6183	0.8038
0.0534	97.0	970	0.5460	0.8165
0.0655	98.0	980	0.4196	0.8861
0.0775	99.0	990	0.5088	0.8354
0.0519	100.0	1000	0.5407	0.8481

Framework versions

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