meat_calssify_fresh_crop_fixed_epoch100_V_0_10

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: 0.6095
• Accuracy: 0.7975

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
1.0941	1.0	10	1.0929	0.3418
1.0817	2.0	20	1.0775	0.4051
1.059	3.0	30	1.0631	0.4494
1.028	4.0	40	1.0305	0.4747
0.9784	5.0	50	1.0019	0.4747
0.9123	6.0	60	0.9389	0.5759
0.8789	7.0	70	0.8875	0.5949
0.816	8.0	80	0.8561	0.6203
0.7632	9.0	90	0.8253	0.6266
0.6857	10.0	100	0.8264	0.6203
0.6834	11.0	110	0.7056	0.6962
0.629	12.0	120	0.7708	0.6329
0.5744	13.0	130	0.6847	0.6962
0.5661	14.0	140	0.6881	0.7215
0.5516	15.0	150	0.7477	0.6646
0.482	16.0	160	0.6717	0.7152
0.4265	17.0	170	0.6200	0.7468
0.4074	18.0	180	0.6404	0.7278
0.3797	19.0	190	0.6577	0.7405
0.3895	20.0	200	0.6127	0.7658
0.3244	21.0	210	0.6776	0.7658
0.3764	22.0	220	0.8015	0.6899
0.3692	23.0	230	0.6790	0.7278
0.2687	24.0	240	0.6951	0.7215
0.3352	25.0	250	0.7140	0.7215
0.2734	26.0	260	0.6895	0.7152
0.2857	27.0	270	0.6515	0.7089
0.2716	28.0	280	0.6171	0.7405
0.2628	29.0	290	0.5954	0.7532
0.222	30.0	300	0.6447	0.7342
0.2458	31.0	310	0.6836	0.7532
0.2489	32.0	320	0.5701	0.7975
0.2282	33.0	330	0.6654	0.7405
0.1824	34.0	340	0.6552	0.7468
0.2261	35.0	350	0.7548	0.7342
0.2198	36.0	360	0.6297	0.7785
0.2118	37.0	370	0.6240	0.7911
0.1751	38.0	380	0.6787	0.7722
0.1507	39.0	390	0.5897	0.7911
0.1647	40.0	400	0.6010	0.7975
0.2214	41.0	410	0.6143	0.7975
0.1462	42.0	420	0.8883	0.7278
0.1841	43.0	430	0.7459	0.7532
0.2076	44.0	440	0.6125	0.8101
0.1359	45.0	450	0.5540	0.8101
0.1315	46.0	460	0.7218	0.7532
0.1658	47.0	470	0.7927	0.7278
0.1807	48.0	480	0.6954	0.7911
0.1601	49.0	490	0.6399	0.7595
0.1385	50.0	500	0.6353	0.7532
0.1387	51.0	510	0.6596	0.7658
0.1435	52.0	520	0.5697	0.8165
0.1116	53.0	530	0.6201	0.8165
0.0899	54.0	540	0.5805	0.8101
0.1245	55.0	550	0.7132	0.7785
0.1309	56.0	560	0.6173	0.7911
0.1176	57.0	570	0.6650	0.8038
0.1516	58.0	580	0.7006	0.7342
0.1359	59.0	590	0.7015	0.7785
0.134	60.0	600	0.6239	0.7975
0.1167	61.0	610	0.5665	0.7848
0.127	62.0	620	0.5368	0.8038
0.1306	63.0	630	0.4862	0.8544
0.0919	64.0	640	0.6305	0.7595
0.1082	65.0	650	0.6479	0.7848
0.1484	66.0	660	0.6687	0.7785
0.1066	67.0	670	0.5404	0.8101
0.1011	68.0	680	0.4724	0.8797
0.0891	69.0	690	0.5482	0.8354
0.1011	70.0	700	0.7259	0.7975
0.0819	71.0	710	0.6372	0.7911
0.0943	72.0	720	0.5851	0.7975
0.0638	73.0	730	0.5816	0.8101
0.0875	74.0	740	0.7538	0.7595
0.1146	75.0	750	0.5902	0.8165
0.0861	76.0	760	0.5353	0.8354
0.1031	77.0	770	0.5022	0.8101
0.0721	78.0	780	0.5100	0.8544
0.0752	79.0	790	0.6330	0.7785
0.0753	80.0	800	0.5908	0.7848
0.0602	81.0	810	0.6954	0.7658
0.082	82.0	820	0.4405	0.8671
0.0905	83.0	830	0.5115	0.8481
0.0597	84.0	840	0.5156	0.8608
0.0716	85.0	850	0.5273	0.8228
0.0606	86.0	860	0.6440	0.8354
0.0736	87.0	870	0.5842	0.8354
0.0614	88.0	880	0.5470	0.8354
0.0496	89.0	890	0.5201	0.8228
0.067	90.0	900	0.5866	0.8228
0.059	91.0	910	0.5842	0.8354
0.0525	92.0	920	0.5256	0.8418
0.0928	93.0	930	0.6557	0.8101
0.0736	94.0	940	0.6496	0.8101
0.064	95.0	950	0.5068	0.8418
0.0654	96.0	960	0.4680	0.8291
0.0426	97.0	970	0.5116	0.8608
0.0515	98.0	980	0.4887	0.8608
0.0466	99.0	990	0.5188	0.8228
0.0746	100.0	1000	0.6095	0.7975

Framework versions

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