meat_calssify_fresh_crop_fixed_epoch100_V_0_9

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: 0.5517
• Accuracy: 0.8038

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
1.1101	1.0	10	1.1019	0.3038
1.087	2.0	20	1.0748	0.4557
1.0593	3.0	30	1.0543	0.5
1.0235	4.0	40	1.0289	0.4873
0.9755	5.0	50	1.0048	0.4873
0.9116	6.0	60	0.9857	0.5
0.9154	7.0	70	0.9614	0.4937
0.8318	8.0	80	0.9839	0.5506
0.795	9.0	90	0.9393	0.5570
0.7544	10.0	100	0.9061	0.5886
0.6596	11.0	110	0.8780	0.6392
0.6111	12.0	120	0.8170	0.6392
0.5791	13.0	130	0.8801	0.6329
0.5287	14.0	140	0.8099	0.6709
0.4966	15.0	150	0.7827	0.6582
0.4842	16.0	160	0.8007	0.6709
0.4059	17.0	170	0.7380	0.6582
0.3905	18.0	180	0.6695	0.7278
0.3681	19.0	190	0.7496	0.6899
0.3618	20.0	200	0.7554	0.7089
0.3446	21.0	210	0.7603	0.6962
0.3625	22.0	220	0.7402	0.6772
0.3356	23.0	230	0.7598	0.6582
0.2758	24.0	240	0.7952	0.6899
0.287	25.0	250	0.8296	0.6772
0.3334	26.0	260	0.9352	0.6456
0.2925	27.0	270	0.8240	0.6772
0.2732	28.0	280	0.7479	0.7278
0.2816	29.0	290	0.7068	0.7152
0.2349	30.0	300	0.6218	0.7658
0.2282	31.0	310	0.6681	0.7342
0.2297	32.0	320	0.9084	0.6709
0.2316	33.0	330	0.8716	0.6772
0.2182	34.0	340	0.7289	0.7342
0.2159	35.0	350	0.6567	0.7405
0.2329	36.0	360	0.6947	0.7468
0.155	37.0	370	0.6736	0.7532
0.1901	38.0	380	0.8000	0.7025
0.1767	39.0	390	0.7780	0.7342
0.1718	40.0	400	0.6616	0.7595
0.1558	41.0	410	0.7514	0.7025
0.1564	42.0	420	0.7801	0.7278
0.2172	43.0	430	0.7421	0.7342
0.1703	44.0	440	0.7043	0.7595
0.1475	45.0	450	0.6865	0.7658
0.1174	46.0	460	0.5958	0.7975
0.1586	47.0	470	0.6927	0.7785
0.1515	48.0	480	0.8407	0.7089
0.1593	49.0	490	0.6465	0.7658
0.1777	50.0	500	0.7899	0.7215
0.1205	51.0	510	0.5897	0.7722
0.1375	52.0	520	0.6837	0.7785
0.1564	53.0	530	0.7868	0.7152
0.1481	54.0	540	0.7252	0.7722
0.1073	55.0	550	0.6796	0.7658
0.1549	56.0	560	0.7610	0.7152
0.1351	57.0	570	0.7985	0.7342
0.1235	58.0	580	0.6534	0.7595
0.1306	59.0	590	0.7046	0.7975
0.1464	60.0	600	0.7280	0.7595
0.1724	61.0	610	0.7066	0.7848
0.115	62.0	620	0.7080	0.7532
0.0842	63.0	630	0.6463	0.7848
0.0883	64.0	640	0.8290	0.7342
0.0901	65.0	650	0.7097	0.7595
0.1174	66.0	660	0.6627	0.7658
0.1167	67.0	670	0.7519	0.7722
0.0795	68.0	680	0.6104	0.7975
0.0583	69.0	690	0.7621	0.7848
0.0973	70.0	700	0.7309	0.7658
0.0909	71.0	710	0.9068	0.7215
0.0931	72.0	720	0.7453	0.7658
0.1101	73.0	730	0.8395	0.7089
0.0867	74.0	740	0.6816	0.7722
0.1154	75.0	750	0.7723	0.7405
0.1016	76.0	760	0.7334	0.7785
0.0821	77.0	770	0.7354	0.7722
0.0624	78.0	780	0.5303	0.8544
0.0698	79.0	790	0.7409	0.7658
0.086	80.0	800	0.6524	0.8038
0.072	81.0	810	0.7530	0.7848
0.0656	82.0	820	0.7409	0.7785
0.0909	83.0	830	0.7190	0.7848
0.0821	84.0	840	0.7085	0.7848
0.0618	85.0	850	0.6801	0.7658
0.0943	86.0	860	0.6859	0.7595
0.0787	87.0	870	0.6259	0.7975
0.0691	88.0	880	0.7148	0.7911
0.0494	89.0	890	0.7675	0.7785
0.0767	90.0	900	0.7293	0.7911
0.0861	91.0	910	0.6653	0.7975
0.0535	92.0	920	0.6421	0.8038
0.0574	93.0	930	0.7444	0.7911
0.0567	94.0	940	0.4409	0.8671
0.0759	95.0	950	0.5884	0.7975
0.0407	96.0	960	0.6606	0.7848
0.0624	97.0	970	0.5409	0.8354
0.0586	98.0	980	0.5585	0.7975
0.0413	99.0	990	0.6347	0.7911
0.0597	100.0	1000	0.5517	0.8038

Framework versions

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