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: 0.5098
Accuracy: 0.8462

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: 80

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1019	1.0	10	1.0993	0.3718
1.0872	2.0	20	1.0762	0.4167
1.0617	3.0	30	1.0498	0.4808
1.0264	4.0	40	1.0153	0.4872
0.9738	5.0	50	0.9431	0.5641
0.9038	6.0	60	0.9137	0.5449
0.8405	7.0	70	0.8209	0.6538
0.8131	8.0	80	0.8620	0.5897
0.7412	9.0	90	0.7370	0.6859
0.7006	10.0	100	0.7230	0.6987
0.6531	11.0	110	0.7679	0.6923
0.6215	12.0	120	0.6398	0.7308
0.5351	13.0	130	0.7016	0.7051
0.4847	14.0	140	0.5606	0.7949
0.4677	15.0	150	0.8849	0.6410
0.6042	16.0	160	0.5766	0.7756
0.4113	17.0	170	0.5573	0.7885
0.3662	18.0	180	0.6451	0.7179
0.3899	19.0	190	0.5613	0.7692
0.3518	20.0	200	0.6618	0.7051
0.303	21.0	210	0.5417	0.7756
0.2568	22.0	220	0.4785	0.8205
0.3098	23.0	230	0.6330	0.7564
0.3299	24.0	240	0.4944	0.8077
0.2373	25.0	250	0.5141	0.8141
0.2556	26.0	260	0.5719	0.8013
0.2387	27.0	270	0.5495	0.8013
0.2651	28.0	280	0.7409	0.7436
0.2909	29.0	290	0.6281	0.7821
0.2369	30.0	300	0.5067	0.8333
0.2084	31.0	310	0.5297	0.8077
0.2506	32.0	320	0.6124	0.7756
0.2395	33.0	330	0.5564	0.7692
0.2243	34.0	340	0.5176	0.7692
0.1951	35.0	350	0.5289	0.7949
0.1967	36.0	360	0.4829	0.8333
0.1602	37.0	370	0.5496	0.8205
0.1647	38.0	380	0.5969	0.7692
0.1772	39.0	390	0.6299	0.7949
0.1595	40.0	400	0.6386	0.7756
0.1801	41.0	410	0.5485	0.7885
0.1577	42.0	420	0.6692	0.7692
0.1683	43.0	430	0.5639	0.8077
0.1677	44.0	440	0.4369	0.8462
0.1367	45.0	450	0.5955	0.7756
0.1061	46.0	460	0.6644	0.8013
0.0957	47.0	470	0.5834	0.8077
0.1341	48.0	480	0.5541	0.8077
0.1153	49.0	490	0.6226	0.7885
0.122	50.0	500	0.5326	0.8269
0.1237	51.0	510	0.4428	0.8462
0.1006	52.0	520	0.5562	0.8269
0.1256	53.0	530	0.5066	0.8333
0.0995	54.0	540	0.6685	0.8013
0.1033	55.0	550	0.5183	0.8269
0.1177	56.0	560	0.6426	0.7692
0.1033	57.0	570	0.5079	0.8141
0.1389	58.0	580	0.5120	0.8205
0.0955	59.0	590	0.5381	0.8333
0.1108	60.0	600	0.5210	0.8526
0.1355	61.0	610	0.5460	0.8205
0.0897	62.0	620	0.4909	0.8269
0.084	63.0	630	0.5438	0.8205
0.082	64.0	640	0.5693	0.8269
0.1026	65.0	650	0.4864	0.8590
0.0872	66.0	660	0.4856	0.8397
0.0966	67.0	670	0.4073	0.8590
0.097	68.0	680	0.5848	0.8269
0.1007	69.0	690	0.4663	0.8205
0.0695	70.0	700	0.5000	0.8333
0.1048	71.0	710	0.6038	0.8141
0.0715	72.0	720	0.6008	0.8269
0.1061	73.0	730	0.5291	0.8269
0.0688	74.0	740	0.4124	0.8654
0.0638	75.0	750	0.5575	0.8205
0.0785	76.0	760	0.5537	0.8141
0.0758	77.0	770	0.4363	0.8718
0.0865	78.0	780	0.5200	0.8269
0.0844	79.0	790	0.6848	0.7949
0.0776	80.0	800	0.5098	0.8462

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.19.2
Tokenizers 0.19.1

talli96123/meat_calssify_fresh_crop_fixed_epoch_80_V_0_1

meat_calssify_fresh_crop_fixed_epoch_80_V_0_1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

talli96123/
meat_calssify_fresh_crop_fixed_epoch_80_V_0_1