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: 0.5094
Accuracy: 0.9198

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: 1
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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0396	1.0	1293	0.9865	0.5123
1.1023	2.0	2586	1.0537	0.5525
1.1657	3.0	3879	1.4125	0.6080
1.1606	4.0	5172	1.0966	0.4568
1.233	5.0	6465	1.0640	0.6481
1.1345	6.0	7758	1.2839	0.6451
1.1208	7.0	9051	1.4499	0.6451
1.0212	8.0	10344	1.1759	0.7068
0.891	9.0	11637	1.0590	0.7130
0.8541	10.0	12930	1.0337	0.7253
0.7985	11.0	14223	0.8852	0.7778
0.7569	12.0	15516	0.9469	0.7778
0.6847	13.0	16809	1.1415	0.7407
0.6794	14.0	18102	0.8935	0.8210
0.6455	15.0	19395	0.9556	0.7809
0.5708	16.0	20688	1.0258	0.8056
0.4988	17.0	21981	1.4170	0.7654
0.477	18.0	23274	0.9100	0.8179
0.4559	19.0	24567	1.0474	0.7994
0.4284	20.0	25860	0.8757	0.8488
0.3892	21.0	27153	0.9961	0.8241
0.419	22.0	28446	0.9303	0.8333
0.3244	23.0	29739	1.0301	0.8179
0.4107	24.0	31032	0.7903	0.8488
0.3853	25.0	32325	0.5818	0.9012
0.294	26.0	33618	0.9773	0.8426
0.2826	27.0	34911	0.7444	0.8735
0.2218	28.0	36204	1.0961	0.8426
0.3422	29.0	37497	0.9692	0.8395
0.2809	30.0	38790	0.8668	0.8673
0.2618	31.0	40083	0.7958	0.8704
0.2702	32.0	41376	0.6700	0.8796
0.253	33.0	42669	1.1036	0.8148
0.2161	34.0	43962	0.5197	0.9198
0.1727	35.0	45255	0.6996	0.8981
0.2117	36.0	46548	1.3509	0.8056
0.1967	37.0	47841	0.5835	0.9105
0.1885	38.0	49134	0.7260	0.8673
0.1445	39.0	50427	0.7016	0.8735
0.1216	40.0	51720	0.7880	0.8858
0.1552	41.0	53013	0.7237	0.8765
0.0992	42.0	54306	0.7155	0.9043
0.1047	43.0	55599	0.5785	0.9167
0.1119	44.0	56892	0.4751	0.9228
0.128	45.0	58185	0.6190	0.9043
0.1066	46.0	59478	0.6420	0.9167
0.1453	47.0	60771	0.5683	0.9198
0.0991	48.0	62064	0.6286	0.9074
0.0688	49.0	63357	0.5495	0.9228
0.0907	50.0	64650	0.5094	0.9198

Framework versions

Transformers 4.41.2
Pytorch 2.3.0
Datasets 2.19.2
Tokenizers 0.19.1

talli96123/meat_calssify_fresh_crop_fixed_overlap_V_0_1

meat_calssify_fresh_crop_fixed_overlap_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_overlap_V_0_1