meat_calssify_fresh_crop_fixed_overlap_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: 0.1854
• Accuracy: 0.9439

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
1.101	1.0	21	1.0776	0.4206
1.0459	2.0	42	1.0368	0.5109
0.9957	3.0	63	0.9830	0.5296
0.9613	4.0	84	0.8994	0.5857
0.9072	5.0	105	0.8663	0.6231
0.8397	6.0	126	0.7738	0.7196
0.7726	7.0	147	0.7461	0.6978
0.7757	8.0	168	0.7647	0.6636
0.6253	9.0	189	0.6437	0.7445
0.5671	10.0	210	0.6791	0.7072
0.529	11.0	231	0.6623	0.7072
0.4362	12.0	252	0.5876	0.7508
0.552	13.0	273	0.5093	0.7913
0.3779	14.0	294	0.7716	0.6573
0.5052	15.0	315	0.7956	0.6791
0.5263	16.0	336	0.6077	0.7445
0.3712	17.0	357	0.4699	0.8474
0.2958	18.0	378	0.5815	0.7819
0.2775	19.0	399	0.5083	0.8100
0.2467	20.0	420	0.4561	0.8162
0.2541	21.0	441	0.4463	0.8380
0.2689	22.0	462	0.5149	0.7944
0.1893	23.0	483	0.4155	0.8567
0.2263	24.0	504	0.7202	0.7601
0.2646	25.0	525	0.4365	0.8162
0.2416	26.0	546	0.3365	0.8816
0.1788	27.0	567	0.3679	0.8723
0.1947	28.0	588	0.3725	0.8660
0.1802	29.0	609	0.4176	0.8567
0.1695	30.0	630	0.3776	0.8692
0.2089	31.0	651	0.3047	0.8785
0.1727	32.0	672	0.3225	0.8754
0.143	33.0	693	0.2355	0.9128
0.1593	34.0	714	0.3424	0.8847
0.1179	35.0	735	0.2873	0.9065
0.1227	36.0	756	0.3114	0.8941
0.1636	37.0	777	0.4101	0.8660
0.1347	38.0	798	0.2253	0.9190
0.1108	39.0	819	0.3387	0.8847
0.1383	40.0	840	0.4024	0.8754
0.1173	41.0	861	0.2436	0.9034
0.1027	42.0	882	0.2603	0.9065
0.1244	43.0	903	0.2990	0.9128
0.1061	44.0	924	0.3082	0.9065
0.1179	45.0	945	0.2212	0.9128
0.0945	46.0	966	0.3455	0.8816
0.1055	47.0	987	0.2951	0.8847
0.0895	48.0	1008	0.3003	0.9065
0.1298	49.0	1029	0.3123	0.9097
0.1379	50.0	1050	0.2787	0.9128
0.0879	51.0	1071	0.2920	0.9128
0.1011	52.0	1092	0.3667	0.8816
0.1038	53.0	1113	0.2967	0.9034
0.0834	54.0	1134	0.2281	0.9346
0.0998	55.0	1155	0.2835	0.8941
0.0794	56.0	1176	0.2260	0.9221
0.0732	57.0	1197	0.3309	0.9003
0.0612	58.0	1218	0.3392	0.9065
0.0679	59.0	1239	0.2728	0.9252
0.0986	60.0	1260	0.2380	0.9221
0.0639	61.0	1281	0.2672	0.9221
0.061	62.0	1302	0.2898	0.9221
0.0741	63.0	1323	0.3098	0.9097
0.0532	64.0	1344	0.2621	0.9252
0.0642	65.0	1365	0.1643	0.9377
0.0762	66.0	1386	0.2332	0.9346
0.0562	67.0	1407	0.2603	0.9252
0.0481	68.0	1428	0.2363	0.9097
0.0576	69.0	1449	0.2421	0.9377
0.0355	70.0	1470	0.2040	0.9346
0.07	71.0	1491	0.2900	0.9283
0.0631	72.0	1512	0.2531	0.9221
0.046	73.0	1533	0.2054	0.9346
0.0767	74.0	1554	0.1651	0.9408
0.0569	75.0	1575	0.2251	0.9377
0.0454	76.0	1596	0.2003	0.9408
0.0596	77.0	1617	0.1607	0.9564
0.0602	78.0	1638	0.1789	0.9408
0.0512	79.0	1659	0.2390	0.9221
0.0402	80.0	1680	0.1433	0.9564
0.0425	81.0	1701	0.1379	0.9502
0.0428	82.0	1722	0.1422	0.9564
0.0353	83.0	1743	0.1433	0.9502
0.0449	84.0	1764	0.2206	0.9190
0.0402	85.0	1785	0.2194	0.9470
0.041	86.0	1806	0.1564	0.9502
0.057	87.0	1827	0.2352	0.9346
0.0475	88.0	1848	0.1618	0.9502
0.0399	89.0	1869	0.1322	0.9564
0.0324	90.0	1890	0.1803	0.9502
0.0796	91.0	1911	0.1577	0.9408
0.0283	92.0	1932	0.1599	0.9626
0.0325	93.0	1953	0.1741	0.9626
0.0345	94.0	1974	0.1089	0.9533
0.0361	95.0	1995	0.1044	0.9595
0.0346	96.0	2016	0.1416	0.9533
0.0339	97.0	2037	0.2032	0.9346
0.0309	98.0	2058	0.1348	0.9595
0.046	99.0	2079	0.1345	0.9533
0.0285	100.0	2100	0.1854	0.9439

Framework versions

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