meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_5

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: 0.2106
• Accuracy: 0.9315

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: 64
• 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
1.1058	1.0	21	1.0981	0.3707
1.0889	2.0	42	1.0703	0.4673
1.0551	3.0	63	1.0219	0.5265
0.9782	4.0	84	0.9533	0.5389
0.916	5.0	105	0.8848	0.6293
0.8579	6.0	126	0.7977	0.6417
0.7614	7.0	147	0.8384	0.6511
0.7643	8.0	168	0.6850	0.7632
0.6182	9.0	189	0.7255	0.7134
0.5827	10.0	210	0.7923	0.6604
0.5751	11.0	231	0.6706	0.7196
0.5045	12.0	252	0.5499	0.7726
0.473	13.0	273	0.7024	0.6885
0.4922	14.0	294	0.6377	0.7165
0.4808	15.0	315	0.4886	0.8224
0.4047	16.0	336	0.4426	0.8318
0.3982	17.0	357	0.5656	0.7508
0.3279	18.0	378	0.5265	0.7819
0.3421	19.0	399	0.4606	0.8100
0.2593	20.0	420	0.4638	0.8100
0.2542	21.0	441	0.4388	0.8474
0.2554	22.0	462	0.5237	0.8100
0.2488	23.0	483	0.4238	0.8474
0.2069	24.0	504	0.3515	0.8847
0.295	25.0	525	0.4371	0.8318
0.2213	26.0	546	0.3588	0.8847
0.1961	27.0	567	0.5877	0.7975
0.27	28.0	588	0.3720	0.8567
0.1791	29.0	609	0.2952	0.9065
0.1763	30.0	630	0.3312	0.8816
0.1664	31.0	651	0.3770	0.8754
0.2713	32.0	672	0.4695	0.8287
0.1645	33.0	693	0.4069	0.8505
0.1942	34.0	714	0.4516	0.8380
0.1435	35.0	735	0.2383	0.9252
0.1399	36.0	756	0.4790	0.8442
0.1615	37.0	777	0.3230	0.8785
0.1405	38.0	798	0.2635	0.9065
0.1569	39.0	819	0.4816	0.8598
0.1332	40.0	840	0.2859	0.8847
0.1108	41.0	861	0.3786	0.8723
0.1014	42.0	882	0.3215	0.9003
0.1186	43.0	903	0.3652	0.8785
0.1021	44.0	924	0.2088	0.9221
0.1444	45.0	945	0.3646	0.8723
0.1058	46.0	966	0.3530	0.8847
0.1297	47.0	987	0.4002	0.8629
0.0997	48.0	1008	0.2928	0.9034
0.1246	49.0	1029	0.2772	0.9065
0.0989	50.0	1050	0.2459	0.9221
0.0794	51.0	1071	0.1970	0.9283
0.0698	52.0	1092	0.3217	0.8847
0.0767	53.0	1113	0.2706	0.9190
0.0966	54.0	1134	0.2246	0.9252
0.0816	55.0	1155	0.2585	0.9065
0.0732	56.0	1176	0.3289	0.8910
0.0992	57.0	1197	0.2790	0.9128
0.0684	58.0	1218	0.2508	0.9252
0.0972	59.0	1239	0.2558	0.9190
0.0702	60.0	1260	0.2411	0.9190
0.0602	61.0	1281	0.4097	0.8660
0.0912	62.0	1302	0.2274	0.9252
0.0556	63.0	1323	0.1940	0.9408
0.0727	64.0	1344	0.2389	0.9190
0.0657	65.0	1365	0.2964	0.9128
0.0486	66.0	1386	0.2597	0.9252
0.0639	67.0	1407	0.2272	0.9346
0.0614	68.0	1428	0.1927	0.9470
0.0444	69.0	1449	0.2771	0.9190
0.0648	70.0	1470	0.2345	0.9283
0.051	71.0	1491	0.2210	0.9159
0.0514	72.0	1512	0.2260	0.9346
0.0473	73.0	1533	0.2496	0.9252
0.0637	74.0	1554	0.3152	0.9128
0.0538	75.0	1575	0.2527	0.9221
0.0622	76.0	1596	0.2148	0.9408
0.0437	77.0	1617	0.2386	0.9190
0.07	78.0	1638	0.2013	0.9315
0.0599	79.0	1659	0.2532	0.9346
0.0367	80.0	1680	0.1835	0.9439
0.0386	81.0	1701	0.2204	0.9283
0.0372	82.0	1722	0.2417	0.9283
0.0516	83.0	1743	0.3098	0.9190
0.0378	84.0	1764	0.1587	0.9533
0.0371	85.0	1785	0.2041	0.9377
0.0378	86.0	1806	0.2343	0.9377
0.0288	87.0	1827	0.1963	0.9439
0.0272	88.0	1848	0.2122	0.9408
0.0293	89.0	1869	0.0979	0.9751
0.037	90.0	1890	0.2385	0.9221
0.0453	91.0	1911	0.2056	0.9439
0.0478	92.0	1932	0.1861	0.9439
0.0241	93.0	1953	0.2129	0.9470
0.0404	94.0	1974	0.1806	0.9502
0.0224	95.0	1995	0.1698	0.9377
0.0194	96.0	2016	0.1960	0.9533
0.022	97.0	2037	0.2140	0.9377
0.0328	98.0	2058	0.1684	0.9502
0.0443	99.0	2079	0.2536	0.9283
0.0386	100.0	2100	0.2106	0.9315

Framework versions

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