meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_16

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: 0.2644
• Accuracy: 0.9159

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
1.1034	1.0	21	1.0943	0.3676
1.0767	2.0	42	1.0823	0.4330
1.0209	3.0	63	1.0269	0.4829
0.9495	4.0	84	1.0109	0.4953
0.9498	5.0	105	0.8882	0.6199
0.7834	6.0	126	0.8506	0.6075
0.6988	7.0	147	0.7727	0.6480
0.6568	8.0	168	0.8098	0.6573
0.634	9.0	189	0.9338	0.5607
0.7335	10.0	210	0.7394	0.6947
0.5521	11.0	231	0.6369	0.7539
0.5108	12.0	252	0.7480	0.7040
0.4485	13.0	273	0.8050	0.6854
0.4928	14.0	294	0.7566	0.7040
0.5092	15.0	315	0.5191	0.7944
0.4473	16.0	336	0.6516	0.7134
0.3521	17.0	357	0.5184	0.8069
0.2994	18.0	378	0.5233	0.8193
0.2844	19.0	399	0.5587	0.7757
0.301	20.0	420	0.5614	0.8131
0.2898	21.0	441	0.4659	0.8287
0.2513	22.0	462	0.4748	0.8287
0.2121	23.0	483	0.4042	0.8505
0.2302	24.0	504	0.6265	0.7757
0.2201	25.0	525	0.4746	0.8349
0.2193	26.0	546	0.3364	0.8816
0.1852	27.0	567	0.3966	0.8567
0.2117	28.0	588	0.4427	0.8349
0.1705	29.0	609	0.4767	0.8255
0.1756	30.0	630	0.4838	0.8380
0.1744	31.0	651	0.5400	0.8131
0.2296	32.0	672	0.4693	0.8255
0.1517	33.0	693	0.3704	0.8660
0.3201	34.0	714	0.7578	0.7539
0.1561	35.0	735	0.3828	0.8660
0.1458	36.0	756	0.4366	0.8692
0.2448	37.0	777	0.3000	0.8972
0.15	38.0	798	0.4457	0.8567
0.1367	39.0	819	0.2505	0.9128
0.1167	40.0	840	0.2869	0.9003
0.0949	41.0	861	0.3303	0.8847
0.1203	42.0	882	0.3524	0.8629
0.1429	43.0	903	0.4549	0.8318
0.11	44.0	924	0.4028	0.8754
0.1231	45.0	945	0.4290	0.8629
0.1009	46.0	966	0.4046	0.8598
0.1132	47.0	987	0.3221	0.8972
0.1023	48.0	1008	0.2680	0.9159
0.0906	49.0	1029	0.3685	0.8754
0.1039	50.0	1050	0.3564	0.8785
0.0948	51.0	1071	0.4784	0.8380
0.0881	52.0	1092	0.3369	0.8816
0.0918	53.0	1113	0.2608	0.9159
0.0828	54.0	1134	0.2678	0.9003
0.0819	55.0	1155	0.2618	0.9034
0.1696	56.0	1176	0.3057	0.9034
0.0943	57.0	1197	0.3915	0.8847
0.0718	58.0	1218	0.3162	0.9065
0.0775	59.0	1239	0.3678	0.8847
0.0674	60.0	1260	0.3083	0.8972
0.0666	61.0	1281	0.3120	0.9128
0.0631	62.0	1302	0.3648	0.9003
0.0726	63.0	1323	0.3771	0.8910
0.0619	64.0	1344	0.3278	0.8910
0.0823	65.0	1365	0.4250	0.8692
0.0628	66.0	1386	0.3618	0.9003
0.0714	67.0	1407	0.4590	0.8629
0.056	68.0	1428	0.4471	0.8910
0.0613	69.0	1449	0.2702	0.9097
0.0642	70.0	1470	0.2646	0.9190
0.0549	71.0	1491	0.3084	0.8972
0.0534	72.0	1512	0.3388	0.9128
0.0414	73.0	1533	0.2962	0.9190
0.0552	74.0	1554	0.3004	0.9221
0.0502	75.0	1575	0.4007	0.8879
0.0403	76.0	1596	0.2649	0.9065
0.0341	77.0	1617	0.1945	0.9408
0.061	78.0	1638	0.2936	0.9221
0.059	79.0	1659	0.2938	0.9128
0.0393	80.0	1680	0.3278	0.8941
0.0475	81.0	1701	0.2856	0.9190
0.0404	82.0	1722	0.2679	0.9252
0.0528	83.0	1743	0.2544	0.9283
0.05	84.0	1764	0.2992	0.9097
0.0449	85.0	1785	0.3004	0.9128
0.0337	86.0	1806	0.2744	0.9190
0.0406	87.0	1827	0.3380	0.9003
0.0314	88.0	1848	0.2801	0.9221
0.0355	89.0	1869	0.2609	0.9190
0.0313	90.0	1890	0.2507	0.9315
0.0478	91.0	1911	0.2934	0.9128
0.0365	92.0	1932	0.2642	0.9283
0.0486	93.0	1953	0.1662	0.9626
0.0271	94.0	1974	0.2194	0.9377
0.0215	95.0	1995	0.2492	0.9252
0.0365	96.0	2016	0.2006	0.9502
0.0275	97.0	2037	0.2267	0.9159
0.0647	98.0	2058	0.3226	0.9159
0.0222	99.0	2079	0.2469	0.9346
0.0426	100.0	2100	0.2644	0.9159

Framework versions

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