meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_8

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: 0.2201
• Accuracy: 0.9377

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
1.0975	1.0	21	1.0890	0.4174
1.0736	2.0	42	1.0605	0.4673
1.0236	3.0	63	1.0034	0.5202
0.9414	4.0	84	0.9182	0.6044
0.8522	5.0	105	0.8534	0.6417
0.7504	6.0	126	0.8599	0.6044
0.7472	7.0	147	0.6873	0.7040
0.6671	8.0	168	0.6945	0.7165
0.5986	9.0	189	0.6044	0.7664
0.5255	10.0	210	0.6201	0.7383
0.4988	11.0	231	0.6229	0.7570
0.5221	12.0	252	0.6687	0.7321
0.4338	13.0	273	0.5720	0.7757
0.4157	14.0	294	0.5662	0.7757
0.5228	15.0	315	0.6383	0.7383
0.3387	16.0	336	0.4655	0.8069
0.2952	17.0	357	0.4642	0.8006
0.3083	18.0	378	0.5752	0.7726
0.2659	19.0	399	0.5155	0.7913
0.2824	20.0	420	0.4943	0.8162
0.3329	21.0	441	0.5901	0.7757
0.3527	22.0	462	0.4185	0.8380
0.2394	23.0	483	0.3630	0.8723
0.2106	24.0	504	0.4305	0.8474
0.1845	25.0	525	0.3412	0.8629
0.1882	26.0	546	0.3621	0.8816
0.2144	27.0	567	0.3275	0.8754
0.1824	28.0	588	0.3481	0.8723
0.163	29.0	609	0.3861	0.8598
0.1467	30.0	630	0.3590	0.8692
0.2073	31.0	651	0.3481	0.8879
0.1669	32.0	672	0.3134	0.8847
0.167	33.0	693	0.3726	0.8754
0.1624	34.0	714	0.5522	0.7944
0.1812	35.0	735	0.4431	0.8193
0.1172	36.0	756	0.3441	0.8816
0.1515	37.0	777	0.4946	0.8255
0.1612	38.0	798	0.3402	0.8847
0.0937	39.0	819	0.4480	0.8598
0.1453	40.0	840	0.4515	0.8411
0.1259	41.0	861	0.3361	0.8847
0.107	42.0	882	0.3544	0.8598
0.1244	43.0	903	0.3990	0.8567
0.0824	44.0	924	0.3566	0.9034
0.1171	45.0	945	0.3223	0.9003
0.1052	46.0	966	0.3364	0.8660
0.1274	47.0	987	0.3034	0.8941
0.0799	48.0	1008	0.3928	0.8910
0.0814	49.0	1029	0.3428	0.8847
0.091	50.0	1050	0.3141	0.9065
0.0777	51.0	1071	0.4016	0.8785
0.0644	52.0	1092	0.3398	0.8972
0.1019	53.0	1113	0.3559	0.8847
0.076	54.0	1134	0.3503	0.8910
0.067	55.0	1155	0.3245	0.8910
0.0679	56.0	1176	0.3099	0.9034
0.0661	57.0	1197	0.3249	0.8723
0.0716	58.0	1218	0.3016	0.9034
0.075	59.0	1239	0.4144	0.8692
0.0874	60.0	1260	0.3850	0.8723
0.0821	61.0	1281	0.2938	0.9065
0.0735	62.0	1302	0.2518	0.9190
0.0755	63.0	1323	0.4015	0.8972
0.2235	64.0	1344	0.3127	0.8972
0.0631	65.0	1365	0.2518	0.9128
0.0711	66.0	1386	0.3544	0.8941
0.0671	67.0	1407	0.3616	0.8816
0.059	68.0	1428	0.2567	0.9097
0.0558	69.0	1449	0.3696	0.8692
0.0755	70.0	1470	0.3032	0.9065
0.0666	71.0	1491	0.2819	0.9128
0.0519	72.0	1512	0.2179	0.9252
0.0443	73.0	1533	0.2722	0.9159
0.0415	74.0	1554	0.2167	0.9346
0.0632	75.0	1575	0.2115	0.9377
0.067	76.0	1596	0.4024	0.8785
0.0592	77.0	1617	0.2328	0.9283
0.0528	78.0	1638	0.2425	0.9065
0.0462	79.0	1659	0.2385	0.9252
0.0248	80.0	1680	0.2694	0.9159
0.04	81.0	1701	0.2192	0.9283
0.0436	82.0	1722	0.2697	0.9221
0.0415	83.0	1743	0.2855	0.9128
0.0431	84.0	1764	0.1680	0.9502
0.0438	85.0	1785	0.2513	0.9221
0.0385	86.0	1806	0.2609	0.9190
0.0291	87.0	1827	0.2136	0.9439
0.0326	88.0	1848	0.2069	0.9439
0.0347	89.0	1869	0.2450	0.9315
0.0393	90.0	1890	0.2609	0.9377
0.0355	91.0	1911	0.1932	0.9408
0.0423	92.0	1932	0.2481	0.9315
0.0386	93.0	1953	0.1963	0.9377
0.029	94.0	1974	0.2220	0.9377
0.0383	95.0	1995	0.2626	0.9252
0.0205	96.0	2016	0.1894	0.9470
0.0392	97.0	2037	0.1744	0.9502
0.0282	98.0	2058	0.2907	0.9190
0.0416	99.0	2079	0.1868	0.9533
0.0223	100.0	2100	0.2201	0.9377

Framework versions

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