meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_10

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: 0.2318
• 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
1.0968	1.0	21	1.0916	0.3551
1.0709	2.0	42	1.0570	0.4704
1.0215	3.0	63	1.0161	0.4891
0.9489	4.0	84	0.9513	0.5670
0.8937	5.0	105	0.8632	0.6106
0.7992	6.0	126	0.7990	0.6449
0.7194	7.0	147	0.7417	0.7227
0.6455	8.0	168	0.6491	0.7321
0.5874	9.0	189	0.6231	0.7072
0.5869	10.0	210	0.7566	0.6978
0.5565	11.0	231	0.5440	0.7913
0.5238	12.0	252	0.5628	0.7726
0.4397	13.0	273	0.5377	0.7882
0.3858	14.0	294	0.5161	0.7850
0.3587	15.0	315	0.6103	0.7726
0.3383	16.0	336	0.5065	0.7850
0.2967	17.0	357	0.4653	0.8224
0.4375	18.0	378	0.4497	0.8255
0.2805	19.0	399	0.5011	0.8287
0.2937	20.0	420	0.4294	0.8318
0.2917	21.0	441	0.4914	0.8224
0.2387	22.0	462	0.5050	0.8255
0.219	23.0	483	0.4312	0.8692
0.2975	24.0	504	0.4167	0.8598
0.2482	25.0	525	0.4272	0.8536
0.1913	26.0	546	0.3625	0.8660
0.1896	27.0	567	0.5346	0.7944
0.1937	28.0	588	0.3983	0.8629
0.1517	29.0	609	0.3777	0.8629
0.3356	30.0	630	0.3373	0.8941
0.1562	31.0	651	0.3154	0.8879
0.1494	32.0	672	0.3680	0.8692
0.1677	33.0	693	0.3984	0.8629
0.2689	34.0	714	0.2916	0.8910
0.1302	35.0	735	0.3458	0.8754
0.1374	36.0	756	0.2694	0.9065
0.2007	37.0	777	0.3715	0.8723
0.1404	38.0	798	0.4245	0.8723
0.1154	39.0	819	0.4718	0.8442
0.2125	40.0	840	0.3549	0.8910
0.1087	41.0	861	0.4262	0.8567
0.1156	42.0	882	0.3013	0.8910
0.1011	43.0	903	0.3019	0.9097
0.11	44.0	924	0.2630	0.9128
0.1233	45.0	945	0.3000	0.8972
0.1236	46.0	966	0.3547	0.8660
0.1571	47.0	987	0.3384	0.8879
0.0855	48.0	1008	0.3221	0.8816
0.1155	49.0	1029	0.4779	0.8536
0.1089	50.0	1050	0.3355	0.9034
0.0939	51.0	1071	0.2130	0.9221
0.0826	52.0	1092	0.3103	0.9097
0.0943	53.0	1113	0.3179	0.9034
0.0574	54.0	1134	0.3351	0.8972
0.0818	55.0	1155	0.2165	0.9315
0.0863	56.0	1176	0.3347	0.8879
0.0963	57.0	1197	0.3789	0.8972
0.0762	58.0	1218	0.3579	0.8972
0.0898	59.0	1239	0.2550	0.9159
0.0802	60.0	1260	0.2112	0.9221
0.0698	61.0	1281	0.3252	0.9097
0.0764	62.0	1302	0.4277	0.8754
0.0781	63.0	1323	0.3593	0.8879
0.0939	64.0	1344	0.3397	0.8941
0.0669	65.0	1365	0.3701	0.8847
0.0632	66.0	1386	0.2624	0.9097
0.0569	67.0	1407	0.2987	0.9221
0.0655	68.0	1428	0.3286	0.9003
0.0581	69.0	1449	0.2540	0.9283
0.0668	70.0	1470	0.2397	0.9346
0.0639	71.0	1491	0.2721	0.9190
0.0617	72.0	1512	0.2059	0.9377
0.0555	73.0	1533	0.4196	0.8879
0.0515	74.0	1554	0.2260	0.9346
0.0494	75.0	1575	0.3137	0.9097
0.0425	76.0	1596	0.3027	0.9128
0.0529	77.0	1617	0.2964	0.9221
0.0473	78.0	1638	0.2776	0.9190
0.0629	79.0	1659	0.2397	0.9346
0.0417	80.0	1680	0.2041	0.9408
0.0437	81.0	1701	0.2451	0.9408
0.0444	82.0	1722	0.2813	0.9315
0.0561	83.0	1743	0.2596	0.9159
0.0458	84.0	1764	0.2085	0.9346
0.0653	85.0	1785	0.3033	0.9221
0.0301	86.0	1806	0.1604	0.9470
0.0441	87.0	1827	0.3603	0.8941
0.0297	88.0	1848	0.2406	0.9377
0.0472	89.0	1869	0.3045	0.9190
0.0421	90.0	1890	0.2231	0.9377
0.0391	91.0	1911	0.2259	0.9439
0.0418	92.0	1932	0.2433	0.9377
0.0405	93.0	1953	0.2753	0.9221
0.0338	94.0	1974	0.1519	0.9533
0.0355	95.0	1995	0.2370	0.9408
0.028	96.0	2016	0.2116	0.9346
0.0248	97.0	2037	0.2833	0.9283
0.033	98.0	2058	0.2603	0.9221
0.0304	99.0	2079	0.2598	0.9252
0.0148	100.0	2100	0.2318	0.9439

Framework versions

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