meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_15

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: 0.1718
• Accuracy: 0.9564

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
1.1001	1.0	21	1.0997	0.3614
1.0637	2.0	42	1.0850	0.3863
1.0464	3.0	63	1.0524	0.4766
0.9569	4.0	84	0.9464	0.5763
0.8778	5.0	105	0.8916	0.6168
0.8396	6.0	126	0.8181	0.6573
0.7752	7.0	147	0.8517	0.6168
0.7765	8.0	168	1.0433	0.5140
0.7283	9.0	189	0.9781	0.5452
0.6714	10.0	210	0.6957	0.7165
0.5872	11.0	231	0.6338	0.7352
0.4924	12.0	252	0.5824	0.7757
0.4441	13.0	273	0.7042	0.7040
0.4818	14.0	294	0.4985	0.8100
0.4477	15.0	315	0.5176	0.8100
0.387	16.0	336	0.5820	0.7757
0.378	17.0	357	0.4651	0.8287
0.3353	18.0	378	0.5163	0.8037
0.3651	19.0	399	0.3980	0.8474
0.312	20.0	420	0.4217	0.8629
0.2572	21.0	441	0.4610	0.8255
0.25	22.0	462	0.4421	0.8349
0.2325	23.0	483	0.4322	0.8193
0.2384	24.0	504	0.4207	0.8380
0.2295	25.0	525	0.4298	0.8411
0.4004	26.0	546	0.4976	0.8224
0.2136	27.0	567	0.3272	0.8723
0.1851	28.0	588	0.3004	0.8941
0.1513	29.0	609	0.3198	0.8785
0.2132	30.0	630	0.3403	0.8879
0.1704	31.0	651	0.4112	0.8692
0.1639	32.0	672	0.3038	0.8941
0.2028	33.0	693	0.6632	0.7601
0.256	34.0	714	0.3475	0.8785
0.142	35.0	735	0.2709	0.9034
0.1358	36.0	756	0.2745	0.9034
0.1543	37.0	777	0.3139	0.8816
0.1214	38.0	798	0.2518	0.9128
0.1291	39.0	819	0.4121	0.8598
0.1423	40.0	840	0.2469	0.9128
0.1071	41.0	861	0.2351	0.9252
0.1259	42.0	882	0.3639	0.8785
0.1114	43.0	903	0.4624	0.8567
0.123	44.0	924	0.3147	0.8941
0.0914	45.0	945	0.3599	0.8879
0.1154	46.0	966	0.2986	0.9003
0.1001	47.0	987	0.2688	0.9034
0.0959	48.0	1008	0.2358	0.9159
0.0935	49.0	1029	0.2724	0.9159
0.104	50.0	1050	0.3857	0.8847
0.1158	51.0	1071	0.3359	0.8910
0.0766	52.0	1092	0.3030	0.8941
0.1048	53.0	1113	0.2648	0.9097
0.1065	54.0	1134	0.2859	0.9128
0.0738	55.0	1155	0.3660	0.8910
0.078	56.0	1176	0.2843	0.9221
0.0755	57.0	1197	0.4503	0.8816
0.1193	58.0	1218	0.5647	0.8006
0.1014	59.0	1239	0.4011	0.8660
0.0557	60.0	1260	0.3376	0.8941
0.054	61.0	1281	0.2309	0.9283
0.0674	62.0	1302	0.3222	0.9003
0.0845	63.0	1323	0.2429	0.9221
0.0721	64.0	1344	0.2247	0.9283
0.0711	65.0	1365	0.3134	0.9097
0.0881	66.0	1386	0.2918	0.9159
0.0753	67.0	1407	0.2734	0.9065
0.059	68.0	1428	0.3353	0.8754
0.0814	69.0	1449	0.3093	0.9159
0.1317	70.0	1470	0.1641	0.9439
0.0539	71.0	1491	0.1988	0.9470
0.0572	72.0	1512	0.2493	0.9159
0.0322	73.0	1533	0.2045	0.9315
0.0473	74.0	1554	0.2380	0.9315
0.0478	75.0	1575	0.1687	0.9377
0.0554	76.0	1596	0.2121	0.9315
0.0444	77.0	1617	0.2172	0.9439
0.0808	78.0	1638	0.3581	0.8910
0.0522	79.0	1659	0.2155	0.9408
0.0402	80.0	1680	0.2204	0.9283
0.0387	81.0	1701	0.1438	0.9564
0.0294	82.0	1722	0.3094	0.9221
0.0449	83.0	1743	0.2850	0.9128
0.029	84.0	1764	0.3040	0.9128
0.0419	85.0	1785	0.1831	0.9439
0.0297	86.0	1806	0.2211	0.9221
0.0382	87.0	1827	0.2203	0.9346
0.0524	88.0	1848	0.2093	0.9377
0.0524	89.0	1869	0.2195	0.9252
0.0446	90.0	1890	0.2358	0.9377
0.0423	91.0	1911	0.2129	0.9283
0.0434	92.0	1932	0.2199	0.9315
0.0429	93.0	1953	0.1954	0.9470
0.0302	94.0	1974	0.1379	0.9564
0.046	95.0	1995	0.1609	0.9502
0.0247	96.0	2016	0.1978	0.9315
0.0289	97.0	2037	0.1872	0.9439
0.0452	98.0	2058	0.2132	0.9377
0.0308	99.0	2079	0.1592	0.9377
0.0274	100.0	2100	0.1718	0.9564

Framework versions

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