meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_2

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: 0.2175
• Accuracy: 0.9283

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: 128
• 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
1.1008	1.0	11	1.0912	0.3583
1.0751	2.0	22	1.0569	0.5140
1.0562	3.0	33	1.0284	0.4891
0.9901	4.0	44	0.9771	0.5607
0.9179	5.0	55	0.9142	0.5888
0.8217	6.0	66	0.8546	0.6262
0.7811	7.0	77	0.7960	0.6791
0.8756	8.0	88	0.7693	0.6760
0.8095	9.0	99	0.7796	0.6636
0.6492	10.0	110	0.7908	0.6760
0.6357	11.0	121	0.7367	0.6885
0.6184	12.0	132	0.7575	0.6542
0.5371	13.0	143	0.5625	0.8069
0.5586	14.0	154	0.5400	0.7819
0.4235	15.0	165	0.5775	0.7664
0.5082	16.0	176	0.5360	0.7819
0.3758	17.0	187	0.5193	0.8131
0.3729	18.0	198	0.6018	0.7695
0.5911	19.0	209	0.4724	0.8224
0.3055	20.0	220	0.4877	0.8162
0.3054	21.0	231	0.5504	0.7726
0.2947	22.0	242	0.5059	0.8069
0.2336	23.0	253	0.4085	0.8598
0.2806	24.0	264	0.5123	0.8193
0.2782	25.0	275	0.4825	0.8131
0.2396	26.0	286	0.3329	0.8910
0.1937	27.0	297	0.3984	0.8816
0.5237	28.0	308	0.5059	0.8224
0.1951	29.0	319	0.6188	0.7757
0.2097	30.0	330	0.3235	0.8754
0.1443	31.0	341	0.4216	0.8567
0.1856	32.0	352	0.3461	0.8785
0.1837	33.0	363	0.3602	0.8723
0.2783	34.0	374	0.3804	0.8660
0.1553	35.0	385	0.3125	0.8879
0.1413	36.0	396	0.3002	0.8972
0.1582	37.0	407	0.3564	0.8723
0.1573	38.0	418	0.4468	0.8380
0.188	39.0	429	0.4019	0.8505
0.1562	40.0	440	0.2482	0.9221
0.1295	41.0	451	0.4421	0.8349
0.1472	42.0	462	0.3083	0.8972
0.12	43.0	473	0.2961	0.9003
0.1056	44.0	484	0.3540	0.8692
0.1121	45.0	495	0.3734	0.8692
0.1055	46.0	506	0.3385	0.8785
0.2452	47.0	517	0.3638	0.8629
0.1398	48.0	528	0.3100	0.8941
0.1255	49.0	539	0.2797	0.9034
0.0972	50.0	550	0.2636	0.9034
0.1057	51.0	561	0.2505	0.9003
0.0929	52.0	572	0.3668	0.8816
0.0991	53.0	583	0.2946	0.8972
0.0994	54.0	594	0.2765	0.9065
0.0949	55.0	605	0.2876	0.9097
0.2796	56.0	616	0.2407	0.9221
0.071	57.0	627	0.3321	0.8941
0.1163	58.0	638	0.2527	0.9315
0.0966	59.0	649	0.2549	0.9252
0.0871	60.0	660	0.3171	0.8879
0.216	61.0	671	0.2085	0.9283
0.0556	62.0	682	0.2115	0.9190
0.0842	63.0	693	0.2602	0.9097
0.0824	64.0	704	0.3565	0.8723
0.0765	65.0	715	0.2983	0.9003
0.3268	66.0	726	0.2924	0.8972
0.0881	67.0	737	0.2990	0.8941
0.0656	68.0	748	0.2518	0.9128
0.0707	69.0	759	0.2702	0.9003
0.0609	70.0	770	0.2493	0.9190
0.0882	71.0	781	0.2210	0.9252
0.0706	72.0	792	0.2242	0.9252
0.0569	73.0	803	0.2450	0.9097
0.0476	74.0	814	0.1686	0.9408
0.0587	75.0	825	0.2537	0.9159
0.056	76.0	836	0.2437	0.9190
0.0613	77.0	847	0.2664	0.9128
0.0554	78.0	858	0.2851	0.9003
0.0522	79.0	869	0.2326	0.9221
0.0564	80.0	880	0.2392	0.9283
0.052	81.0	891	0.2298	0.9252
0.0489	82.0	902	0.2626	0.9190
0.0545	83.0	913	0.2442	0.9159
0.054	84.0	924	0.1613	0.9439
0.0481	85.0	935	0.2730	0.9190
0.0541	86.0	946	0.2194	0.9315
0.0489	87.0	957	0.1749	0.9470
0.0515	88.0	968	0.1577	0.9502
0.05	89.0	979	0.2191	0.9252
0.0484	90.0	990	0.2574	0.9252
0.0503	91.0	1001	0.1792	0.9408
0.0434	92.0	1012	0.2147	0.9377
0.0449	93.0	1023	0.2430	0.9159
0.0464	94.0	1034	0.2486	0.9159
0.0469	95.0	1045	0.1922	0.9408
0.0449	96.0	1056	0.2005	0.9283
0.0456	97.0	1067	0.2175	0.9346
0.0425	98.0	1078	0.1975	0.9346
0.0419	99.0	1089	0.2070	0.9283
0.0363	100.0	1100	0.2175	0.9283

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0
• Datasets 2.19.2
• Tokenizers 0.19.1