meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_14

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: 0.1627
• Accuracy: 0.9470

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
1.0987	1.0	21	1.0847	0.4361
1.0683	2.0	42	1.0508	0.5171
1.0224	3.0	63	1.0214	0.4704
0.9556	4.0	84	0.9954	0.4891
0.9266	5.0	105	0.9473	0.5389
0.9168	6.0	126	0.8557	0.5919
0.7754	7.0	147	0.8971	0.5763
0.7383	8.0	168	0.6777	0.7695
0.6482	9.0	189	0.7117	0.7009
0.5976	10.0	210	0.5923	0.7757
0.6336	11.0	231	0.5497	0.7975
0.5193	12.0	252	0.6389	0.7383
0.4496	13.0	273	0.5799	0.7632
0.4089	14.0	294	0.5227	0.8006
0.3668	15.0	315	0.5907	0.7539
0.3644	16.0	336	0.7197	0.7414
0.3398	17.0	357	0.4430	0.8255
0.2927	18.0	378	0.5855	0.7819
0.3007	19.0	399	0.4378	0.8287
0.252	20.0	420	0.3540	0.8816
0.3041	21.0	441	0.5140	0.8162
0.2773	22.0	462	0.4456	0.8287
0.2474	23.0	483	0.4632	0.8100
0.2469	24.0	504	0.5080	0.8131
0.2201	25.0	525	0.3787	0.8660
0.167	26.0	546	0.3245	0.8723
0.1614	27.0	567	0.5479	0.8287
0.1585	28.0	588	0.3292	0.8598
0.1686	29.0	609	0.5806	0.7944
0.2157	30.0	630	0.4449	0.8193
0.1846	31.0	651	0.6371	0.7850
0.1614	32.0	672	0.3739	0.8754
0.1214	33.0	693	0.3230	0.8879
0.1294	34.0	714	0.4792	0.8442
0.112	35.0	735	0.3600	0.8847
0.1436	36.0	756	0.4445	0.8567
0.121	37.0	777	0.3601	0.8785
0.1524	38.0	798	0.4202	0.8567
0.1221	39.0	819	0.3454	0.8754
0.1397	40.0	840	0.4782	0.8536
0.1608	41.0	861	0.5481	0.8224
0.1207	42.0	882	0.3432	0.8660
0.1176	43.0	903	0.3480	0.8816
0.1072	44.0	924	0.3242	0.8785
0.0989	45.0	945	0.3556	0.8847
0.0946	46.0	966	0.3630	0.8723
0.1087	47.0	987	0.2972	0.8910
0.2532	48.0	1008	0.2845	0.9097
0.0912	49.0	1029	0.3424	0.8816
0.1181	50.0	1050	0.2204	0.9159
0.0925	51.0	1071	0.3311	0.8785
0.1092	52.0	1092	0.2445	0.9221
0.0924	53.0	1113	0.3297	0.8879
0.0871	54.0	1134	0.1846	0.9315
0.0799	55.0	1155	0.3486	0.9034
0.1778	56.0	1176	0.3292	0.8941
0.1039	57.0	1197	0.4066	0.8567
0.0732	58.0	1218	0.3245	0.9097
0.0642	59.0	1239	0.2939	0.9190
0.0811	60.0	1260	0.4293	0.8847
0.0679	61.0	1281	0.3204	0.8941
0.0563	62.0	1302	0.3244	0.9190
0.0868	63.0	1323	0.2359	0.9315
0.1067	64.0	1344	0.2720	0.9159
0.0696	65.0	1365	0.3054	0.9003
0.0586	66.0	1386	0.3045	0.9003
0.0612	67.0	1407	0.3321	0.8972
0.059	68.0	1428	0.3224	0.9003
0.0669	69.0	1449	0.3123	0.9003
0.056	70.0	1470	0.2288	0.9252
0.0517	71.0	1491	0.2590	0.9221
0.0496	72.0	1512	0.2533	0.9252
0.0462	73.0	1533	0.2943	0.9065
0.0457	74.0	1554	0.2280	0.9377
0.051	75.0	1575	0.3099	0.9128
0.0395	76.0	1596	0.2711	0.9221
0.0338	77.0	1617	0.1932	0.9408
0.0483	78.0	1638	0.1974	0.9533
0.0506	79.0	1659	0.2310	0.9283
0.0362	80.0	1680	0.2853	0.9252
0.0485	81.0	1701	0.1954	0.9408
0.0448	82.0	1722	0.2609	0.9252
0.0313	83.0	1743	0.2825	0.9190
0.0506	84.0	1764	0.3219	0.9065
0.0379	85.0	1785	0.2786	0.9221
0.0345	86.0	1806	0.3341	0.9065
0.019	87.0	1827	0.2731	0.9346
0.0438	88.0	1848	0.2449	0.9252
0.0321	89.0	1869	0.2719	0.9252
0.0478	90.0	1890	0.2214	0.9408
0.0598	91.0	1911	0.2174	0.9315
0.0372	92.0	1932	0.2075	0.9315
0.0422	93.0	1953	0.1781	0.9439
0.0324	94.0	1974	0.1692	0.9470
0.0325	95.0	1995	0.1999	0.9408
0.0369	96.0	2016	0.1929	0.9346
0.0309	97.0	2037	0.2310	0.9315
0.0347	98.0	2058	0.1347	0.9626
0.0445	99.0	2079	0.1967	0.9470
0.0337	100.0	2100	0.1627	0.9470

Framework versions

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