meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_11

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: 0.2049
• Accuracy: 0.9315

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
1.089	1.0	21	1.0699	0.4642
1.0499	2.0	42	1.0288	0.5514
1.012	3.0	63	0.9738	0.5234
0.9484	4.0	84	0.9146	0.5763
0.8696	5.0	105	0.8897	0.6075
0.8194	6.0	126	0.8737	0.6168
0.7567	7.0	147	0.7329	0.6916
0.6649	8.0	168	0.7376	0.6978
0.6515	9.0	189	1.0486	0.5202
0.7191	10.0	210	0.7651	0.6636
0.573	11.0	231	0.7393	0.6885
0.4787	12.0	252	0.7596	0.6791
0.4838	13.0	273	0.6008	0.7788
0.4554	14.0	294	0.6622	0.7477
0.5433	15.0	315	0.6715	0.7196
0.4842	16.0	336	0.5973	0.7414
0.4186	17.0	357	0.5679	0.7757
0.3345	18.0	378	0.4770	0.8162
0.2651	19.0	399	0.4308	0.8442
0.2247	20.0	420	0.4637	0.8442
0.2601	21.0	441	0.3916	0.8723
0.2419	22.0	462	0.3525	0.8785
0.2626	23.0	483	0.4901	0.8380
0.2554	24.0	504	0.6997	0.7445
0.2352	25.0	525	0.2725	0.9159
0.2139	26.0	546	0.5544	0.8006
0.2456	27.0	567	0.3419	0.8785
0.2336	28.0	588	0.3981	0.8349
0.1654	29.0	609	0.3819	0.8474
0.1543	30.0	630	0.2538	0.9128
0.1744	31.0	651	0.4008	0.8536
0.1627	32.0	672	0.3453	0.8785
0.1641	33.0	693	0.2883	0.8972
0.1816	34.0	714	0.3159	0.8910
0.3087	35.0	735	0.5607	0.8131
0.1463	36.0	756	0.2616	0.9034
0.2832	37.0	777	0.3128	0.9003
0.1135	38.0	798	0.2374	0.9221
0.109	39.0	819	0.2972	0.9159
0.103	40.0	840	0.3414	0.8879
0.1084	41.0	861	0.5068	0.8318
0.1464	42.0	882	0.2895	0.9034
0.0994	43.0	903	0.2374	0.9221
0.0908	44.0	924	0.2381	0.9283
0.113	45.0	945	0.2854	0.9065
0.1415	46.0	966	0.2304	0.9283
0.0965	47.0	987	0.2900	0.9003
0.0773	48.0	1008	0.3234	0.8972
0.0749	49.0	1029	0.3964	0.8785
0.1094	50.0	1050	0.4835	0.8536
0.1152	51.0	1071	0.2459	0.9159
0.1123	52.0	1092	0.2469	0.9190
0.0837	53.0	1113	0.2169	0.9252
0.0944	54.0	1134	0.2855	0.9003
0.0975	55.0	1155	0.2581	0.9065
0.0738	56.0	1176	0.2912	0.8972
0.0735	57.0	1197	0.2847	0.9003
0.0773	58.0	1218	0.2194	0.9252
0.0917	59.0	1239	0.2202	0.9159
0.0843	60.0	1260	0.4062	0.8629
0.0796	61.0	1281	0.2564	0.9190
0.0592	62.0	1302	0.2795	0.9097
0.0526	63.0	1323	0.2589	0.9252
0.072	64.0	1344	0.1720	0.9470
0.0721	65.0	1365	0.3482	0.8972
0.0643	66.0	1386	0.2056	0.9315
0.0632	67.0	1407	0.2368	0.9377
0.0656	68.0	1428	0.1891	0.9346
0.0547	69.0	1449	0.2592	0.9315
0.0613	70.0	1470	0.2446	0.9221
0.0572	71.0	1491	0.1700	0.9439
0.0707	72.0	1512	0.1974	0.9377
0.0462	73.0	1533	0.3013	0.9221
0.045	74.0	1554	0.2223	0.9252
0.0729	75.0	1575	0.2085	0.9346
0.049	76.0	1596	0.2198	0.9470
0.0531	77.0	1617	0.2064	0.9439
0.047	78.0	1638	0.3139	0.9065
0.0484	79.0	1659	0.3167	0.9190
0.0572	80.0	1680	0.2002	0.9408
0.0356	81.0	1701	0.2248	0.9283
0.0405	82.0	1722	0.2738	0.9283
0.0502	83.0	1743	0.1940	0.9315
0.0403	84.0	1764	0.2541	0.9252
0.0334	85.0	1785	0.2284	0.9439
0.0395	86.0	1806	0.2369	0.9315
0.0359	87.0	1827	0.1361	0.9688
0.0412	88.0	1848	0.2190	0.9408
0.0399	89.0	1869	0.2068	0.9408
0.047	90.0	1890	0.2655	0.9159
0.0377	91.0	1911	0.1519	0.9377
0.0246	92.0	1932	0.2156	0.9377
0.0285	93.0	1953	0.2732	0.9315
0.0447	94.0	1974	0.2069	0.9315
0.0271	95.0	1995	0.2119	0.9377
0.0316	96.0	2016	0.2199	0.9377
0.0335	97.0	2037	0.1942	0.9439
0.0285	98.0	2058	0.1771	0.9439
0.0262	99.0	2079	0.1745	0.9470
0.0276	100.0	2100	0.2049	0.9315

Framework versions

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