meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_6

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: 0.2352
• 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: 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
1.1152	1.0	21	1.0916	0.3801
1.0864	2.0	42	1.0644	0.4361
1.0324	3.0	63	1.0130	0.4766
0.9613	4.0	84	0.9579	0.5607
0.9331	5.0	105	0.8873	0.6044
0.8671	6.0	126	0.8661	0.5981
0.7318	7.0	147	0.8945	0.5545
0.7254	8.0	168	0.6857	0.7227
0.7335	9.0	189	0.7473	0.6822
0.5766	10.0	210	0.8212	0.6760
0.6084	11.0	231	0.6611	0.7383
0.4562	12.0	252	0.5661	0.7882
0.4669	13.0	273	0.6090	0.7664
0.4217	14.0	294	0.8163	0.6760
0.4267	15.0	315	0.6919	0.7134
0.3741	16.0	336	0.4754	0.8255
0.3325	17.0	357	0.5114	0.8069
0.298	18.0	378	0.5082	0.8069
0.2493	19.0	399	0.4226	0.8255
0.2422	20.0	420	0.4855	0.8255
0.2086	21.0	441	0.5766	0.7913
0.229	22.0	462	0.5744	0.7913
0.2352	23.0	483	0.4443	0.8318
0.2055	24.0	504	0.4859	0.8255
0.1953	25.0	525	0.4014	0.8598
0.2064	26.0	546	0.4137	0.8474
0.1801	27.0	567	0.4048	0.8536
0.1797	28.0	588	0.3656	0.8847
0.1676	29.0	609	0.4490	0.8505
0.1748	30.0	630	0.4745	0.8349
0.1896	31.0	651	0.4727	0.8411
0.1507	32.0	672	0.3046	0.8660
0.1744	33.0	693	0.4198	0.8692
0.122	34.0	714	0.4129	0.8474
0.1495	35.0	735	0.4908	0.8224
0.164	36.0	756	0.4992	0.8411
0.1876	37.0	777	0.3301	0.8816
0.287	38.0	798	0.4695	0.8349
0.14	39.0	819	0.4662	0.8318
0.1043	40.0	840	0.4756	0.8474
0.1275	41.0	861	0.3540	0.8785
0.1201	42.0	882	0.4236	0.8536
0.131	43.0	903	0.4375	0.8598
0.0773	44.0	924	0.4115	0.8723
0.1095	45.0	945	0.4374	0.8598
0.0934	46.0	966	0.3057	0.8972
0.2323	47.0	987	0.4779	0.8536
0.1005	48.0	1008	0.2861	0.9065
0.1041	49.0	1029	0.3541	0.8910
0.1067	50.0	1050	0.3192	0.8941
0.1206	51.0	1071	0.3898	0.8816
0.0798	52.0	1092	0.4014	0.8723
0.088	53.0	1113	0.3105	0.9097
0.1013	54.0	1134	0.3736	0.8785
0.0896	55.0	1155	0.2967	0.8972
0.0862	56.0	1176	0.3588	0.8879
0.0686	57.0	1197	0.2938	0.8941
0.0847	58.0	1218	0.4074	0.8910
0.0953	59.0	1239	0.3553	0.8910
0.0854	60.0	1260	0.2624	0.9097
0.0712	61.0	1281	0.3190	0.9065
0.0699	62.0	1302	0.2595	0.9190
0.0644	63.0	1323	0.2592	0.9190
0.0754	64.0	1344	0.2786	0.9003
0.0548	65.0	1365	0.2758	0.9159
0.0715	66.0	1386	0.2817	0.9003
0.0806	67.0	1407	0.2805	0.9065
0.0485	68.0	1428	0.2198	0.9159
0.0688	69.0	1449	0.3272	0.8941
0.0713	70.0	1470	0.4739	0.8754
0.0746	71.0	1491	0.2930	0.9065
0.0753	72.0	1512	0.3323	0.8972
0.0565	73.0	1533	0.2289	0.9190
0.0509	74.0	1554	0.5005	0.8536
0.0787	75.0	1575	0.2635	0.9128
0.0541	76.0	1596	0.3005	0.9128
0.0415	77.0	1617	0.2386	0.9315
0.0538	78.0	1638	0.3808	0.8972
0.064	79.0	1659	0.1887	0.9252
0.0549	80.0	1680	0.3037	0.9034
0.0547	81.0	1701	0.2018	0.9283
0.0404	82.0	1722	0.2307	0.9315
0.0438	83.0	1743	0.2480	0.9159
0.0298	84.0	1764	0.2932	0.9221
0.0409	85.0	1785	0.2534	0.9252
0.028	86.0	1806	0.3352	0.9065
0.0421	87.0	1827	0.3456	0.8972
0.0376	88.0	1848	0.2733	0.9221
0.0413	89.0	1869	0.3693	0.8941
0.035	90.0	1890	0.2873	0.9159
0.0688	91.0	1911	0.1962	0.9439
0.0438	92.0	1932	0.2506	0.9252
0.046	93.0	1953	0.2469	0.9252
0.0325	94.0	1974	0.2693	0.9190
0.0315	95.0	1995	0.1809	0.9533
0.0417	96.0	2016	0.2053	0.9315
0.0511	97.0	2037	0.2489	0.9346
0.0305	98.0	2058	0.2066	0.9315
0.0301	99.0	2079	0.2825	0.9159
0.0371	100.0	2100	0.2352	0.9283

Framework versions

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