meat_calssify_fresh_crop_fixed_overlap_epoch100_V_0_13

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: 0.1337
• Accuracy: 0.9595

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
1.0893	1.0	21	1.0721	0.4922
1.057	2.0	42	1.0397	0.5234
1.018	3.0	63	0.9985	0.5265
0.9639	4.0	84	0.9241	0.5794
0.8882	5.0	105	0.8763	0.6231
0.8154	6.0	126	0.8003	0.6542
0.6905	7.0	147	0.8660	0.5981
0.7078	8.0	168	0.7604	0.6729
0.6762	9.0	189	0.7024	0.7134
0.5977	10.0	210	0.7110	0.6854
0.516	11.0	231	0.6112	0.7383
0.4939	12.0	252	0.5301	0.7882
0.4254	13.0	273	0.5863	0.7664
0.4009	14.0	294	0.6802	0.7103
0.4477	15.0	315	0.6327	0.7508
0.3547	16.0	336	0.4456	0.8442
0.3203	17.0	357	0.5052	0.7975
0.3331	18.0	378	0.4561	0.8442
0.3304	19.0	399	0.5010	0.8131
0.3035	20.0	420	0.4363	0.8474
0.2585	21.0	441	0.4671	0.8224
0.2425	22.0	462	0.4404	0.8474
0.2911	23.0	483	0.4463	0.8442
0.2466	24.0	504	0.3739	0.8692
0.2028	25.0	525	0.3317	0.8754
0.1761	26.0	546	0.5032	0.8287
0.2257	27.0	567	0.4841	0.8567
0.2464	28.0	588	0.3266	0.8941
0.1637	29.0	609	0.5122	0.8193
0.2037	30.0	630	0.3683	0.8847
0.1592	31.0	651	0.3185	0.8785
0.1779	32.0	672	0.4130	0.8660
0.1726	33.0	693	0.2861	0.9128
0.1685	34.0	714	0.3174	0.8910
0.1571	35.0	735	0.3252	0.8941
0.1315	36.0	756	0.4721	0.8224
0.2717	37.0	777	0.4957	0.8380
0.1968	38.0	798	0.2139	0.9346
0.1257	39.0	819	0.2550	0.9003
0.1178	40.0	840	0.3248	0.8816
0.1101	41.0	861	0.3600	0.8847
0.117	42.0	882	0.4135	0.8567
0.1339	43.0	903	0.3311	0.8847
0.1098	44.0	924	0.4151	0.8660
0.0872	45.0	945	0.2727	0.9097
0.1106	46.0	966	0.3106	0.9065
0.0955	47.0	987	0.2232	0.9315
0.1308	48.0	1008	0.2594	0.9128
0.0809	49.0	1029	0.2846	0.9065
0.1123	50.0	1050	0.2310	0.9221
0.0971	51.0	1071	0.3536	0.8879
0.1126	52.0	1092	0.3048	0.8972
0.0909	53.0	1113	0.2762	0.9097
0.089	54.0	1134	0.2672	0.9065
0.0881	55.0	1155	0.3479	0.8972
0.0852	56.0	1176	0.3397	0.9003
0.0712	57.0	1197	0.2242	0.9252
0.0844	58.0	1218	0.2430	0.9221
0.0619	59.0	1239	0.3453	0.8785
0.0904	60.0	1260	0.2579	0.9190
0.0704	61.0	1281	0.2337	0.9252
0.0637	62.0	1302	0.2778	0.9128
0.0752	63.0	1323	0.2019	0.9315
0.0759	64.0	1344	0.2226	0.9221
0.048	65.0	1365	0.3095	0.9003
0.0546	66.0	1386	0.3657	0.8972
0.0664	67.0	1407	0.3862	0.8972
0.0584	68.0	1428	0.2183	0.9408
0.0704	69.0	1449	0.2288	0.9283
0.0444	70.0	1470	0.2355	0.9252
0.0475	71.0	1491	0.1171	0.9626
0.0594	72.0	1512	0.2632	0.9252
0.0428	73.0	1533	0.2323	0.9346
0.0501	74.0	1554	0.2586	0.9221
0.0556	75.0	1575	0.2172	0.9252
0.0427	76.0	1596	0.2898	0.9097
0.0572	77.0	1617	0.1617	0.9502
0.038	78.0	1638	0.2294	0.9221
0.0453	79.0	1659	0.1670	0.9502
0.0378	80.0	1680	0.1205	0.9595
0.0444	81.0	1701	0.1833	0.9470
0.065	82.0	1722	0.2581	0.9252
0.0498	83.0	1743	0.2651	0.9315
0.0607	84.0	1764	0.2678	0.9221
0.0554	85.0	1785	0.1547	0.9470
0.0313	86.0	1806	0.1567	0.9533
0.0267	87.0	1827	0.1955	0.9346
0.0377	88.0	1848	0.1900	0.9346
0.0388	89.0	1869	0.1831	0.9377
0.0297	90.0	1890	0.1823	0.9470
0.0424	91.0	1911	0.2606	0.9315
0.0459	92.0	1932	0.1478	0.9502
0.0308	93.0	1953	0.1695	0.9439
0.0415	94.0	1974	0.1325	0.9564
0.0387	95.0	1995	0.0877	0.9751
0.0318	96.0	2016	0.1765	0.9408
0.0317	97.0	2037	0.1650	0.9564
0.0198	98.0	2058	0.2043	0.9439
0.0422	99.0	2079	0.1777	0.9377
0.0335	100.0	2100	0.1337	0.9595

Framework versions

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