ViT_L16

This model is a fine-tuned version of google/mobilenet_v2_1.4_224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1493
• Accuracy: 0.9586
• Precision: 0.9825
• Recall: 0.9267
• F1: 0.9538
• Tp: 1518
• Tn: 1883
• Fp: 27
• Fn: 120

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-06
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 552
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Tp	Tn	Fp	Fn
0.6498	0.2477	55	0.6233	0.5950	0.7445	0.1868	0.2987	306	1805	105	1332
0.6063	0.4955	110	0.6222	0.6206	0.7160	0.2955	0.4183	484	1718	192	1154
0.5307	0.7432	165	0.4872	0.8120	0.9036	0.6636	0.7652	1087	1794	116	551
0.4383	0.9910	220	0.4204	0.8695	0.8808	0.8297	0.8544	1359	1726	184	279
0.3821	1.2387	275	0.4293	0.8171	0.7416	0.9267	0.8239	1518	1381	529	120
0.3412	1.4865	330	0.3600	0.8763	0.8601	0.8742	0.8671	1432	1677	233	206
0.3323	1.7342	385	0.5002	0.7562	0.7125	0.7912	0.7498	1296	1387	523	342
0.3128	1.9820	440	0.3087	0.9073	0.9078	0.8895	0.8986	1457	1762	148	181
0.2916	2.2297	495	0.3092	0.9005	0.8640	0.9310	0.8963	1525	1670	240	113
0.2882	2.4775	550	0.4698	0.7802	0.6864	0.9646	0.8020	1580	1188	722	58
0.2775	2.7252	605	0.2448	0.9332	0.9420	0.9115	0.9265	1493	1818	92	145
0.2577	2.9730	660	0.2544	0.9239	0.9264	0.9072	0.9167	1486	1792	118	152
0.2541	3.2207	715	0.2914	0.9028	0.8542	0.9518	0.9004	1559	1644	266	79
0.2499	3.4685	770	0.2302	0.9281	0.9314	0.9115	0.9213	1493	1800	110	145
0.2356	3.7162	825	0.2430	0.9284	0.9109	0.9365	0.9235	1534	1760	150	104
0.2403	3.9640	880	0.2341	0.9169	0.8929	0.9316	0.9119	1526	1727	183	112
0.2454	4.2117	935	0.3786	0.8396	0.7642	0.9438	0.8446	1546	1433	477	92
0.2296	4.4595	990	0.3143	0.8591	0.8014	0.9237	0.8582	1513	1535	375	125
0.2311	4.7072	1045	0.3683	0.8238	0.7346	0.9683	0.8354	1586	1337	573	52
0.2181	4.9550	1100	0.1968	0.9380	0.9350	0.9304	0.9327	1524	1804	106	114
0.2119	5.2027	1155	0.3088	0.8661	0.7987	0.9493	0.8675	1555	1518	392	83
0.2222	5.4505	1210	0.3543	0.8503	0.7780	0.9457	0.8537	1549	1468	442	89
0.2047	5.6982	1265	0.1789	0.9462	0.9485	0.9341	0.9412	1530	1827	83	108
0.2169	5.9459	1320	0.1936	0.9414	0.9503	0.9212	0.9355	1509	1831	79	129
0.2233	6.1937	1375	0.2493	0.8949	0.8388	0.9560	0.8936	1566	1609	301	72
0.2245	6.4414	1430	0.2624	0.8797	0.8172	0.9524	0.8796	1560	1561	349	78
0.2220	6.6892	1485	0.2528	0.9101	0.8586	0.9640	0.9083	1579	1650	260	59
0.2158	6.9369	1540	0.2083	0.9290	0.9130	0.9353	0.9240	1532	1764	146	106
0.2151	7.1847	1595	0.1952	0.9394	0.9273	0.9426	0.9349	1544	1789	121	94
0.2192	7.4324	1650	0.2952	0.8670	0.7941	0.9609	0.8696	1574	1502	408	64
0.2162	7.6802	1705	0.2100	0.9247	0.9025	0.9383	0.9201	1537	1744	166	101
0.1981	7.9279	1760	0.1673	0.9487	0.9522	0.9359	0.9440	1533	1833	77	105
0.2019	8.1757	1815	0.2276	0.9146	0.8739	0.9524	0.9115	1560	1685	225	78
0.2292	8.4234	1870	0.1978	0.9377	0.9170	0.9512	0.9338	1558	1769	141	80
0.2045	8.6712	1925	0.1614	0.9546	0.9953	0.9060	0.9485	1484	1903	7	154
0.2145	8.9189	1980	0.1544	0.9580	0.9794	0.9286	0.9533	1521	1878	32	117
0.1937	9.1667	2035	0.1571	0.9515	0.9747	0.9188	0.9459	1505	1871	39	133
0.2071	9.4144	2090	0.1948	0.9374	0.9194	0.9475	0.9333	1552	1774	136	86
0.2136	9.6622	2145	0.2500	0.8861	0.8324	0.9432	0.8844	1545	1599	311	93
0.1980	9.9099	2200	0.1493	0.9586	0.9825	0.9267	0.9538	1518	1883	27	120

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2