efficientnet-b0

This model is a fine-tuned version of google/efficientnet-b0 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0460
• Accuracy: 0.9868
• Precision: 0.9944
• Recall: 0.9768
• F1: 0.9855
• Tp: 1600
• Tn: 1901
• Fp: 9
• Fn: 38

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: 0.0003
• train_batch_size: 128
• eval_batch_size: 128
• 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: 55
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Tp	Tn	Fp	Fn
0.1420	0.0991	11	0.0896	0.9777	0.9809	0.9707	0.9758	1590	1879	31	48
0.1258	0.1982	22	0.0769	0.9845	0.9944	0.9719	0.9830	1592	1901	9	46
0.1397	0.2973	33	0.0904	0.9797	0.9821	0.9737	0.9779	1595	1881	29	43
0.1355	0.3964	44	0.0796	0.9803	0.9775	0.9799	0.9787	1605	1873	37	33
0.1395	0.4955	55	0.0982	0.9707	0.9565	0.9811	0.9687	1607	1837	73	31
0.1446	0.5946	66	0.0911	0.9775	0.9779	0.9731	0.9755	1594	1874	36	44
0.1362	0.6937	77	0.1183	0.9653	0.9501	0.9762	0.9630	1599	1826	84	39
0.1351	0.7928	88	0.1260	0.9704	0.9582	0.9786	0.9683	1603	1840	70	35
0.1650	0.8919	99	0.2204	0.9448	0.9083	0.9792	0.9424	1604	1748	162	34
0.1695	0.9910	110	0.0850	0.9794	0.9827	0.9725	0.9776	1593	1882	28	45
0.1571	1.0901	121	0.1192	0.9642	0.9967	0.9255	0.9598	1516	1905	5	122
0.1219	1.1892	132	0.0881	0.9738	0.9911	0.9518	0.9710	1559	1896	14	79
0.1456	1.2883	143	0.0895	0.9760	0.9911	0.9567	0.9736	1567	1896	14	71
0.1357	1.3874	154	0.1397	0.9572	0.9360	0.9737	0.9545	1595	1801	109	43
0.1516	1.4865	165	0.0801	0.9760	0.9755	0.9725	0.9740	1593	1870	40	45
0.1309	1.5856	176	0.0961	0.9707	0.9593	0.9780	0.9686	1602	1842	68	36
0.1430	1.6847	187	0.0573	0.9862	0.9975	0.9725	0.9849	1593	1906	4	45
0.1649	1.7838	198	0.0741	0.9808	0.9846	0.9737	0.9791	1595	1885	25	43
0.1575	1.8829	209	0.0638	0.9828	0.9962	0.9664	0.9811	1583	1904	6	55
0.1463	1.9820	220	0.0575	0.9853	0.9994	0.9689	0.9839	1587	1909	1	51
0.1375	2.0811	231	0.0587	0.9848	0.995	0.9719	0.9833	1592	1902	8	46
0.1264	2.1802	242	0.0637	0.9842	0.9913	0.9744	0.9828	1596	1896	14	42
0.1238	2.2793	253	0.0579	0.9851	0.9932	0.9744	0.9837	1596	1899	11	42
0.1521	2.3784	264	0.0558	0.9868	0.9963	0.9750	0.9855	1597	1904	6	41
0.1453	2.4775	275	0.0728	0.9853	0.9877	0.9805	0.9841	1606	1890	20	32
0.1527	2.5766	286	0.0702	0.9893	0.9975	0.9792	0.9883	1604	1906	4	34
0.1387	2.6757	297	0.0544	0.9884	0.9975	0.9774	0.9874	1601	1906	4	37
0.1397	2.7748	308	0.1035	0.9665	0.9502	0.9786	0.9642	1603	1826	84	35
0.1193	2.8739	319	0.0624	0.9851	0.9865	0.9811	0.9838	1607	1888	22	31
0.1358	2.9730	330	0.0782	0.9794	0.9815	0.9737	0.9776	1595	1880	30	43
0.1298	3.0721	341	0.0548	0.9873	0.9920	0.9805	0.9862	1606	1897	13	32
0.1428	3.1712	352	0.0909	0.9760	0.9698	0.9786	0.9742	1603	1860	50	35
0.1350	3.2703	363	0.0829	0.9777	0.9716	0.9805	0.9760	1606	1863	47	32
0.1231	3.3694	374	0.0606	0.9839	0.9829	0.9823	0.9826	1609	1882	28	29
0.1355	3.4685	385	0.0676	0.9814	0.9834	0.9762	0.9798	1599	1883	27	39
0.1236	3.5676	396	0.0571	0.9845	0.9919	0.9744	0.9831	1596	1897	13	42
0.1331	3.6667	407	0.0565	0.9851	0.9919	0.9756	0.9837	1598	1897	13	40
0.1495	3.7658	418	0.0656	0.9825	0.9864	0.9756	0.9810	1598	1888	22	40
0.1236	3.8649	429	0.0532	0.9870	0.9956	0.9762	0.9858	1599	1903	7	39
0.1385	3.9640	440	0.0583	0.9842	0.9883	0.9774	0.9828	1601	1891	19	37
0.1266	4.0631	451	0.0523	0.9859	0.9938	0.9756	0.9846	1598	1900	10	40
0.1266	4.1622	462	0.0950	0.9698	0.9587	0.9768	0.9676	1600	1841	69	38
0.1549	4.2613	473	0.0660	0.9797	0.9751	0.9811	0.9781	1607	1869	41	31
0.1208	4.3604	484	0.0493	0.9876	0.9969	0.9762	0.9864	1599	1905	5	39
0.1195	4.4595	495	0.0789	0.9763	0.9709	0.9780	0.9745	1602	1862	48	36
0.1163	4.5586	506	0.0504	0.9873	0.9975	0.9750	0.9861	1597	1906	4	41
0.1489	4.6577	517	0.0565	0.9834	0.9852	0.9786	0.9819	1603	1886	24	35
0.1176	4.7568	528	0.0534	0.9848	0.9901	0.9768	0.9834	1600	1894	16	38
0.1236	4.8559	539	0.0514	0.9859	0.9907	0.9786	0.9846	1603	1895	15	35
0.1268	4.9550	550	0.0460	0.9868	0.9944	0.9768	0.9855	1600	1901	9	38

Framework versions

• Transformers 5.2.0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2