ConvNeXtV2_Tiny_v1

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0001
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: 663
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.1981	1.0	222	0.2166	0.7833	0.6850	0.9823	0.8071
0.1752	2.0	444	0.0761	0.9831	0.9962	0.9670	0.9814
0.1949	3.0	666	0.0968	0.9744	0.9708	0.9737	0.9723
0.2268	4.0	888	0.1141	0.9569	0.9340	0.9756	0.9543
0.1607	5.0	1110	0.0756	0.9794	0.9839	0.9713	0.9776
0.1947	6.0	1332	0.0927	0.9713	0.9539	0.9853	0.9694
0.1371	7.0	1554	0.0563	0.9868	0.9889	0.9823	0.9856
0.1546	8.0	1776	0.0645	0.9856	0.9901	0.9786	0.9843
0.1402	9.0	1998	0.0613	0.9856	0.9865	0.9823	0.9844
0.1380	10.0	2220	0.0686	0.9842	0.9931	0.9725	0.9827
0.1513	11.0	2442	0.0754	0.9789	0.9682	0.9866	0.9773
0.1225	12.0	2664	0.0544	0.9845	0.9829	0.9835	0.9832
0.1459	13.0	2886	0.0604	0.9890	0.9988	0.9774	0.9880
0.1127	14.0	3108	0.0557	0.9884	0.9975	0.9774	0.9874
0.1950	15.0	3330	0.0443	0.9899	0.9938	0.9841	0.9890
0.1249	16.0	3552	0.0519	0.9882	0.9957	0.9786	0.9871
0.1705	17.0	3774	0.0556	0.9870	0.9848	0.9872	0.9860
0.1539	18.0	3996	0.0482	0.9901	0.9963	0.9823	0.9892
0.2072	19.0	4218	0.0503	0.9890	0.992	0.9841	0.9880
0.1602	20.0	4440	0.0514	0.9904	0.9963	0.9829	0.9896
0.1275	21.0	4662	0.0436	0.9907	0.9957	0.9841	0.9899
0.1030	22.0	4884	0.0416	0.9918	0.9975	0.9847	0.9911
0.1806	23.0	5106	0.0416	0.9918	0.9963	0.9860	0.9911
0.1248	24.0	5328	0.0489	0.9893	0.9914	0.9853	0.9884
0.1292	25.0	5550	0.0408	0.9907	0.9932	0.9866	0.9899
0.0732	26.0	5772	0.0399	0.9921	0.9969	0.9860	0.9914
0.1518	27.0	5994	0.0418	0.9907	0.9945	0.9853	0.9899
0.1213	28.0	6216	0.0411	0.9907	0.9951	0.9847	0.9899
0.0904	29.0	6438	0.0402	0.9907	0.9951	0.9847	0.9899
0.0839	30.0	6660	0.0418	0.9910	0.9957	0.9847	0.9902