kematangan-pisang-vit-h-14-100eph-224-telyu

This model is a fine-tuned version of google/vit-huge-patch14-224-in21k on the dataset kematangan pisang primer.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Recall	Specificity	Precision	Npv	Accuracy	F1
No log	1.0	187	0.3757	0.8980	0.9768	0.9387	0.9798	0.9307	0.9066
No log	2.0	374	0.2434	0.9469	0.9854	0.9464	0.9851	0.9547	0.9464
0.3226	3.0	561	0.1817	0.9616	0.9899	0.9593	0.9896	0.968	0.9604
0.3226	4.0	748	0.1778	0.9436	0.9862	0.9498	0.9865	0.9573	0.9459
0.3226	5.0	935	0.1710	0.9395	0.9842	0.9490	0.9847	0.952	0.9428
0.1007	6.0	1122	0.1100	0.9658	0.9907	0.9636	0.9904	0.9707	0.9646
0.1007	7.0	1309	0.1017	0.9689	0.9918	0.9640	0.9914	0.9733	0.9661
0.1007	8.0	1496	0.0911	0.9715	0.9926	0.9677	0.9923	0.976	0.9694
0.0882	9.0	1683	0.2328	0.8882	0.9735	0.9223	0.9762	0.92	0.8943
0.0882	10.0	1870	0.1409	0.9405	0.9851	0.9518	0.9857	0.9547	0.9442
0.0606	11.0	2057	0.1400	0.9388	0.9859	0.9570	0.9871	0.9573	0.9446
0.0606	12.0	2244	0.0992	0.9541	0.9889	0.9577	0.9890	0.9653	0.9556
0.0606	13.0	2431	0.0883	0.9747	0.9928	0.9669	0.9922	0.976	0.9697
0.0495	14.0	2618	0.1169	0.9601	0.9878	0.9492	0.9869	0.96	0.9521
0.0495	15.0	2805	0.1043	0.9547	0.9888	0.9595	0.9890	0.9653	0.9566
0.0495	16.0	2992	0.1056	0.9572	0.9903	0.9708	0.9912	0.9707	0.9624
0.0524	17.0	3179	0.2722	0.8751	0.9733	0.9335	0.9779	0.92	0.8825
0.0524	18.0	3366	0.0712	0.9667	0.9923	0.9713	0.9926	0.976	0.9688
0.0343	19.0	3553	0.0973	0.9576	0.9911	0.9762	0.9923	0.9733	0.9644
0.0343	20.0	3740	0.0733	0.9626	0.9905	0.9664	0.9906	0.9707	0.9642
0.0343	21.0	3927	0.0747	0.9789	0.9937	0.9701	0.9931	0.9787	0.9731
0.0359	22.0	4114	0.1891	0.9069	0.9794	0.9498	0.9825	0.9387	0.9164
0.0359	23.0	4301	0.0650	0.9773	0.9936	0.9703	0.9931	0.9787	0.9730
0.0359	24.0	4488	0.2470	0.8837	0.9741	0.9389	0.9781	0.9227	0.8924
0.0345	25.0	4675	0.0792	0.9619	0.9920	0.9784	0.9931	0.976	0.9681
0.0345	26.0	4862	0.1752	0.9323	0.9848	0.9610	0.9867	0.9547	0.9407
0.0329	27.0	5049	0.0451	0.9801	0.9939	0.9789	0.9937	0.9813	0.9794
0.0329	28.0	5236	0.0707	0.9786	0.9924	0.9708	0.9917	0.976	0.9740
0.0329	29.0	5423	0.1154	0.9594	0.9903	0.9706	0.9909	0.9707	0.9637
0.0206	30.0	5610	0.1213	0.9594	0.9903	0.9706	0.9909	0.9707	0.9637
0.0206	31.0	5797	0.0892	0.9652	0.9912	0.9708	0.9915	0.9733	0.9676
0.0206	32.0	5984	0.0765	0.9589	0.9895	0.9659	0.9898	0.968	0.9617
0.0208	33.0	6171	0.1340	0.9598	0.9911	0.9759	0.9921	0.9733	0.9658
0.0208	34.0	6358	0.0987	0.9572	0.9903	0.9708	0.9912	0.9707	0.9624
0.0242	35.0	6545	0.1154	0.9572	0.9903	0.9708	0.9912	0.9707	0.9624
0.0242	36.0	6732	0.3260	0.8859	0.9741	0.9382	0.9778	0.9227	0.8946
0.0242	37.0	6919	0.1599	0.9557	0.9892	0.9710	0.9901	0.968	0.9612
0.0218	38.0	7106	0.1251	0.9535	0.9893	0.9712	0.9904	0.968	0.9598
0.0218	39.0	7293	0.2713	0.9112	0.9803	0.9516	0.9832	0.9413	0.9206
0.0218	40.0	7480	0.1112	0.9598	0.9911	0.9759	0.9921	0.9733	0.9658
0.0175	41.0	7667	0.0745	0.9695	0.9921	0.9734	0.9923	0.976	0.9711
0.0175	42.0	7854	0.0876	0.9610	0.9904	0.9683	0.9908	0.9707	0.9640
0.02	43.0	8041	0.0901	0.9588	0.9904	0.9683	0.9910	0.9707	0.9626
0.02	44.0	8228	0.1402	0.9529	0.9894	0.9685	0.9904	0.968	0.9587
0.02	45.0	8415	0.1325	0.9572	0.9903	0.9708	0.9912	0.9707	0.9624
0.0163	46.0	8602	0.0987	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0163	47.0	8789	0.1056	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0163	48.0	8976	0.0599	0.9800	0.9948	0.9811	0.9949	0.984	0.9805
0.0091	49.0	9163	0.0611	0.9705	0.9929	0.9780	0.9934	0.9787	0.9735
0.0091	50.0	9350	0.0606	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0123	51.0	9537	0.0622	0.9816	0.9949	0.9797	0.9948	0.984	0.9806
0.0123	52.0	9724	0.1036	0.9588	0.9904	0.9683	0.9910	0.9707	0.9626
0.0123	53.0	9911	0.0854	0.9715	0.9930	0.9758	0.9933	0.9787	0.9734
0.0076	54.0	10098	0.0600	0.9773	0.9940	0.9769	0.9940	0.9813	0.9771
0.0076	55.0	10285	0.1901	0.9429	0.9875	0.9674	0.9891	0.9627	0.9508
0.0076	56.0	10472	0.1208	0.9614	0.9912	0.9731	0.9919	0.9733	0.9660
0.0118	57.0	10659	0.2020	0.9386	0.9866	0.9654	0.9884	0.96	0.9469
0.0118	58.0	10846	0.0568	0.9806	0.9942	0.9749	0.9938	0.9813	0.9774
0.0161	59.0	11033	0.0507	0.9806	0.9942	0.9749	0.9938	0.9813	0.9774
0.0161	60.0	11220	0.0830	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0161	61.0	11407	0.0931	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0086	62.0	11594	0.1000	0.9715	0.9930	0.9758	0.9933	0.9787	0.9734
0.0086	63.0	11781	0.1215	0.9588	0.9904	0.9683	0.9910	0.9707	0.9626
0.0086	64.0	11968	0.0695	0.9858	0.9958	0.9825	0.9956	0.9867	0.9841
0.0048	65.0	12155	0.0747	0.9752	0.9941	0.9767	0.9942	0.9813	0.9759
0.0048	66.0	12342	0.0733	0.9795	0.9940	0.9772	0.9938	0.9813	0.9783
0.0066	67.0	12529	0.1429	0.9551	0.9894	0.9683	0.9902	0.968	0.9601
0.0066	68.0	12716	0.1146	0.9673	0.9922	0.9733	0.9925	0.976	0.9699
0.0066	69.0	12903	0.1022	0.9737	0.9930	0.9760	0.9931	0.9787	0.9747
0.0068	70.0	13090	0.0850	0.9789	0.9941	0.9757	0.9939	0.9813	0.9772
0.0068	71.0	13277	0.1619	0.9509	0.9885	0.9660	0.9894	0.9653	0.9564
0.0068	72.0	13464	0.1334	0.9636	0.9911	0.9730	0.9917	0.9733	0.9674
0.0046	73.0	13651	0.1099	0.9636	0.9911	0.9730	0.9917	0.9733	0.9674
0.0046	74.0	13838	0.2110	0.9493	0.9884	0.9691	0.9896	0.9653	0.9561
0.0087	75.0	14025	0.1417	0.9572	0.9903	0.9708	0.9912	0.9707	0.9624
0.0087	76.0	14212	0.2051	0.9471	0.9884	0.9695	0.9899	0.9653	0.9546
0.0087	77.0	14399	0.1403	0.9641	0.9920	0.9781	0.9928	0.976	0.9694
0.0061	78.0	14586	0.2232	0.9408	0.9866	0.9650	0.9882	0.96	0.9485
0.0061	79.0	14773	0.0962	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0061	80.0	14960	0.1113	0.9683	0.9928	0.9803	0.9936	0.9787	0.9731
0.0076	81.0	15147	0.1090	0.9683	0.9928	0.9803	0.9936	0.9787	0.9731
0.0076	82.0	15334	0.0826	0.9741	0.9938	0.9803	0.9942	0.9813	0.9768
0.0023	83.0	15521	0.0644	0.9832	0.9950	0.9787	0.9947	0.984	0.9807
0.0023	84.0	15708	0.0605	0.9832	0.9950	0.9787	0.9947	0.984	0.9807
0.0023	85.0	15895	0.1132	0.9594	0.9903	0.9706	0.9909	0.9707	0.9637
0.0061	86.0	16082	0.0592	0.9773	0.9940	0.9769	0.9940	0.9813	0.9771
0.0061	87.0	16269	0.1200	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0061	88.0	16456	0.1636	0.9578	0.9902	0.9734	0.9911	0.9707	0.9635
0.0011	89.0	16643	0.1011	0.9699	0.9929	0.9779	0.9934	0.9787	0.9733
0.0011	90.0	16830	0.1491	0.9598	0.9911	0.9759	0.9921	0.9733	0.9658
0.0012	91.0	17017	0.1201	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0012	92.0	17204	0.0848	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0012	93.0	17391	0.0739	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0014	94.0	17578	0.0755	0.9757	0.9939	0.9784	0.9941	0.9813	0.9770
0.0014	95.0	17765	0.1235	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0014	96.0	17952	0.1216	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0017	97.0	18139	0.1223	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0017	98.0	18326	0.1069	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0035	99.0	18513	0.1174	0.9657	0.9921	0.9755	0.9927	0.976	0.9697
0.0035	100.0	18700	0.1179	0.9657	0.9921	0.9755	0.9927	0.976	0.9697

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3