AhamadShaik/SegFormer_RESIZE_NLM

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

• Train Loss: 0.0424
• Train Dice Coef: 0.8817
• Train Iou: 0.7903
• Validation Loss: 0.0436
• Validation Dice Coef: 0.8897
• Validation Iou: 0.8024
• Train Lr: 1e-10
• Epoch: 99

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:

• optimizer: {'name': 'Adam', 'learning_rate': 1e-10, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Dice Coef	Train Iou	Validation Loss	Validation Dice Coef	Validation Iou	Train Lr	Epoch
0.2282	0.5657	0.4102	0.1322	0.6524	0.4967	1e-04	0
0.1354	0.6853	0.5329	0.0855	0.7853	0.6544	1e-04	1
0.1105	0.7364	0.5924	0.0737	0.8147	0.6916	1e-04	2
0.0985	0.7610	0.6226	0.0632	0.8518	0.7440	1e-04	3
0.0933	0.7745	0.6399	0.0627	0.8455	0.7351	1e-04	4
0.0886	0.7856	0.6535	0.0584	0.8603	0.7566	1e-04	5
0.0831	0.7971	0.6695	0.0559	0.8621	0.7596	1e-04	6
0.0770	0.8107	0.6867	0.0530	0.8726	0.7756	1e-04	7
0.0741	0.8160	0.6942	0.0512	0.8775	0.7832	1e-04	8
0.0750	0.8163	0.6945	0.0581	0.8627	0.7606	1e-04	9
0.0678	0.8306	0.7138	0.0531	0.8719	0.7745	1e-04	10
0.0659	0.8341	0.7196	0.0519	0.8738	0.7781	1e-04	11
0.0626	0.8412	0.7294	0.0496	0.8789	0.7853	1e-04	12
0.0637	0.8383	0.7257	0.0515	0.8772	0.7828	1e-04	13
0.0601	0.8462	0.7367	0.0498	0.8765	0.7814	1e-04	14
0.0573	0.8525	0.7458	0.0474	0.8817	0.7897	1e-04	15
0.0565	0.8520	0.7456	0.0459	0.8850	0.7948	1e-04	16
0.0633	0.8381	0.7262	0.0487	0.8797	0.7868	1e-04	17
0.0558	0.8544	0.7489	0.0476	0.8828	0.7917	1e-04	18
0.0523	0.8617	0.7595	0.0454	0.8872	0.7983	1e-04	19
0.0516	0.8632	0.7617	0.0465	0.8838	0.7934	1e-04	20
0.0515	0.8636	0.7625	0.0494	0.8816	0.7894	1e-04	21
0.0518	0.8630	0.7615	0.0487	0.8836	0.7930	1e-04	22
0.0521	0.8616	0.7595	0.0483	0.8822	0.7908	1e-04	23
0.0510	0.8634	0.7624	0.0501	0.8814	0.7899	1e-04	24
0.0485	0.8703	0.7728	0.0439	0.8892	0.8018	5e-06	25
0.0464	0.8755	0.7807	0.0433	0.8890	0.8015	5e-06	26
0.0456	0.8760	0.7817	0.0439	0.8884	0.8004	5e-06	27
0.0446	0.8790	0.7860	0.0428	0.8896	0.8024	5e-06	28
0.0443	0.8786	0.7855	0.0426	0.8905	0.8038	5e-06	29
0.0439	0.8795	0.7867	0.0439	0.8881	0.7999	5e-06	30
0.0436	0.8800	0.7876	0.0429	0.8902	0.8032	5e-06	31
0.0430	0.8809	0.7890	0.0439	0.8876	0.7992	5e-06	32
0.0427	0.8812	0.7894	0.0432	0.8892	0.8016	5e-06	33
0.0431	0.8798	0.7875	0.0433	0.8895	0.8022	5e-06	34
0.0425	0.8816	0.7903	0.0435	0.8892	0.8016	2.5e-07	35
0.0420	0.8826	0.7917	0.0433	0.8894	0.8021	2.5e-07	36
0.0423	0.8833	0.7926	0.0429	0.8893	0.8018	2.5e-07	37
0.0420	0.8833	0.7929	0.0430	0.8895	0.8023	2.5e-07	38
0.0424	0.8832	0.7924	0.0437	0.8890	0.8013	2.5e-07	39
0.0422	0.8824	0.7914	0.0427	0.8897	0.8024	1.25e-08	40
0.0426	0.8824	0.7913	0.0431	0.8900	0.8030	1.25e-08	41
0.0424	0.8832	0.7926	0.0433	0.8893	0.8019	1.25e-08	42
0.0424	0.8830	0.7922	0.0436	0.8886	0.8008	1.25e-08	43
0.0427	0.8806	0.7888	0.0434	0.8893	0.8020	1.25e-08	44
0.0421	0.8829	0.7921	0.0431	0.8899	0.8028	6.25e-10	45
0.0427	0.8817	0.7901	0.0431	0.8896	0.8023	6.25e-10	46
0.0422	0.8825	0.7916	0.0433	0.8895	0.8022	6.25e-10	47
0.0423	0.8823	0.7912	0.0431	0.8897	0.8024	6.25e-10	48
0.0423	0.8826	0.7916	0.0433	0.8895	0.8021	6.25e-10	49
0.0425	0.8827	0.7918	0.0433	0.8896	0.8023	1e-10	50
0.0421	0.8838	0.7937	0.0431	0.8891	0.8014	1e-10	51
0.0424	0.8820	0.7907	0.0436	0.8884	0.8003	1e-10	52
0.0424	0.8824	0.7915	0.0426	0.8899	0.8029	1e-10	53
0.0423	0.8828	0.7920	0.0433	0.8894	0.8020	1e-10	54
0.0424	0.8818	0.7905	0.0431	0.8901	0.8031	1e-10	55
0.0421	0.8823	0.7911	0.0438	0.8887	0.8008	1e-10	56
0.0421	0.8821	0.7909	0.0426	0.8896	0.8023	1e-10	57
0.0420	0.8818	0.7906	0.0428	0.8903	0.8035	1e-10	58
0.0416	0.8845	0.7945	0.0434	0.8889	0.8012	1e-10	59
0.0421	0.8830	0.7921	0.0429	0.8900	0.8029	1e-10	60
0.0420	0.8834	0.7927	0.0433	0.8888	0.8010	1e-10	61
0.0425	0.8820	0.7909	0.0429	0.8896	0.8023	1e-10	62
0.0421	0.8827	0.7919	0.0431	0.8906	0.8039	1e-10	63
0.0422	0.8815	0.7901	0.0429	0.8901	0.8031	1e-10	64
0.0420	0.8833	0.7927	0.0430	0.8899	0.8029	1e-10	65
0.0426	0.8822	0.7911	0.0431	0.8891	0.8015	1e-10	66
0.0422	0.8829	0.7923	0.0428	0.8902	0.8033	1e-10	67
0.0424	0.8813	0.7898	0.0435	0.8893	0.8019	1e-10	68
0.0420	0.8826	0.7918	0.0430	0.8896	0.8024	1e-10	69
0.0428	0.8811	0.7895	0.0434	0.8900	0.8030	1e-10	70
0.0422	0.8832	0.7926	0.0431	0.8895	0.8021	1e-10	71
0.0427	0.8816	0.7902	0.0432	0.8898	0.8026	1e-10	72
0.0426	0.8817	0.7904	0.0434	0.8891	0.8015	1e-10	73
0.0424	0.8811	0.7897	0.0434	0.8899	0.8028	1e-10	74
0.0432	0.8807	0.7890	0.0430	0.8897	0.8025	1e-10	75
0.0423	0.8816	0.7904	0.0435	0.8894	0.8019	1e-10	76
0.0418	0.8838	0.7935	0.0431	0.8897	0.8025	1e-10	77
0.0425	0.8817	0.7901	0.0428	0.8898	0.8026	1e-10	78
0.0424	0.8818	0.7904	0.0434	0.8891	0.8015	1e-10	79
0.0419	0.8828	0.7920	0.0431	0.8901	0.8031	1e-10	80
0.0429	0.8812	0.7897	0.0425	0.8903	0.8034	1e-10	81
0.0419	0.8829	0.7922	0.0427	0.8905	0.8038	1e-10	82
0.0426	0.8820	0.7908	0.0431	0.8894	0.8019	1e-10	83
0.0424	0.8830	0.7921	0.0433	0.8893	0.8018	1e-10	84
0.0420	0.8832	0.7927	0.0432	0.8894	0.8019	1e-10	85
0.0421	0.8828	0.7921	0.0426	0.8907	0.8042	1e-10	86
0.0424	0.8817	0.7903	0.0430	0.8905	0.8038	1e-10	87
0.0423	0.8819	0.7908	0.0431	0.8901	0.8032	1e-10	88
0.0428	0.8809	0.7891	0.0429	0.8897	0.8025	1e-10	89
0.0424	0.8818	0.7903	0.0434	0.8897	0.8025	1e-10	90
0.0422	0.8827	0.7918	0.0428	0.8902	0.8033	1e-10	91
0.0426	0.8813	0.7897	0.0433	0.8891	0.8016	1e-10	92
0.0418	0.8839	0.7936	0.0427	0.8898	0.8026	1e-10	93
0.0418	0.8831	0.7924	0.0431	0.8900	0.8031	1e-10	94
0.0425	0.8822	0.7912	0.0429	0.8904	0.8037	1e-10	95
0.0424	0.8812	0.7895	0.0429	0.8896	0.8023	1e-10	96
0.0423	0.8818	0.7908	0.0428	0.8900	0.8028	1e-10	97
0.0417	0.8838	0.7934	0.0427	0.8906	0.8040	1e-10	98
0.0424	0.8817	0.7903	0.0436	0.8897	0.8024	1e-10	99

Framework versions

• Transformers 4.27.4
• TensorFlow 2.10.1
• Datasets 2.11.0
• Tokenizers 0.13.3