greathero/mit-b0-finetuned-contrails-morethanx35newercontrailsdataset

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: 0.0016
• Validation Loss: 0.0026
• Validation Mean Iou: 0.9068
• Validation Mean Accuracy: 0.9377
• Validation Overall Accuracy: 0.9993
• Validation Accuracy Unlabeled: 1.0
• Validation Accuracy Notlabeled: 0.9997
• Validation Accuracy Otherclass: 1.0
• Validation Accuracy Contrail: 0.7513
• Validation Iou Unlabeled: 1.0
• Validation Iou Notlabeled: 0.9993
• Validation Iou Otherclass: 0.9993
• Validation Iou Contrail: 0.6286
• Epoch: 49

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Unlabeled	Validation Accuracy Notlabeled	Validation Accuracy Otherclass	Validation Accuracy Contrail	Validation Iou Unlabeled	Validation Iou Notlabeled	Validation Iou Otherclass	Validation Iou Contrail	Epoch
0.2395	0.0367	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	0
0.0286	0.0204	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	1
0.0194	0.0156	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	2
0.0157	0.0144	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	3
0.0141	0.0137	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	4
0.0133	0.0132	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	5
0.0126	0.0125	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	6
0.0118	0.0117	0.2496	0.25	0.9983	0.0	1.0	0.0	0.0	0.0	0.9983	0.0	0.0	7
0.0112	0.0110	0.2551	0.2555	0.9983	0.0	1.0000	0.0222	0.0	0.0	0.9983	0.0220	0.0	8
0.0106	0.0103	0.2744	0.2756	0.9983	0.0180	1.0000	0.0832	0.0013	0.0179	0.9983	0.0801	0.0013	9
0.0100	0.0094	0.3172	0.3225	0.9983	0.0527	1.0000	0.2344	0.0030	0.0521	0.9983	0.2154	0.0030	10
0.0091	0.0087	0.3117	0.3138	0.9983	0.1026	1.0000	0.1470	0.0055	0.1014	0.9983	0.1415	0.0055	11
0.0083	0.0076	0.3844	0.3941	0.9983	0.1540	1.0000	0.4189	0.0037	0.1516	0.9983	0.3840	0.0037	12
0.0073	0.0070	0.4402	0.4781	0.9983	0.1997	0.9999	0.6616	0.0511	0.1978	0.9983	0.5167	0.0479	13
0.0067	0.0062	0.5049	0.5454	0.9983	0.4868	1.0000	0.6893	0.0057	0.4702	0.9983	0.5456	0.0056	14
0.0060	0.0056	0.5133	0.5326	0.9983	0.4799	1.0000	0.6283	0.0221	0.4722	0.9983	0.5608	0.0218	15
0.0055	0.0056	0.5975	0.6504	0.9984	0.7018	0.9999	0.8058	0.0942	0.6731	0.9984	0.6317	0.0868	16
0.0051	0.0050	0.5800	0.6003	0.9984	0.6893	0.9999	0.6644	0.0476	0.6707	0.9984	0.6048	0.0462	17
0.0048	0.0047	0.6598	0.6878	0.9984	0.8252	0.9998	0.7809	0.1453	0.8013	0.9984	0.7095	0.1298	18
0.0045	0.0045	0.6596	0.7122	0.9984	0.9057	0.9998	0.7739	0.1693	0.8117	0.9984	0.6774	0.1508	19
0.0042	0.0042	0.6956	0.7259	0.9985	0.8669	0.9998	0.8294	0.2074	0.8609	0.9985	0.7396	0.1835	20
0.0039	0.0045	0.6824	0.6971	0.9985	0.8710	0.9999	0.7933	0.1243	0.8579	0.9985	0.7546	0.1186	21
0.0038	0.0041	0.7516	0.7748	0.9985	0.9612	0.9998	0.8779	0.2605	0.9397	0.9985	0.8395	0.2287	22
0.0035	0.0038	0.7683	0.8089	0.9986	0.9667	0.9997	0.9334	0.3359	0.9356	0.9986	0.8546	0.2843	23
0.0034	0.0037	0.7905	0.8212	0.9986	0.9639	0.9996	0.9182	0.4031	0.9508	0.9986	0.8856	0.3270	24
0.0032	0.0037	0.7938	0.8154	0.9987	0.9515	0.9997	0.9112	0.3992	0.9469	0.9987	0.8939	0.3358	25
0.0031	0.0036	0.8250	0.8524	0.9988	0.9806	0.9996	0.9431	0.4864	0.9772	0.9988	0.9315	0.3924	26
0.0030	0.0035	0.8204	0.8392	0.9987	0.9736	0.9997	0.9820	0.4015	0.9736	0.9987	0.9659	0.3435	27
0.0029	0.0033	0.8431	0.8689	0.9988	0.9917	0.9997	0.9834	0.5011	0.9910	0.9988	0.9653	0.4172	28
0.0027	0.0034	0.8337	0.8539	0.9988	0.9945	0.9997	0.9875	0.4341	0.9945	0.9988	0.9648	0.3767	29
0.0027	0.0033	0.8518	0.8834	0.9988	1.0	0.9996	0.9931	0.5411	0.9972	0.9988	0.9802	0.4311	30
0.0025	0.0031	0.8622	0.8848	0.9990	0.9986	0.9997	0.9958	0.5449	0.9986	0.9990	0.9890	0.4622	31
0.0025	0.0031	0.8667	0.8975	0.9989	0.9986	0.9996	0.9986	0.5933	0.9979	0.9989	0.9897	0.4801	32
0.0024	0.0031	0.8607	0.8791	0.9990	1.0	0.9998	0.9986	0.5181	1.0	0.9990	0.9877	0.4563	33
0.0022	0.0031	0.8783	0.9102	0.9990	1.0	0.9996	0.9917	0.6497	1.0	0.9990	0.9876	0.5266	34
0.0022	0.0029	0.8780	0.9016	0.9991	1.0	0.9997	0.9931	0.6138	1.0	0.9991	0.9903	0.5225	35
0.0022	0.0030	0.8853	0.9238	0.9991	1.0	0.9996	0.9986	0.6969	0.9972	0.9991	0.9965	0.5484	36
0.0021	0.0030	0.8859	0.9156	0.9991	1.0	0.9996	0.9986	0.6641	1.0	0.9991	0.9979	0.5466	37
0.0021	0.0029	0.8865	0.9165	0.9991	1.0	0.9997	1.0	0.6662	0.9993	0.9991	0.9952	0.5526	38
0.0021	0.0028	0.8932	0.9227	0.9992	1.0	0.9997	0.9986	0.6926	1.0	0.9992	0.9965	0.5771	39
0.0020	0.0029	0.8929	0.9235	0.9992	1.0	0.9997	0.9986	0.6959	1.0	0.9992	0.9979	0.5747	40
0.0020	0.0028	0.8935	0.9252	0.9992	1.0	0.9996	0.9986	0.7026	1.0	0.9991	0.9979	0.5767	41
0.0019	0.0028	0.8934	0.9144	0.9992	1.0	0.9998	0.9986	0.6590	1.0	0.9992	0.9986	0.5758	42
0.0019	0.0028	0.8945	0.9174	0.9992	1.0	0.9997	0.9986	0.6713	1.0	0.9992	0.9979	0.5807	43
0.0018	0.0027	0.9009	0.9327	0.9992	1.0	0.9997	0.9986	0.7324	1.0	0.9992	0.9979	0.6065	44
0.0019	0.0027	0.9028	0.9385	0.9992	1.0	0.9996	1.0	0.7543	1.0	0.9992	0.9993	0.6125	45
0.0017	0.0028	0.9048	0.9362	0.9992	1.0	0.9997	1.0	0.7453	1.0	0.9992	1.0	0.6199	46
0.0017	0.0029	0.9043	0.9362	0.9992	1.0	0.9997	0.9986	0.7466	1.0	0.9992	0.9979	0.6202	47
0.0017	0.0027	0.9060	0.9365	0.9993	1.0	0.9997	0.9986	0.7477	1.0	0.9993	0.9979	0.6270	48
0.0016	0.0026	0.9068	0.9377	0.9993	1.0	0.9997	1.0	0.7513	1.0	0.9993	0.9993	0.6286	49

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.15.0
• Tokenizers 0.15.0