car_identified_model_9

This model is a fine-tuned version of apple/mobilevitv2-1.0-imagenet1k-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3580
• F1: 0.8333
• Roc Auc: 0.8333
• Accuracy: 0.6667

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2586	1.0	1	0.6925	0.3889	0.5417	0.0
0.2586	2.0	2	0.6926	0.3889	0.5417	0.0
0.2586	3.0	4	0.6924	0.3889	0.5417	0.0
0.2586	4.0	5	0.6922	0.3889	0.5417	0.0
0.2586	5.0	6	0.6917	0.5	0.5	0.0
0.2586	6.0	8	0.6904	0.6667	0.5833	0.0
0.2586	7.0	9	0.6890	0.6667	0.5833	0.0
0.2586	8.0	10	0.6871	0.6667	0.5833	0.0
0.2586	9.0	11	0.6845	0.6667	0.5833	0.0
0.2586	10.0	12	0.6813	0.6667	0.5833	0.0
0.2586	11.0	14	0.6764	0.6667	0.5833	0.0
0.2586	12.0	15	0.6724	0.6667	0.5833	0.0
0.2586	13.0	16	0.6689	0.6667	0.5833	0.0
0.2586	14.0	18	0.6653	0.6667	0.5833	0.0
0.2586	15.0	19	0.6634	0.6667	0.5833	0.0
0.2586	16.0	20	0.6618	0.625	0.625	0.3333
0.2586	17.0	21	0.6601	0.625	0.625	0.3333
0.2586	18.0	22	0.6586	0.625	0.625	0.3333
0.2586	19.0	24	0.6844	0.3889	0.5417	0.0
0.2586	20.0	25	0.8059	0.4583	0.4583	0.25
0.2586	21.0	26	0.9269	0.4583	0.4583	0.25
0.2586	22.0	28	1.0221	0.4583	0.4583	0.25
0.2586	23.0	29	1.0359	0.4583	0.4583	0.25
0.2586	24.0	30	1.0373	0.4583	0.4583	0.25
0.2586	25.0	31	1.0350	0.4583	0.4583	0.25
0.2586	26.0	32	0.9747	0.4583	0.4583	0.25
0.2586	27.0	34	0.8764	0.5417	0.5417	0.3333
0.2586	28.0	35	0.7686	0.5417	0.5417	0.3333
0.2586	29.0	36	0.6511	0.6667	0.6667	0.4167
0.2586	30.0	38	0.5987	0.75	0.75	0.5
0.2586	31.0	39	0.5267	0.75	0.75	0.5
0.2586	32.0	40	0.4412	0.7917	0.7917	0.5833
0.2586	33.0	41	0.3719	0.875	0.875	0.75
0.2586	34.0	42	0.3447	0.875	0.875	0.75
0.2586	35.0	44	0.3333	0.875	0.875	0.75
0.2586	36.0	45	0.3295	0.875	0.875	0.75
0.2586	37.0	46	0.3310	0.8980	0.8958	0.75
0.2586	38.0	48	0.3435	0.8980	0.8958	0.75
0.2586	39.0	49	0.3457	0.8980	0.8958	0.75
0.2586	40.0	50	0.3664	0.9167	0.9167	0.8333
0.2586	41.0	51	0.3809	0.8571	0.8542	0.6667
0.2586	42.0	52	0.4175	0.8400	0.8333	0.5833
0.2586	43.0	54	0.4183	0.8163	0.8125	0.5833
0.2586	44.0	55	0.4444	0.7755	0.7708	0.5833
0.2586	45.0	56	0.4301	0.8333	0.8333	0.75
0.2586	46.0	58	0.4282	0.8333	0.8333	0.75
0.2586	47.0	59	0.4202	0.8333	0.8333	0.75
0.2586	48.0	60	0.3871	0.875	0.875	0.8333
0.2586	49.0	61	0.3560	0.875	0.875	0.8333
0.2586	50.0	62	0.3330	0.8571	0.8542	0.75
0.2586	51.0	64	0.3034	0.8980	0.8958	0.75
0.2586	52.0	65	0.3170	0.8980	0.8958	0.75
0.2586	53.0	66	0.3288	0.8980	0.8958	0.75
0.2586	54.0	68	0.3157	0.9388	0.9375	0.8333
0.2586	55.0	69	0.3490	0.8571	0.8542	0.6667
0.2586	56.0	70	0.3491	0.8571	0.8542	0.6667
0.2586	57.0	71	0.3429	0.8980	0.8958	0.75
0.2586	58.0	72	0.3620	0.8571	0.8542	0.6667
0.2586	59.0	74	0.4072	0.8571	0.8542	0.6667
0.2586	60.0	75	0.4153	0.8333	0.8333	0.5833
0.2586	61.0	76	0.4254	0.8333	0.8333	0.5833
0.2586	62.0	78	0.4320	0.8163	0.8125	0.5833
0.2586	63.0	79	0.4318	0.8163	0.8125	0.5833
0.2586	64.0	80	0.4116	0.8163	0.8125	0.5833
0.2586	65.0	81	0.3835	0.8571	0.8542	0.6667
0.2586	66.0	82	0.3554	0.8571	0.8542	0.6667
0.2586	67.0	84	0.3407	0.875	0.875	0.75
0.2586	68.0	85	0.3252	0.875	0.875	0.75
0.2586	69.0	86	0.3069	0.875	0.875	0.75
0.2586	70.0	88	0.2970	0.875	0.875	0.75
0.2586	71.0	89	0.2934	0.8571	0.8542	0.6667
0.2586	72.0	90	0.2999	0.8571	0.8542	0.6667
0.2586	73.0	91	0.3068	0.8571	0.8542	0.6667
0.2586	74.0	92	0.3181	0.8571	0.8542	0.6667
0.2586	75.0	94	0.3391	0.8571	0.8542	0.6667
0.2586	76.0	95	0.3482	0.8571	0.8542	0.6667
0.2586	77.0	96	0.3577	0.8571	0.8542	0.6667
0.2586	78.0	98	0.4279	0.8163	0.8125	0.5833
0.2586	79.0	99	0.4492	0.7347	0.7292	0.5
0.2586	80.0	100	0.4291	0.7755	0.7708	0.5833
0.2586	81.0	101	0.4267	0.7755	0.7708	0.5833
0.2586	82.0	102	0.4160	0.7755	0.7708	0.5833
0.2586	83.0	104	0.4000	0.8333	0.8333	0.5833
0.2586	84.0	105	0.3792	0.8571	0.8542	0.6667
0.2586	85.0	106	0.3368	0.8571	0.8542	0.6667
0.2586	86.0	108	0.3480	0.8571	0.8542	0.6667
0.2586	87.0	109	0.3798	0.8333	0.8333	0.5833
0.2586	88.0	110	0.3806	0.8163	0.8125	0.5833
0.2586	89.0	111	0.3533	0.8571	0.8542	0.6667
0.2586	90.0	112	0.3428	0.8571	0.8542	0.6667
0.2586	91.0	114	0.3447	0.875	0.875	0.6667
0.2586	92.0	115	0.3440	0.8571	0.8542	0.6667
0.2586	93.0	116	0.3433	0.8571	0.8542	0.6667
0.2586	94.0	118	0.3584	0.8571	0.8542	0.6667
0.2586	95.0	119	0.3502	0.8571	0.8542	0.6667
0.2586	96.0	120	0.3413	0.8571	0.8542	0.6667
0.2586	97.0	121	0.3247	0.8571	0.8542	0.6667
0.2586	98.0	122	0.3232	0.8571	0.8542	0.6667
0.2586	99.0	124	0.3178	0.8571	0.8542	0.6667
0.2586	100.0	125	0.3201	0.8571	0.8542	0.6667
0.2586	101.0	126	0.3100	0.8333	0.8333	0.6667
0.2586	102.0	128	0.3137	0.8511	0.8542	0.6667
0.2586	103.0	129	0.3140	0.8511	0.8542	0.6667
0.2586	104.0	130	0.3332	0.8333	0.8333	0.5833
0.2586	105.0	131	0.3598	0.7917	0.7917	0.5833
0.2586	106.0	132	0.3742	0.8511	0.8542	0.5833
0.2586	107.0	134	0.3924	0.8571	0.8542	0.6667
0.2586	108.0	135	0.4015	0.8333	0.8333	0.6667
0.2586	109.0	136	0.4096	0.8333	0.8333	0.6667
0.2586	110.0	138	0.4227	0.7917	0.7917	0.5833
0.2586	111.0	139	0.4343	0.7917	0.7917	0.5833
0.2586	112.0	140	0.4349	0.7917	0.7917	0.5833
0.2586	113.0	141	0.4187	0.7917	0.7917	0.5833
0.2586	114.0	142	0.4037	0.7917	0.7917	0.5833
0.2586	115.0	144	0.3776	0.8571	0.8542	0.6667
0.2586	116.0	145	0.3763	0.8571	0.8542	0.6667
0.2586	117.0	146	0.3666	0.8571	0.8542	0.6667
0.2586	118.0	148	0.3539	0.8571	0.8542	0.6667
0.2586	119.0	149	0.3497	0.8571	0.8542	0.6667
0.2586	120.0	150	0.3375	0.8571	0.8542	0.6667
0.2586	121.0	151	0.3265	0.8571	0.8542	0.6667
0.2586	122.0	152	0.3154	0.8571	0.8542	0.6667
0.2586	123.0	154	0.3044	0.8571	0.8542	0.6667
0.2586	124.0	155	0.3225	0.8333	0.8333	0.6667
0.2586	125.0	156	0.3338	0.8333	0.8333	0.6667
0.2586	126.0	158	0.3363	0.8571	0.8542	0.6667
0.2586	127.0	159	0.3446	0.8571	0.8542	0.6667
0.2586	128.0	160	0.3458	0.8333	0.8333	0.6667
0.2586	129.0	161	0.3591	0.8571	0.8542	0.6667
0.2586	130.0	162	0.3573	0.8333	0.8333	0.6667
0.2586	131.0	164	0.3623	0.8571	0.8542	0.6667
0.2586	132.0	165	0.3636	0.8571	0.8542	0.6667
0.2586	133.0	166	0.3622	0.8571	0.8542	0.6667
0.2586	134.0	168	0.3569	0.8571	0.8542	0.6667
0.2586	135.0	169	0.3532	0.8571	0.8542	0.6667
0.2586	136.0	170	0.3576	0.8571	0.8542	0.6667
0.2586	137.0	171	0.3548	0.8571	0.8542	0.6667
0.2586	138.0	172	0.3503	0.8571	0.8542	0.6667
0.2586	139.0	174	0.3547	0.8571	0.8542	0.6667
0.2586	140.0	175	0.3484	0.8571	0.8542	0.6667
0.2586	141.0	176	0.3491	0.8571	0.8542	0.6667
0.2586	142.0	178	0.3511	0.8571	0.8542	0.6667
0.2586	143.0	179	0.3620	0.8571	0.8542	0.6667
0.2586	144.0	180	0.3616	0.8333	0.8333	0.6667
0.2586	145.0	181	0.3654	0.8333	0.8333	0.6667
0.2586	146.0	182	0.3541	0.8571	0.8542	0.6667
0.2586	147.0	184	0.3533	0.8333	0.8333	0.6667
0.2586	148.0	185	0.3675	0.8333	0.8333	0.6667
0.2586	149.0	186	0.3616	0.8333	0.8333	0.6667
0.2586	150.0	188	0.3747	0.8333	0.8333	0.6667
0.2586	151.0	189	0.3888	0.7917	0.7917	0.5833
0.2586	152.0	190	0.3884	0.8085	0.8125	0.5833
0.2586	153.0	191	0.3759	0.8333	0.8333	0.6667
0.2586	154.0	192	0.3743	0.8333	0.8333	0.6667
0.2586	155.0	194	0.3895	0.7917	0.7917	0.5833
0.2586	156.0	195	0.3965	0.7917	0.7917	0.5833
0.2586	157.0	196	0.3917	0.7917	0.7917	0.5833
0.2586	158.0	198	0.3845	0.7917	0.7917	0.5833
0.2586	159.0	199	0.3597	0.8333	0.8333	0.6667
0.2586	160.0	200	0.3580	0.8333	0.8333	0.6667

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1