car_identified_model_7

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: 0.5755
• F1: 0.3629
• Roc Auc: 0.6990
• Accuracy: 0.0714

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
0.6919	0.73	1	0.6887	0.1786	0.5738	0.0
0.6919	1.45	2	0.6856	0.1818	0.5761	0.0
0.6919	2.91	4	0.6802	0.2116	0.6066	0.0
0.6919	3.64	5	0.6800	0.1861	0.5826	0.0
0.6919	4.36	6	0.6858	0.1905	0.5973	0.0
0.6919	5.82	8	0.6938	0.1549	0.5342	0.0
0.6919	6.55	9	0.6917	0.1805	0.5802	0.0
0.6919	8.0	11	0.6735	0.1905	0.5932	0.0
0.6919	8.73	12	0.6727	0.1952	0.6007	0.0
0.6919	9.45	13	0.6698	0.2061	0.6172	0.0
0.6919	10.91	15	0.6672	0.2008	0.6092	0.0
0.6919	11.64	16	0.6645	0.2092	0.6196	0.0
0.6919	12.36	17	0.6646	0.2049	0.6144	0.0
0.6919	13.82	19	0.6623	0.2081	0.6167	0.0
0.6919	14.55	20	0.6607	0.2078	0.6149	0.0
0.6919	16.0	22	0.6585	0.2203	0.6320	0.0
0.6919	16.73	23	0.6562	0.2156	0.6219	0.0
0.6919	17.45	24	0.6555	0.2182	0.6263	0.0
0.6919	18.91	26	0.6522	0.2185	0.6232	0.0
0.6919	19.64	27	0.6512	0.2228	0.6273	0.0
0.6919	20.36	28	0.6501	0.2356	0.6410	0.0
0.6919	21.82	30	0.6477	0.2280	0.6284	0.0
0.6919	22.55	31	0.6476	0.2326	0.6343	0.0
0.6919	24.0	33	0.6469	0.2408	0.6434	0.0
0.6919	24.73	34	0.6432	0.2409	0.6369	0.0
0.6919	25.45	35	0.6432	0.2431	0.6408	0.0
0.6919	26.91	37	0.6402	0.2486	0.6449	0.0
0.6919	27.64	38	0.6386	0.2686	0.6664	0.0
0.6919	28.36	39	0.6376	0.2762	0.6796	0.0
0.6919	29.82	41	0.6347	0.2692	0.6721	0.0
0.6919	30.55	42	0.6339	0.2655	0.6643	0.0
0.6919	32.0	44	0.6310	0.2674	0.6630	0.0
0.6919	32.73	45	0.6307	0.2789	0.6731	0.0
0.6919	33.45	46	0.6291	0.2714	0.6656	0.0
0.6919	34.91	48	0.6271	0.2761	0.6659	0.0
0.6919	35.64	49	0.6271	0.2687	0.6612	0.0
0.6919	36.36	50	0.6277	0.2606	0.6509	0.0
0.6919	37.82	52	0.6257	0.2741	0.6620	0.0
0.6919	38.55	53	0.6244	0.2892	0.6793	0.0
0.6919	40.0	55	0.6203	0.2968	0.6806	0.0
0.6919	40.73	56	0.6198	0.2902	0.6770	0.0
0.6919	41.45	57	0.6184	0.3023	0.6866	0.0
0.6919	42.91	59	0.6163	0.2977	0.6812	0.0
0.6919	43.64	60	0.6147	0.3322	0.7112	0.0
0.6919	44.36	61	0.6154	0.3197	0.6954	0.0
0.6919	45.82	63	0.6129	0.3016	0.6832	0.0
0.6919	46.55	64	0.6112	0.3020	0.6804	0.0
0.6919	48.0	66	0.6095	0.2961	0.6773	0.0
0.6919	48.73	67	0.6091	0.3133	0.6923	0.0
0.6919	49.45	68	0.6090	0.3265	0.7019	0.0
0.6919	50.91	70	0.6077	0.3093	0.6840	0.0
0.6919	51.64	71	0.6065	0.3239	0.6941	0.0
0.6919	52.36	72	0.6058	0.3237	0.6907	0.0
0.6919	53.82	74	0.6028	0.3285	0.6928	0.0
0.6919	54.55	75	0.6038	0.3285	0.6928	0.0238
0.6919	56.0	77	0.6056	0.3197	0.6825	0.0
0.6919	56.73	78	0.6074	0.3249	0.6913	0.0
0.6919	57.45	79	0.6030	0.3158	0.6775	0.0238
0.6919	58.91	81	0.6001	0.3359	0.6925	0.0238
0.6919	59.64	82	0.5993	0.3409	0.6980	0.0238
0.6919	60.36	83	0.6017	0.3259	0.6884	0.0238
0.6919	61.82	85	0.6009	0.3146	0.6770	0.0238
0.6919	62.55	86	0.6018	0.3197	0.6825	0.0238
0.6919	64.0	88	0.5975	0.3130	0.6731	0.0238
0.6919	64.73	89	0.5978	0.3271	0.6889	0.0238
0.6919	65.45	90	0.5967	0.3424	0.6951	0.0238
0.6919	66.91	92	0.5973	0.3125	0.6698	0.0238
0.6919	67.64	93	0.5956	0.3372	0.6931	0.0238
0.6919	68.36	94	0.5922	0.3373	0.6897	0.0238
0.6919	69.82	96	0.5949	0.3320	0.6843	0.0476
0.6919	70.55	97	0.5959	0.3413	0.6913	0.0476
0.6919	72.0	99	0.5944	0.3420	0.7019	0.0238
0.6919	72.73	100	0.5955	0.3333	0.6881	0.0476
0.6919	73.45	101	0.5933	0.3346	0.6887	0.0238
0.6919	74.91	103	0.5894	0.3543	0.7032	0.0238
0.6919	75.64	104	0.5903	0.3424	0.6951	0.0238
0.6919	76.36	105	0.5890	0.3411	0.6946	0.0476
0.6919	77.82	107	0.5922	0.3346	0.6887	0.0476
0.6919	78.55	108	0.5923	0.3243	0.6812	0.0476
0.6919	80.0	110	0.5908	0.3468	0.6933	0.0476
0.6919	80.73	111	0.5922	0.328	0.6793	0.0476
0.6919	81.45	112	0.5892	0.3440	0.6923	0.0238
0.6919	82.91	114	0.5880	0.3506	0.6982	0.0238
0.6919	83.64	115	0.5869	0.3454	0.6928	0.0476
0.6919	84.36	116	0.5841	0.3465	0.6967	0.0238
0.6919	85.82	118	0.5841	0.3568	0.6969	0.0714
0.6919	86.55	119	0.5843	0.3496	0.6944	0.0476
0.6919	88.0	121	0.5860	0.3598	0.6980	0.0476
0.6919	88.73	122	0.5837	0.3457	0.6894	0.0476
0.6919	89.45	123	0.5826	0.3636	0.7029	0.0714
0.6919	90.91	125	0.5822	0.3651	0.7034	0.0714
0.6919	91.64	126	0.5814	0.3607	0.7019	0.0714
0.6919	92.36	127	0.5814	0.3629	0.7063	0.0476
0.6919	93.82	129	0.5818	0.3713	0.7055	0.0714
0.6919	94.55	130	0.5802	0.3766	0.7109	0.0714
0.6919	96.0	132	0.5803	0.3675	0.7006	0.0714
0.6919	96.73	133	0.5825	0.3519	0.6881	0.0714
0.6919	97.45	134	0.5790	0.3629	0.6990	0.0714
0.6919	98.91	136	0.5795	0.3766	0.7109	0.0714
0.6919	99.64	137	0.5784	0.3697	0.7050	0.0714
0.6919	100.36	138	0.5819	0.3583	0.6975	0.0714
0.6919	101.82	140	0.5834	0.3525	0.6954	0.0476
0.6919	102.55	141	0.5825	0.3689	0.7083	0.0238
0.6919	104.0	143	0.5839	0.3460	0.6861	0.0714
0.6919	104.73	144	0.5838	0.3333	0.6814	0.0476
0.6919	105.45	145	0.5801	0.3387	0.6869	0.0238
0.6919	106.91	147	0.5811	0.3515	0.6915	0.0476
0.6919	107.64	148	0.5793	0.3374	0.6830	0.0476
0.6919	108.36	149	0.5766	0.3448	0.6822	0.0714
0.6919	109.82	151	0.5760	0.3445	0.6856	0.0714
0.6919	110.55	152	0.5757	0.3559	0.6931	0.0714
0.6919	112.0	154	0.5760	0.3475	0.6866	0.0714
0.6919	112.73	155	0.5743	0.3629	0.6990	0.0714
0.6919	113.45	156	0.5732	0.3636	0.7029	0.0714
0.6919	114.91	158	0.5736	0.3786	0.7153	0.0476
0.6919	115.64	159	0.5764	0.3667	0.7039	0.0238
0.6919	116.36	160	0.5765	0.3613	0.6985	0.0476
0.6919	117.82	162	0.5749	0.3574	0.6936	0.0714
0.6919	118.55	163	0.5754	0.3592	0.7013	0.0476
0.6919	120.0	165	0.5757	0.3665	0.7112	0.0476
0.6919	120.73	166	0.5771	0.3729	0.7060	0.0714
0.6919	121.45	167	0.5746	0.3629	0.6990	0.0714
0.6919	122.91	169	0.5758	0.3644	0.6995	0.0714
0.6919	123.64	170	0.5745	0.3559	0.6931	0.0714
0.6919	124.36	171	0.5758	0.3544	0.6925	0.0714
0.6919	125.82	173	0.5759	0.3598	0.6980	0.0714
0.6919	126.55	174	0.5772	0.3568	0.6969	0.0714
0.6919	128.0	176	0.5747	0.3583	0.6975	0.0714
0.6919	128.73	177	0.5738	0.3644	0.6995	0.0714
0.6919	129.45	178	0.5751	0.3644	0.6995	0.0714
0.6919	130.91	180	0.5741	0.3713	0.7055	0.0952
0.6919	131.64	181	0.5748	0.3713	0.7055	0.0952
0.6919	132.36	182	0.5767	0.3660	0.7001	0.0714
0.6919	133.82	184	0.5732	0.3660	0.7001	0.0952
0.6919	134.55	185	0.5742	0.3772	0.7037	0.0952
0.6919	136.0	187	0.5690	0.3755	0.7032	0.0952
0.6919	136.73	188	0.5699	0.3805	0.7047	0.0714
0.6919	137.45	189	0.5743	0.3707	0.7016	0.0714
0.6919	138.91	191	0.5740	0.3529	0.6920	0.0952
0.6919	139.64	192	0.5740	0.3660	0.7001	0.0714
0.6919	140.36	193	0.5734	0.3644	0.6995	0.0714
0.6919	141.82	195	0.5740	0.3675	0.7006	0.0714
0.6919	142.55	196	0.5721	0.3707	0.7016	0.0714
0.6919	144.0	198	0.5725	0.3767	0.6998	0.0714
0.6919	144.73	199	0.5734	0.3729	0.7060	0.0952
0.6919	145.45	200	0.5755	0.3629	0.6990	0.0714

Framework versions

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