vit-base_tobacco_wr_0.01_wd_0.2

This model is a fine-tuned version of jordyvl/vit-base_tobacco on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9831
Accuracy: 0.755
Brier Loss: 0.3936
Nll: 1.4572
F1 Micro: 0.755
F1 Macro: 0.7245
Ece: 0.2101
Aurc: 0.1059

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.01
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Brier Loss	Nll	F1 Micro	F1 Macro	Ece	Aurc
No log	0.96	12	0.7384	0.815	0.3056	1.1863	0.815	0.8021	0.2211	0.0789
No log	2.0	25	0.7504	0.795	0.3109	1.2594	0.795	0.7691	0.2235	0.0789
No log	2.96	37	0.7415	0.765	0.3109	1.0445	0.765	0.7422	0.2323	0.0762
No log	4.0	50	0.7222	0.805	0.2989	1.3200	0.805	0.7951	0.2028	0.0682
No log	4.96	62	0.7160	0.815	0.2989	1.2307	0.815	0.8067	0.2381	0.0688
No log	6.0	75	0.7149	0.825	0.2950	1.3097	0.825	0.8127	0.2110	0.0809
No log	6.96	87	0.7157	0.815	0.2986	1.2310	0.815	0.8007	0.2195	0.0779
No log	8.0	100	0.7245	0.81	0.3020	1.3030	0.81	0.7949	0.1997	0.0834
No log	8.96	112	0.7111	0.815	0.2972	1.2310	0.815	0.8009	0.2090	0.0793
No log	10.0	125	0.7344	0.81	0.3087	1.2974	0.81	0.7956	0.2240	0.0913
No log	10.96	137	0.7264	0.81	0.3057	1.3216	0.81	0.7907	0.2074	0.0879
No log	12.0	150	0.7301	0.805	0.3056	1.2448	0.805	0.7919	0.2112	0.0932
No log	12.96	162	0.7224	0.805	0.3020	1.2950	0.805	0.7899	0.1930	0.0915
No log	14.0	175	0.7235	0.81	0.3045	1.2965	0.81	0.7956	0.2025	0.0902
No log	14.96	187	0.7239	0.81	0.3039	1.2970	0.81	0.7956	0.2156	0.0906
No log	16.0	200	0.7293	0.81	0.3060	1.4336	0.81	0.7924	0.2029	0.0955
No log	16.96	212	0.7253	0.805	0.3044	1.2984	0.805	0.7853	0.1946	0.0911
No log	18.0	225	0.7293	0.805	0.3076	1.1852	0.805	0.7861	0.2015	0.0916
No log	18.96	237	0.7328	0.8	0.3050	1.3844	0.8000	0.7836	0.1900	0.0986
No log	20.0	250	0.7263	0.8	0.3058	1.2943	0.8000	0.7754	0.2003	0.0900
No log	20.96	262	0.7370	0.805	0.3102	1.3612	0.805	0.7818	0.1998	0.0939
No log	22.0	275	0.7412	0.795	0.3118	1.3673	0.795	0.7714	0.1952	0.0957
No log	22.96	287	0.7326	0.795	0.3077	1.3572	0.795	0.7666	0.1935	0.0925
No log	24.0	300	0.7308	0.805	0.3076	1.4265	0.805	0.7818	0.1968	0.0906
No log	24.96	312	0.7424	0.8	0.3122	1.3666	0.8000	0.7774	0.1853	0.0960
No log	26.0	325	0.7383	0.8	0.3097	1.3644	0.8000	0.7774	0.1911	0.0952
No log	26.96	337	0.7468	0.805	0.3143	1.4295	0.805	0.7829	0.1952	0.0971
No log	28.0	350	0.7484	0.795	0.3135	1.4327	0.795	0.7668	0.1906	0.0989
No log	28.96	362	0.7459	0.8	0.3135	1.3624	0.8000	0.7704	0.1945	0.0944
No log	30.0	375	0.7513	0.8	0.3160	1.4282	0.8000	0.7698	0.1991	0.0953
No log	30.96	387	0.7535	0.795	0.3168	1.4336	0.795	0.7656	0.1799	0.0980
No log	32.0	400	0.7540	0.8	0.3171	1.4469	0.8000	0.7774	0.1943	0.0959
No log	32.96	412	0.7566	0.8	0.3180	1.3772	0.8000	0.7704	0.1809	0.0972
No log	34.0	425	0.7641	0.795	0.3220	1.3878	0.795	0.7691	0.1937	0.1021
No log	34.96	437	0.7602	0.795	0.3192	1.3748	0.795	0.7656	0.1908	0.0973
No log	36.0	450	0.7577	0.8	0.3186	1.4397	0.8000	0.7704	0.1858	0.0951
No log	36.96	462	0.7724	0.795	0.3233	1.3800	0.795	0.7656	0.1796	0.1002
No log	38.0	475	0.7675	0.795	0.3223	1.3659	0.795	0.7654	0.1862	0.0976
No log	38.96	487	0.7772	0.79	0.3261	1.4406	0.79	0.7633	0.1877	0.1062
0.0949	40.0	500	0.7631	0.795	0.3211	1.4302	0.795	0.7654	0.1896	0.0953
0.0949	40.96	512	0.7878	0.79	0.3304	1.5689	0.79	0.7631	0.1770	0.1014
0.0949	42.0	525	0.7639	0.815	0.3198	1.5524	0.815	0.7879	0.1890	0.0938
0.0949	42.96	537	0.7967	0.785	0.3350	1.4516	0.785	0.7606	0.1809	0.1040
0.0949	44.0	550	0.7735	0.81	0.3237	1.4915	0.81	0.7784	0.2079	0.0963
0.0949	44.96	562	0.7859	0.79	0.3300	1.5076	0.79	0.7594	0.1851	0.0991
0.0949	46.0	575	0.7917	0.79	0.3323	1.5062	0.79	0.7631	0.1944	0.1015
0.0949	46.96	587	0.7879	0.795	0.3310	1.4304	0.795	0.7656	0.1761	0.0987
0.0949	48.0	600	0.7917	0.79	0.3320	1.4382	0.79	0.7629	0.1828	0.0994
0.0949	48.96	612	0.7950	0.79	0.3333	1.4929	0.79	0.7549	0.1811	0.0995
0.0949	50.0	625	0.8005	0.79	0.3363	1.4351	0.79	0.7631	0.1953	0.1009
0.0949	50.96	637	0.8019	0.79	0.3363	1.4891	0.79	0.7631	0.1837	0.0998
0.0949	52.0	650	0.8021	0.79	0.3354	1.4899	0.79	0.7586	0.1990	0.0994
0.0949	52.96	662	0.8012	0.795	0.3346	1.4913	0.795	0.7648	0.1878	0.0984
0.0949	54.0	675	0.8078	0.785	0.3388	1.4920	0.785	0.7559	0.1938	0.1000
0.0949	54.96	687	0.8092	0.785	0.3391	1.5003	0.785	0.7561	0.1878	0.1004
0.0949	56.0	700	0.8095	0.795	0.3378	1.4914	0.795	0.7634	0.1879	0.0994
0.0949	56.96	712	0.8124	0.785	0.3396	1.4926	0.785	0.7555	0.1996	0.1005
0.0949	58.0	725	0.8120	0.78	0.3391	1.4405	0.78	0.7469	0.1924	0.1005
0.0949	58.96	737	0.8185	0.785	0.3406	1.5007	0.785	0.7523	0.1910	0.1013
0.0949	60.0	750	0.8182	0.785	0.3421	1.4371	0.785	0.7555	0.1727	0.1010
0.0949	60.96	762	0.8224	0.78	0.3443	1.4404	0.78	0.7475	0.1941	0.1019
0.0949	62.0	775	0.8267	0.78	0.3463	1.4995	0.78	0.7535	0.1927	0.1016
0.0949	62.96	787	0.8252	0.775	0.3447	1.4965	0.775	0.7465	0.1798	0.1016
0.0949	64.0	800	0.8286	0.78	0.3446	1.4987	0.78	0.7475	0.1911	0.1014
0.0949	64.96	812	0.8308	0.78	0.3467	1.4438	0.78	0.7469	0.1866	0.1019
0.0949	66.0	825	0.8346	0.775	0.3476	1.4592	0.775	0.7444	0.1878	0.1034
0.0949	66.96	837	0.8348	0.78	0.3484	1.4423	0.78	0.7515	0.1821	0.1021
0.0949	68.0	850	0.8376	0.78	0.3481	1.4970	0.78	0.7469	0.1922	0.1015
0.0949	68.96	862	0.8379	0.78	0.3497	1.4388	0.78	0.7515	0.1850	0.1018
0.0949	70.0	875	0.8452	0.78	0.3512	1.4974	0.78	0.7525	0.1828	0.1036
0.0949	70.96	887	0.8437	0.78	0.3511	1.4519	0.78	0.7469	0.2076	0.1032
0.0949	72.0	900	0.8485	0.775	0.3535	1.5163	0.775	0.7444	0.1863	0.1033
0.0949	72.96	912	0.8516	0.77	0.3555	1.5015	0.7700	0.7404	0.1868	0.1030
0.0949	74.0	925	0.8507	0.77	0.3541	1.4407	0.7700	0.7404	0.1996	0.1026
0.0949	74.96	937	0.8508	0.77	0.3540	1.4424	0.7700	0.7400	0.1996	0.1025
0.0949	76.0	950	0.8559	0.77	0.3558	1.4487	0.7700	0.7400	0.2001	0.1031
0.0949	76.96	962	0.8564	0.77	0.3568	1.4389	0.7700	0.7400	0.1804	0.1024
0.0949	78.0	975	0.8611	0.775	0.3569	1.4966	0.775	0.7440	0.1831	0.1031
0.0949	78.96	987	0.8573	0.77	0.3557	1.4946	0.7700	0.7400	0.1933	0.1013
0.0366	80.0	1000	0.8640	0.775	0.3587	1.4998	0.775	0.7440	0.1871	0.1032
0.0366	80.96	1012	0.8640	0.77	0.3585	1.4983	0.7700	0.7400	0.1921	0.1032
0.0366	82.0	1025	0.8696	0.77	0.3608	1.5032	0.7700	0.7400	0.2033	0.1036
0.0366	82.96	1037	0.8702	0.77	0.3613	1.4987	0.7700	0.7400	0.2022	0.1029
0.0366	84.0	1050	0.8686	0.77	0.3597	1.4446	0.7700	0.7400	0.1887	0.1028
0.0366	84.96	1062	0.8700	0.77	0.3607	1.4365	0.7700	0.7400	0.1900	0.1025
0.0366	86.0	1075	0.8756	0.765	0.3621	1.5009	0.765	0.7308	0.1983	0.1040
0.0366	86.96	1087	0.8768	0.76	0.3623	1.5035	0.76	0.7282	0.1956	0.1040
0.0366	88.0	1100	0.8762	0.765	0.3618	1.4409	0.765	0.7308	0.1957	0.1033
0.0366	88.96	1112	0.8777	0.765	0.3629	1.4427	0.765	0.7308	0.1974	0.1036
0.0366	90.0	1125	0.8854	0.76	0.3661	1.4681	0.76	0.7282	0.2023	0.1049
0.0366	90.96	1137	0.8867	0.76	0.3660	1.5057	0.76	0.7282	0.1995	0.1049
0.0366	92.0	1150	0.8849	0.765	0.3648	1.5011	0.765	0.7308	0.1953	0.1039
0.0366	92.96	1162	0.8898	0.76	0.3670	1.5077	0.76	0.7282	0.2083	0.1045
0.0366	94.0	1175	0.8891	0.765	0.3662	1.4520	0.765	0.7308	0.2091	0.1040
0.0366	94.96	1187	0.8910	0.755	0.3679	1.4460	0.755	0.7247	0.2039	0.1043
0.0366	96.0	1200	0.8935	0.76	0.3684	1.4435	0.76	0.7273	0.1929	0.1041
0.0366	96.96	1212	0.8964	0.755	0.3689	1.4526	0.755	0.7247	0.1980	0.1048
0.0366	98.0	1225	0.8979	0.755	0.3701	1.4507	0.755	0.7247	0.2017	0.1045
0.0366	98.96	1237	0.8965	0.755	0.3692	1.4474	0.755	0.7247	0.2057	0.1044
0.0366	100.0	1250	0.9019	0.755	0.3716	1.4526	0.755	0.7247	0.2051	0.1047
0.0366	100.96	1262	0.8994	0.755	0.3694	1.4485	0.755	0.7247	0.1979	0.1041
0.0366	102.0	1275	0.9023	0.755	0.3715	1.4465	0.755	0.7247	0.2140	0.1044
0.0366	102.96	1287	0.9048	0.755	0.3720	1.4472	0.755	0.7247	0.2066	0.1045
0.0366	104.0	1300	0.9060	0.755	0.3719	1.4565	0.755	0.7247	0.2003	0.1044
0.0366	104.96	1312	0.9105	0.755	0.3735	1.4625	0.755	0.7247	0.2094	0.1053
0.0366	106.0	1325	0.9099	0.76	0.3738	1.4463	0.76	0.7273	0.2050	0.1044
0.0366	106.96	1337	0.9111	0.755	0.3751	1.4486	0.755	0.7247	0.2173	0.1041
0.0366	108.0	1350	0.9149	0.755	0.3745	1.5081	0.755	0.7247	0.2062	0.1052
0.0366	108.96	1362	0.9146	0.755	0.3744	1.4513	0.755	0.7247	0.2073	0.1047
0.0366	110.0	1375	0.9157	0.755	0.3764	1.4486	0.755	0.7247	0.2094	0.1046
0.0366	110.96	1387	0.9201	0.755	0.3767	1.4529	0.755	0.7247	0.2093	0.1051
0.0366	112.0	1400	0.9190	0.755	0.3759	1.4533	0.755	0.7247	0.2020	0.1049
0.0366	112.96	1412	0.9230	0.755	0.3782	1.4529	0.755	0.7247	0.2054	0.1050
0.0366	114.0	1425	0.9234	0.755	0.3778	1.4505	0.755	0.7247	0.2009	0.1049
0.0366	114.96	1437	0.9238	0.755	0.3780	1.4469	0.755	0.7247	0.1974	0.1051
0.0366	116.0	1450	0.9264	0.755	0.3786	1.4538	0.755	0.7247	0.2016	0.1051
0.0366	116.96	1462	0.9275	0.755	0.3787	1.4553	0.755	0.7247	0.2012	0.1054
0.0366	118.0	1475	0.9306	0.755	0.3798	1.4595	0.755	0.7247	0.2139	0.1057
0.0366	118.96	1487	0.9291	0.76	0.3789	1.4529	0.76	0.7273	0.2014	0.1054
0.0214	120.0	1500	0.9318	0.755	0.3804	1.4520	0.755	0.7247	0.2017	0.1050
0.0214	120.96	1512	0.9325	0.755	0.3796	1.4535	0.755	0.7247	0.2087	0.1053
0.0214	122.0	1525	0.9339	0.755	0.3804	1.4534	0.755	0.7247	0.2068	0.1056
0.0214	122.96	1537	0.9342	0.755	0.3807	1.4519	0.755	0.7247	0.1986	0.1052
0.0214	124.0	1550	0.9357	0.755	0.3808	1.4524	0.755	0.7247	0.2058	0.1054
0.0214	124.96	1562	0.9360	0.755	0.3808	1.4514	0.755	0.7247	0.2061	0.1052
0.0214	126.0	1575	0.9409	0.755	0.3828	1.4557	0.755	0.7247	0.2044	0.1058
0.0214	126.96	1587	0.9390	0.755	0.3819	1.4523	0.755	0.7247	0.2062	0.1052
0.0214	128.0	1600	0.9425	0.755	0.3833	1.4559	0.755	0.7247	0.2049	0.1058
0.0214	128.96	1612	0.9421	0.755	0.3824	1.4534	0.755	0.7247	0.1978	0.1055
0.0214	130.0	1625	0.9433	0.755	0.3831	1.4530	0.755	0.7247	0.2069	0.1056
0.0214	130.96	1637	0.9463	0.755	0.3842	1.4535	0.755	0.7247	0.2127	0.1058
0.0214	132.0	1650	0.9462	0.755	0.3835	1.4546	0.755	0.7247	0.1975	0.1057
0.0214	132.96	1662	0.9479	0.755	0.3842	1.4562	0.755	0.7247	0.2012	0.1059
0.0214	134.0	1675	0.9493	0.755	0.3852	1.4547	0.755	0.7247	0.2161	0.1057
0.0214	134.96	1687	0.9484	0.755	0.3842	1.4563	0.755	0.7247	0.2046	0.1055
0.0214	136.0	1700	0.9500	0.755	0.3849	1.4528	0.755	0.7247	0.2081	0.1058
0.0214	136.96	1712	0.9510	0.755	0.3854	1.4510	0.755	0.7247	0.1976	0.1053
0.0214	138.0	1725	0.9519	0.755	0.3855	1.4516	0.755	0.7247	0.2090	0.1056
0.0214	138.96	1737	0.9535	0.755	0.3857	1.4537	0.755	0.7247	0.2091	0.1057
0.0214	140.0	1750	0.9546	0.755	0.3862	1.4557	0.755	0.7247	0.2020	0.1057
0.0214	140.96	1762	0.9558	0.755	0.3867	1.4530	0.755	0.7247	0.2018	0.1059
0.0214	142.0	1775	0.9567	0.755	0.3870	1.4522	0.755	0.7247	0.2059	0.1055
0.0214	142.96	1787	0.9589	0.755	0.3876	1.4555	0.755	0.7247	0.2063	0.1060
0.0214	144.0	1800	0.9584	0.755	0.3872	1.4568	0.755	0.7245	0.2162	0.1056
0.0214	144.96	1812	0.9613	0.755	0.3881	1.4594	0.755	0.7247	0.2085	0.1063
0.0214	146.0	1825	0.9604	0.755	0.3873	1.5132	0.755	0.7247	0.2047	0.1056
0.0214	146.96	1837	0.9627	0.755	0.3887	1.4573	0.755	0.7247	0.2107	0.1059
0.0214	148.0	1850	0.9643	0.755	0.3890	1.4570	0.755	0.7247	0.2041	0.1065
0.0214	148.96	1862	0.9633	0.755	0.3886	1.4526	0.755	0.7247	0.2085	0.1055
0.0214	150.0	1875	0.9637	0.755	0.3887	1.4551	0.755	0.7245	0.2096	0.1054
0.0214	150.96	1887	0.9645	0.755	0.3886	1.4534	0.755	0.7247	0.2100	0.1058
0.0214	152.0	1900	0.9661	0.755	0.3891	1.4550	0.755	0.7247	0.2072	0.1060
0.0214	152.96	1912	0.9665	0.755	0.3894	1.4543	0.755	0.7247	0.2092	0.1057
0.0214	154.0	1925	0.9667	0.755	0.3894	1.4570	0.755	0.7245	0.2019	0.1056
0.0214	154.96	1937	0.9681	0.755	0.3900	1.4537	0.755	0.7245	0.2098	0.1059
0.0214	156.0	1950	0.9689	0.755	0.3903	1.4533	0.755	0.7245	0.2022	0.1056
0.0214	156.96	1962	0.9689	0.755	0.3898	1.4553	0.755	0.7247	0.2074	0.1058
0.0214	158.0	1975	0.9705	0.755	0.3901	1.4566	0.755	0.7247	0.2072	0.1062
0.0214	158.96	1987	0.9721	0.755	0.3911	1.4570	0.755	0.7245	0.2055	0.1062
0.0155	160.0	2000	0.9712	0.755	0.3904	1.4551	0.755	0.7245	0.2070	0.1060
0.0155	160.96	2012	0.9721	0.755	0.3906	1.4563	0.755	0.7245	0.2108	0.1059
0.0155	162.0	2025	0.9734	0.755	0.3914	1.4550	0.755	0.7245	0.2071	0.1057
0.0155	162.96	2037	0.9740	0.755	0.3913	1.4565	0.755	0.7245	0.2073	0.1062
0.0155	164.0	2050	0.9744	0.755	0.3915	1.4563	0.755	0.7245	0.2101	0.1059
0.0155	164.96	2062	0.9752	0.755	0.3917	1.4558	0.755	0.7245	0.2102	0.1059
0.0155	166.0	2075	0.9755	0.755	0.3916	1.4566	0.755	0.7245	0.2102	0.1062
0.0155	166.96	2087	0.9755	0.755	0.3917	1.4542	0.755	0.7245	0.2100	0.1057
0.0155	168.0	2100	0.9768	0.755	0.3921	1.4578	0.755	0.7245	0.2103	0.1059
0.0155	168.96	2112	0.9767	0.755	0.3919	1.4575	0.755	0.7245	0.2106	0.1057
0.0155	170.0	2125	0.9776	0.755	0.3922	1.4567	0.755	0.7245	0.2101	0.1058
0.0155	170.96	2137	0.9783	0.755	0.3925	1.4560	0.755	0.7245	0.2080	0.1062
0.0155	172.0	2150	0.9793	0.755	0.3927	1.4578	0.755	0.7245	0.2102	0.1064
0.0155	172.96	2162	0.9783	0.755	0.3923	1.4557	0.755	0.7245	0.2098	0.1058
0.0155	174.0	2175	0.9790	0.755	0.3927	1.4550	0.755	0.7245	0.2087	0.1057
0.0155	174.96	2187	0.9801	0.755	0.3929	1.4577	0.755	0.7245	0.2100	0.1059
0.0155	176.0	2200	0.9800	0.755	0.3928	1.4566	0.755	0.7245	0.2081	0.1058
0.0155	176.96	2212	0.9809	0.755	0.3932	1.4568	0.755	0.7245	0.2101	0.1058
0.0155	178.0	2225	0.9808	0.755	0.3930	1.4571	0.755	0.7245	0.2101	0.1058
0.0155	178.96	2237	0.9808	0.755	0.3930	1.4566	0.755	0.7245	0.2082	0.1057
0.0155	180.0	2250	0.9813	0.755	0.3931	1.4567	0.755	0.7245	0.2082	0.1058
0.0155	180.96	2262	0.9817	0.755	0.3933	1.4571	0.755	0.7245	0.2032	0.1059
0.0155	182.0	2275	0.9819	0.755	0.3933	1.4570	0.755	0.7245	0.2103	0.1058
0.0155	182.96	2287	0.9822	0.755	0.3934	1.4567	0.755	0.7245	0.2101	0.1058
0.0155	184.0	2300	0.9824	0.755	0.3934	1.4572	0.755	0.7245	0.2101	0.1059
0.0155	184.96	2312	0.9825	0.755	0.3935	1.4569	0.755	0.7245	0.2081	0.1060
0.0155	186.0	2325	0.9825	0.755	0.3934	1.4574	0.755	0.7245	0.2101	0.1059
0.0155	186.96	2337	0.9829	0.755	0.3935	1.4571	0.755	0.7245	0.2101	0.1059
0.0155	188.0	2350	0.9830	0.755	0.3936	1.4569	0.755	0.7245	0.2081	0.1060
0.0155	188.96	2362	0.9831	0.755	0.3936	1.4572	0.755	0.7245	0.2082	0.1059
0.0155	190.0	2375	0.9830	0.755	0.3935	1.4575	0.755	0.7245	0.2101	0.1059
0.0155	190.96	2387	0.9831	0.755	0.3936	1.4572	0.755	0.7245	0.2101	0.1059
0.0155	192.0	2400	0.9831	0.755	0.3936	1.4572	0.755	0.7245	0.2101	0.1059

Framework versions

Transformers 4.30.2
Pytorch 1.13.1
Datasets 2.13.1
Tokenizers 0.13.3

ayanban011/vit-base_tobacco_wr_0.01_wd_0.2

vit-base_tobacco_wr_0.01_wd_0.2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model