vit-base_tobacco

ayanban011/vit-base_tobacco

vit-base_tobacco is a image classification model from ayanban011. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

376

Public

Repo size

687 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Jul 12, 2023
Updated: Jul 12, 2023
SHA: 8696f129

Model card

From the Hugging Face model README

vit-base_tobacco

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: 0.7324
Accuracy: 0.8
Brier Loss: 0.3049
Nll: 1.3070
F1 Micro: 0.8000
F1 Macro: 0.7733
Ece: 0.2124
Aurc: 0.0840

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: 40
eval_batch_size: 40
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 640
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Brier Loss	Nll	F1 Micro	F1 Macro	Ece	Aurc
No log	0.8	1	0.7434	0.815	0.3073	1.1863	0.815	0.7942	0.2217	0.0720
No log	1.6	2	0.7569	0.81	0.3117	1.2131	0.81	0.7893	0.2153	0.0800
No log	2.4	3	0.7491	0.82	0.3107	1.2631	0.82	0.8063	0.2311	0.0777
No log	4.0	5	0.7489	0.795	0.3088	1.1544	0.795	0.7766	0.2427	0.0730
No log	4.8	6	0.7658	0.81	0.3171	1.3766	0.81	0.7983	0.2434	0.0822
No log	5.6	7	0.7496	0.815	0.3097	1.1920	0.815	0.8014	0.2434	0.0848
No log	6.4	8	0.7468	0.8	0.3090	1.0732	0.8000	0.7750	0.2195	0.0774
No log	8.0	10	0.7563	0.815	0.3131	1.3472	0.815	0.8082	0.2255	0.0741
No log	8.8	11	0.7548	0.81	0.3116	1.2016	0.81	0.7930	0.2496	0.0868
No log	9.6	12	0.7395	0.805	0.3071	1.1664	0.805	0.7841	0.2432	0.0772
No log	10.4	13	0.7296	0.82	0.3018	1.1776	0.82	0.8078	0.2214	0.0676
No log	12.0	15	0.7515	0.815	0.3104	1.2034	0.815	0.7987	0.2307	0.0835
No log	12.8	16	0.7350	0.81	0.3053	1.1762	0.81	0.7978	0.2196	0.0747
No log	13.6	17	0.7281	0.805	0.3023	1.1664	0.805	0.7841	0.2144	0.0718
No log	14.4	18	0.7395	0.81	0.3064	1.1750	0.81	0.7871	0.2306	0.0778
No log	16.0	20	0.7427	0.81	0.3076	1.2637	0.81	0.7986	0.2194	0.0808
No log	16.8	21	0.7337	0.81	0.3044	1.2447	0.81	0.7948	0.2321	0.0743
No log	17.6	22	0.7340	0.805	0.3050	1.1681	0.805	0.7841	0.2307	0.0743
No log	18.4	23	0.7338	0.805	0.3047	1.1708	0.805	0.7841	0.2290	0.0759
No log	20.0	25	0.7390	0.815	0.3058	1.2551	0.815	0.7984	0.2489	0.0818
No log	20.8	26	0.7390	0.815	0.3063	1.1894	0.815	0.7984	0.2294	0.0818
No log	21.6	27	0.7349	0.805	0.3054	1.1714	0.805	0.7847	0.2011	0.0791
No log	22.4	28	0.7308	0.81	0.3037	1.1694	0.81	0.7948	0.2128	0.0766
No log	24.0	30	0.7353	0.81	0.3051	1.1852	0.81	0.7956	0.2282	0.0794
No log	24.8	31	0.7378	0.81	0.3062	1.1870	0.81	0.7956	0.2293	0.0819
No log	25.6	32	0.7356	0.81	0.3054	1.1863	0.81	0.7956	0.2287	0.0817
No log	26.4	33	0.7309	0.81	0.3037	1.1801	0.81	0.7954	0.2209	0.0795
No log	28.0	35	0.7336	0.805	0.3050	1.1733	0.805	0.7850	0.2082	0.0789
No log	28.8	36	0.7334	0.81	0.3045	1.1799	0.81	0.7956	0.2207	0.0797
No log	29.6	37	0.7320	0.81	0.3040	1.2447	0.81	0.7956	0.2279	0.0804
No log	30.4	38	0.7328	0.81	0.3045	1.2473	0.81	0.7956	0.2154	0.0812
No log	32.0	40	0.7322	0.805	0.3044	1.1796	0.805	0.7850	0.2384	0.0804
No log	32.8	41	0.7318	0.81	0.3045	1.1792	0.81	0.7954	0.2291	0.0794
No log	33.6	42	0.7302	0.81	0.3034	1.2401	0.81	0.7954	0.2086	0.0794
No log	34.4	43	0.7311	0.805	0.3036	1.2424	0.805	0.7850	0.2278	0.0804
No log	36.0	45	0.7323	0.805	0.3043	1.1902	0.805	0.7850	0.2119	0.0816
No log	36.8	46	0.7304	0.805	0.3034	1.2428	0.805	0.7850	0.2330	0.0807
No log	37.6	47	0.7297	0.805	0.3032	1.2413	0.805	0.7850	0.2447	0.0801
No log	38.4	48	0.7310	0.805	0.3039	1.2424	0.805	0.7850	0.2233	0.0802
No log	40.0	50	0.7316	0.805	0.3040	1.2451	0.805	0.7850	0.2094	0.0809
No log	40.8	51	0.7313	0.805	0.3041	1.2450	0.805	0.7850	0.2093	0.0810
No log	41.6	52	0.7313	0.805	0.3041	1.2445	0.805	0.7850	0.2073	0.0814
No log	42.4	53	0.7315	0.805	0.3040	1.2447	0.805	0.7850	0.2198	0.0821
No log	44.0	55	0.7303	0.805	0.3034	1.2441	0.805	0.7850	0.2048	0.0813
No log	44.8	56	0.7306	0.805	0.3038	1.2444	0.805	0.7850	0.1966	0.0809
No log	45.6	57	0.7317	0.805	0.3043	1.2449	0.805	0.7850	0.1976	0.0821
No log	46.4	58	0.7317	0.805	0.3041	1.2466	0.805	0.7850	0.2007	0.0822
No log	48.0	60	0.7316	0.805	0.3041	1.2499	0.805	0.7850	0.2137	0.0820
No log	48.8	61	0.7320	0.8	0.3043	1.2536	0.8000	0.7733	0.2081	0.0822
No log	49.6	62	0.7319	0.805	0.3044	1.2494	0.805	0.7850	0.1998	0.0825
No log	50.4	63	0.7326	0.805	0.3048	1.2476	0.805	0.7850	0.1936	0.0828
No log	52.0	65	0.7313	0.8	0.3044	1.2495	0.8000	0.7733	0.2117	0.0822
No log	52.8	66	0.7304	0.8	0.3039	1.2524	0.8000	0.7733	0.2009	0.0818
No log	53.6	67	0.7306	0.8	0.3038	1.2505	0.8000	0.7733	0.2182	0.0818
No log	54.4	68	0.7321	0.8	0.3044	1.2513	0.8000	0.7733	0.2185	0.0833
No log	56.0	70	0.7326	0.8	0.3049	1.2519	0.8000	0.7733	0.2014	0.0833
No log	56.8	71	0.7320	0.8	0.3047	1.2580	0.8000	0.7733	0.2175	0.0829
No log	57.6	72	0.7313	0.8	0.3043	1.2571	0.8000	0.7733	0.2045	0.0828
No log	58.4	73	0.7314	0.8	0.3043	1.3065	0.8000	0.7733	0.2038	0.0827
No log	60.0	75	0.7322	0.8	0.3046	1.3081	0.8000	0.7733	0.2047	0.0840
No log	60.8	76	0.7323	0.8	0.3047	1.3078	0.8000	0.7733	0.2053	0.0839
No log	61.6	77	0.7322	0.8	0.3047	1.3070	0.8000	0.7733	0.2051	0.0837
No log	62.4	78	0.7316	0.8	0.3045	1.3062	0.8000	0.7733	0.2145	0.0835
No log	64.0	80	0.7315	0.8	0.3044	1.3063	0.8000	0.7733	0.2067	0.0836
No log	64.8	81	0.7320	0.8	0.3047	1.3064	0.8000	0.7733	0.2041	0.0839
No log	65.6	82	0.7323	0.8	0.3048	1.3070	0.8000	0.7733	0.2046	0.0839
No log	66.4	83	0.7323	0.8	0.3048	1.3068	0.8000	0.7733	0.2045	0.0838
No log	68.0	85	0.7320	0.8	0.3046	1.3068	0.8000	0.7733	0.2046	0.0840
No log	68.8	86	0.7318	0.8	0.3045	1.3069	0.8000	0.7733	0.2114	0.0838
No log	69.6	87	0.7316	0.8	0.3045	1.3066	0.8000	0.7733	0.2149	0.0836
No log	70.4	88	0.7316	0.8	0.3045	1.3066	0.8000	0.7733	0.2244	0.0834
No log	72.0	90	0.7321	0.8	0.3047	1.3069	0.8000	0.7733	0.2151	0.0837
No log	72.8	91	0.7322	0.8	0.3048	1.3070	0.8000	0.7733	0.2151	0.0839
No log	73.6	92	0.7322	0.8	0.3048	1.3070	0.8000	0.7733	0.2155	0.0840
No log	74.4	93	0.7323	0.8	0.3048	1.3071	0.8000	0.7733	0.2129	0.0842
No log	76.0	95	0.7324	0.8	0.3049	1.3071	0.8000	0.7733	0.2084	0.0841
No log	76.8	96	0.7324	0.8	0.3049	1.3071	0.8000	0.7733	0.2141	0.0842
No log	77.6	97	0.7324	0.8	0.3049	1.3070	0.8000	0.7733	0.2136	0.0841
No log	78.4	98	0.7324	0.8	0.3049	1.3070	0.8000	0.7733	0.2136	0.0841
No log	80.0	100	0.7324	0.8	0.3049	1.3070	0.8000	0.7733	0.2124	0.0840

Framework versions

Transformers 4.30.2
Pytorch 1.13.1
Datasets 2.13.1
Tokenizers 0.13.3

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Jul 12, 2023
Updated: Jul 12, 2023