ryan03312024_lr_2e-5_wd_001

rshrott/ryan03312024_lr_2e-5_wd_001

ryan03312024_lr_2e-5_wd_001 is a image classification model from rshrott. 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

29% of all-time downloads

All-time downloads

Public

Parameters

85.8M

14.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Mar 31, 2024
Updated: Mar 31, 2024
SHA: 9b680ae2

Base models

google/vit-base-patch16-224-in21k

Model card

From the Hugging Face model README

ryan03312024_lr_2e-5_wd_001

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the properties dataset. It achieves the following results on the evaluation set:

Loss: 0.1916
Ordinal Mae: 0.4221
Ordinal Accuracy: 0.6828
Na Accuracy: 0.8591

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Ordinal Mae	Ordinal Accuracy	Na Accuracy
0.4436	0.04	100	0.3698	0.8706	0.3332	0.7990
0.3143	0.07	200	0.3215	0.8555	0.4017	0.8093
0.3385	0.11	300	0.2997	0.8303	0.4485	0.8591
0.3127	0.14	400	0.2889	0.8013	0.4881	0.8746
0.3054	0.18	500	0.2804	0.7619	0.5325	0.8780
0.3051	0.22	600	0.2752	0.7215	0.5235	0.9158
0.2833	0.25	700	0.2653	0.6807	0.5487	0.8969
0.2907	0.29	800	0.2550	0.6432	0.5618	0.8351
0.2468	0.32	900	0.2522	0.6119	0.5972	0.8058
0.2199	0.36	1000	0.2437	0.6023	0.6062	0.8127
0.2219	0.4	1100	0.2361	0.5574	0.5959	0.9038
0.2071	0.43	1200	0.2387	0.5439	0.6175	0.7715
0.2214	0.47	1300	0.2341	0.5257	0.6232	0.7955
0.2627	0.5	1400	0.2315	0.5152	0.6124	0.7990
0.2067	0.54	1500	0.2247	0.5026	0.6396	0.8110
0.2086	0.58	1600	0.2192	0.4955	0.6589	0.8041
0.1993	0.61	1700	0.2182	0.4738	0.6522	0.8127
0.1962	0.65	1800	0.2211	0.4858	0.6232	0.9141
0.1882	0.69	1900	0.2045	0.4669	0.6632	0.8625
0.1895	0.72	2000	0.2082	0.4696	0.6316	0.8608
0.1979	0.76	2100	0.2270	0.4791	0.6373	0.9003
0.2643	0.79	2200	0.2069	0.4663	0.6414	0.8557
0.2279	0.83	2300	0.2030	0.4581	0.6543	0.8694
0.1965	0.87	2400	0.2109	0.4446	0.6820	0.8007
0.1637	0.9	2500	0.2005	0.4439	0.6763	0.8557
0.1705	0.94	2600	0.1964	0.4321	0.6748	0.8540
0.2412	0.97	2700	0.1958	0.4345	0.6730	0.8780
0.1438	1.01	2800	0.1972	0.4301	0.6784	0.8471
0.123	1.05	2900	0.1995	0.4231	0.6753	0.8419
0.1411	1.08	3000	0.1946	0.4220	0.6817	0.8454
0.1443	1.12	3100	0.1916	0.4221	0.6828	0.8591
0.208	1.15	3200	0.1942	0.4163	0.6740	0.8677
0.1343	1.19	3300	0.1962	0.4182	0.6889	0.8471
0.1347	1.23	3400	0.1938	0.4161	0.6900	0.8660
0.1076	1.26	3500	0.1970	0.4181	0.6943	0.8471
0.1248	1.3	3600	0.1951	0.4151	0.6959	0.8471
0.1455	1.33	3700	0.1952	0.4147	0.6851	0.8814
0.131	1.37	3800	0.1953	0.4172	0.6948	0.8454
0.1307	1.41	3900	0.1932	0.4127	0.6928	0.8643
0.1198	1.44	4000	0.1947	0.4110	0.6941	0.8574
0.1363	1.48	4100	0.1952	0.4087	0.6887	0.8574

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Mar 31, 2024
Updated: Mar 31, 2024