Modelpublic

carolinetfls/plant-seedlings-model-freeze-1

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes7downloads

Model Card

plant-seedlings-model-freeze-1

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

—Loss: 0.2053
—Accuracy: 0.9618

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: 0.0002
—trainbatchsize: 16
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 16
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4645	0.8	100	0.3145	0.8965
0.1731	1.6	200	0.2368	0.9188
0.1494	2.4	300	0.2755	0.9196
0.0819	3.2	400	0.1742	0.9530
0.0847	4.0	500	0.2245	0.9459
0.1155	4.8	600	0.4147	0.9140
0.0406	5.6	700	0.1918	0.9522
0.005	6.4	800	0.2489	0.9451
0.0003	7.2	900	0.2258	0.9530
0.0002	8.0	1000	0.2189	0.9570
0.0001	8.8	1100	0.2014	0.9618
0.0001	9.6	1200	0.2009	0.9626
0.0001	10.4	1300	0.2026	0.9610
0.0001	11.2	1400	0.2029	0.9610
0.0001	12.0	1500	0.2035	0.9618
0.0001	12.8	1600	0.2042	0.9626
0.0001	13.6	1700	0.2046	0.9618
0.0001	14.4	1800	0.2049	0.9618
0.0001	15.2	1900	0.2052	0.9626
0.0001	16.0	2000	0.2053	0.9618

Framework versions

—Transformers 4.28.1
—Pytorch 2.0.0+cu118
—Datasets 2.11.0
—Tokenizers 0.13.3