Plant_Classification_model_vit-base-patch16-224-in21k

This model is a fine-tuned version of Professor/Plant_Classification_model_vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4976
• Accuracy: 0.8737

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: 0.001
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	193	1.6872	0.5531
No log	2.0	386	1.2610	0.6490
1.7011	3.0	579	1.1522	0.6658
1.7011	4.0	772	0.9463	0.7293
1.7011	5.0	965	0.8893	0.7377
0.9968	6.0	1158	0.8774	0.7306
0.9968	7.0	1351	0.7006	0.7908
0.734	8.0	1544	0.7599	0.7791
0.734	9.0	1737	0.6890	0.7895
0.734	10.0	1930	0.6686	0.7882
0.5624	11.0	2123	0.6111	0.8271
0.5624	12.0	2316	0.6342	0.8122
0.4342	13.0	2509	0.5493	0.8381
0.4342	14.0	2702	0.5186	0.8452
0.4342	15.0	2895	0.5610	0.8381
0.3097	16.0	3088	0.5520	0.8439
0.3097	17.0	3281	0.5237	0.8588
0.3097	18.0	3474	0.4999	0.8659
0.2119	19.0	3667	0.4976	0.8737
0.2119	20.0	3860	0.5038	0.8711

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0