save-model-final-fork

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on the jbarat/plant_species dataset. It achieves the following results on the evaluation set:

• Loss: 0.0002
• Accuracy: 1.0

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: 0.0003
• train_batch_size: 64
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 21

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
No log	1.0	10	0.725	0.7459
No log	2.0	20	0.875	0.5996
No log	3.0	30	0.7375	0.8398
No log	4.0	40	0.8125	0.6444
No log	5.0	50	0.8375	0.6891
No log	6.0	60	0.825	0.6675
No log	7.0	70	0.8375	0.7300
No log	8.0	80	0.85	0.8635
No log	9.0	90	0.95	0.3333
0.1657	10.0	100	0.9375	0.2634
0.1657	11.0	110	0.9375	0.3821
0.1657	12.0	120	0.9625	0.2343
0.1657	13.0	130	0.9375	0.3103
0.1657	14.0	140	0.95	0.3481
0.1657	15.0	150	0.9625	0.2419
0.1657	16.0	160	0.9375	0.2408
0.1657	17.0	170	0.95	0.3202
0.1657	18.0	180	0.9125	0.4016
0.1657	19.0	190	0.925	0.3918
0.0254	20.0	200	0.9375	0.3874
0.0254	21.0	210	0.0006	1.0

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2