plant-seedlings-model

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

• Loss: 0.1235
• Accuracy: 0.9783

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
• 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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3236	1.27	500	0.2747	0.9019
0.2273	2.54	1000	0.3031	0.9038
0.082	3.82	1500	0.2103	0.9280
0.061	5.09	2000	0.2235	0.9408
0.0668	6.36	2500	0.1633	0.9554
0.0739	7.63	3000	0.1561	0.9586
0.0836	8.91	3500	0.1904	0.9446
0.0078	10.18	4000	0.2045	0.9535
0.087	11.45	4500	0.4487	0.9146
0.0119	12.72	5000	0.2162	0.9567
0.0002	13.99	5500	0.1157	0.9758
0.0001	15.27	6000	0.1199	0.9771
0.0001	16.54	6500	0.1215	0.9790
0.0001	17.81	7000	0.1223	0.9790
0.0001	19.08	7500	0.1235	0.9783

Framework versions

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