edit-training-arg

This model is a fine-tuned version of vuongnhathien/SwinV2-30VNFood on the jbarat/plant_species dataset. It achieves the following results on the evaluation set:

• Loss: 1.3643
• Accuracy: 0.5875

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: 0.0005
• 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: cosine
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	0.7014	0.7375
No log	2.0	20	0.5727	0.75
No log	3.0	30	0.7431	0.7875
No log	4.0	40	0.7550	0.7875
No log	5.0	50	0.6643	0.7875
No log	6.0	60	0.6035	0.8625
No log	7.0	70	0.8655	0.8375
No log	8.0	80	0.7624	0.825
No log	9.0	90	0.6606	0.85
0.2933	10.0	100	0.6476	0.85

Framework versions

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