test-cont-lr

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: 0.9419
• Accuracy: 0.7

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	1.0693	0.6125
No log	2.0	20	0.8939	0.675
No log	3.0	30	1.1355	0.7
No log	4.0	40	1.6583	0.6625
No log	5.0	50	1.5728	0.7
No log	6.0	60	1.4494	0.6625
No log	7.0	70	1.3951	0.6625
No log	8.0	80	1.7134	0.6875
No log	9.0	90	1.5019	0.6875
0.2446	10.0	100	1.4587	0.675

Framework versions

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