convnext-tiny-224-finetuned-eurosat-albumentations

This model is a fine-tuned version of paom/convnext-tiny-224-finetuned-eurosat-albumentations on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6948
• Accuracy: 0.0

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.6948	0.0
No log	2.0	2	0.5057	0.0
No log	3.0	3	0.2286	0.0
No log	4.0	4	0.0823	0.0
No log	5.0	5	0.0320	0.0
No log	6.0	6	0.0489	0.0
No log	7.0	7	0.0881	0.0
No log	8.0	8	0.1134	0.0
No log	9.0	9	0.1179	0.0
0.0638	10.0	10	0.1054	0.0
0.0638	11.0	11	0.0826	0.0
0.0638	12.0	12	0.0587	0.0
0.0638	13.0	13	0.0386	0.0
0.0638	14.0	14	0.0241	0.0
0.0638	15.0	15	0.0158	0.0
0.0638	16.0	16	0.0115	0.0
0.0638	17.0	17	0.0096	0.0
0.0638	18.0	18	0.0087	0.0
0.0638	19.0	19	0.0084	0.0
0.0048	20.0	20	0.0083	0.0

Framework versions

• Transformers 4.29.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3