vit-base-patch16-224-in21k-finetuned-eurosat

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

• Loss: 0.0581
• Accuracy: 0.9904

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: IPU
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• training precision: Mixed Precision

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0804	1.0	759	0.1383	0.9741
0.0385	2.0	1518	0.0756	0.9859
0.1211	3.0	2277	0.0581	0.9904

Framework versions

• Transformers 4.20.1
• Pytorch 1.10.0+cpu
• Datasets 2.7.1
• Tokenizers 0.12.1