MRR_image_classification_dit_29_jan-finetuned-eurosat

This model is a fine-tuned version of microsoft/dit-large on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4995
• Accuracy: 0.8250

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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 results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0588	1.0	175	0.8931	0.6622
0.7206	2.0	351	0.6266	0.7774
0.6833	2.99	525	0.4995	0.8250

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1