msi-nat-mini-pretrain

This model is a fine-tuned version of shi-labs/nat-mini-in1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.6286
• Accuracy: 0.8705

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
0.1151	1.0	1562	0.2480	0.9242
0.0453	2.0	3125	0.5128	0.8816
0.0466	3.0	4686	0.6286	0.8705

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0