vit-base-patch16-224-MSC-ARMD-1

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

• Loss: 0.6451
• Accuracy: 0.95

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.67	1	1.3505	0.25
No log	2.0	3	1.1657	0.4
No log	2.67	4	1.0703	0.55
No log	4.0	6	0.8973	0.85
No log	4.67	7	0.8834	0.8
1.0988	6.0	9	0.7316	0.9
1.0988	6.67	10	0.6451	0.95
1.0988	8.0	12	0.5251	0.95
1.0988	8.67	13	0.4916	0.95
1.0988	10.0	15	0.4606	0.85
0.4896	10.67	16	0.4564	0.85

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3