image_classification

This model is a fine-tuned version of nateraw/vit-age-classifier on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.8469
• Accuracy: 0.3438

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.3
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	1	1.8452	0.3125
No log	1.6	2	1.8435	0.35
No log	2.4	3	1.8282	0.3688
No log	4.0	5	1.8112	0.3563
No log	4.8	6	1.8180	0.3312
No log	5.6	7	1.8291	0.3375
No log	6.4	8	1.8036	0.3563
1.6711	8.0	10	1.8134	0.3375

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1