portrait_cosu_exp4

This model is a fine-tuned version of NekoFi/portrait_cosu_exp3 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.2432
• Accuracy: 0.9037
• Precision: 0.9043
• Recall: 0.9037
• F1: 0.9035
• Confusion Matrix: [[66, 5], [8, 56]]

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Confusion Matrix
0.3876	1.0	19	0.3650	0.8370	0.8555	0.8370	0.8336	[[68, 3], [19, 45]]
0.2696	2.0	38	0.2479	0.8963	0.8965	0.8963	0.8962	[[65, 6], [8, 56]]
0.2143	3.0	57	0.2665	0.8889	0.8906	0.8889	0.8885	[[66, 5], [10, 54]]
0.1629	4.0	76	0.2432	0.9037	0.9043	0.9037	0.9035	[[66, 5], [8, 56]]

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1