custom-vgg19

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3984
• Accuracy: 0.9216

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	13	0.5019	0.8235
No log	2.0	26	0.4287	0.9020
No log	3.0	39	0.4242	0.9020
No log	4.0	52	0.5184	0.8039
No log	5.0	65	0.4223	0.8824
No log	6.0	78	0.4254	0.8824
No log	7.0	91	0.4310	0.8824
No log	8.0	104	0.3984	0.9216
No log	9.0	117	0.4275	0.8824
No log	10.0	130	0.4264	0.8824

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1