alyzbane/resnet-50-finetuned-FBark-5

resnet-50-finetuned-FBark-1k

This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.9792
• F1: 0.9808
• Loss: 0.0686
• Precision: 0.9788
• Recall: 0.9833

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 35

Training results

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.15.1