resnet-18-dungeons-001

This model is a fine-tuned version of microsoft/resnet-18 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.1886
• Accuracy: 0.5

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: 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: cosine_with_restarts
• lr_scheduler_warmup_steps: 100
• num_epochs: 85
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0594	6.6667	10	1.3086	0.5833
0.0973	13.3333	20	1.3523	0.5
0.068	20.0	30	1.2428	0.5833
0.0671	26.6667	40	1.2280	0.5833
0.0527	33.3333	50	1.2677	0.5833
0.0592	40.0	60	1.2846	0.5833
0.0446	46.6667	70	1.2210	0.5833
0.0565	53.3333	80	1.1886	0.5

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1