resnet-18-cifar100-42

This model is a fine-tuned version of microsoft/resnet-18 on the cifar100 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9912
• Accuracy: 0.7224

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 256
• 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
3.7105	1.0	1329	2.1789	0.4799
2.7042	2.0	2658	1.5676	0.6031
2.2904	3.0	3987	1.3354	0.6456
1.9172	4.0	5316	1.1968	0.6825
1.8135	5.0	6645	1.1388	0.6864
1.7271	6.0	7974	1.0620	0.7079
1.6387	7.0	9303	1.0278	0.7141
1.5859	8.0	10632	1.0033	0.7171
1.5589	9.0	11961	0.9872	0.7223
1.5331	10.0	13290	0.9912	0.7224

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.13.3