Upload README.md with huggingface_hub

README.md

@@ -24,9 +24,9 @@ model-index:
 
 # Model Card for Model ID
 
-This model is a small resnet18 trained on cifar100. It achieves the following results on the evaluation set: Accuracy: 0.7843.
+This model is a small resnet18 trained on cifar100.
 
-- **Developed by:** Eduardo Dadalto
+- **Test Accuracy:** 0.7843
 - **License:** MIT
 
 ## How to Get Started with the Model
@@ -36,25 +36,50 @@ Use the code below to get started with the model.
 ```python
 import detectors
 import timm
+
 model = timm.create_model("resnet18_cifar100", pretrained=True)
 ```
 
 ## Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
 Training data is cifar100.
 
 ## Training Hyperparameters
 
-## Evaluation
 
-### Testing Data
+- config: scripts/train_configs/cifar100.json
 
-<!-- This should link to a Data Card if possible. -->
+- model: resnet18_cifar100
 
-Testing data is cifar100.
+- dataset: cifar100
+
+- batch_size: 64
+
+- epochs: 200
+
+- validation_frequency: 5
+
+- seed: 1
+
+- criterion: CrossEntropyLoss
+
+- criterion_kwargs: {}
 
-## Results
+- optimizer: SGD
+
+- lr: 0.1
+
+- optimizer_kwargs: {'momentum': 0.9, 'weight_decay': 0.0005}
+
+- scheduler: CosineAnnealingLR
+
+- scheduler_kwargs: {'T_max': 190}
+
+- debug: False
+
+
+## Testing Data
+
+Testing data is cifar100.
 
-Accuracy is 0.7843.
+This model card was created by Eduardo Dadalto.