Parameter | Value |
---|---|
Model Name | resnet18 |
Epochs | Because of early stopping: the trainingstopped at epoch 7 |
Batch Size | Auto-selected batch size by Ludwig: 16 |
Fine Tune | True |
Use Pretrained | True |
Learning Rate | Auto-selected learning rate by Ludwig: 1e-05 Based on model architecture and training setup (e.g., fine-tuning). See Ludwig Trainer Parameters for details. |
Random Seedearly Stop | N/A |
Data Split | Detected a split column (with values 0 and 2) in the input CSV. Used this column as a base andreassigned 15.0% of the training set (originally labeled 0) to validation (labeled 1). |
Model trained using Ludwig.
If want to learn more about Ludwig default settings,please check the their website(ludwig.ai).
Metric | Train | Validation | Test |
---|---|---|---|
accuracy | 0.8417 | 0.1500 | 0.2000 |
accuracy_micro | 0.8471 | 0.2000 | 0.2000 |
hits_at_k | 0.9250 | 0.4500 | 0.3000 |
loss | 0.6749 | 2.7907 | 2.8261 |
roc_auc | 0.9998 | 0.7824 | 0.6917 |