Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,38 @@
+# Training Logs - EfficientNet-B3
+## Experiment: 20251110_181006
+
+### Model Architecture
+- **Base Model**: EfficientNet-B3 (pretrained on ImageNet)
+- **Task**: Multi-task learning (Age Regression + Gender Classification)
+- **Input Size**: 256x256
+
+### Training Configuration
+- **Batch Size**: 16
+- **Learning Rate**: 0.0002
+- **Optimizer**: AdamW (weight_decay=1e-4)
+- **Scheduler**: CosineAnnealingWarmRestarts
+- **Epochs Trained**: 12 / 40
+
+### Best Results
+- **Validation Harmonic Mean**: 0.9683
+- **Validation Age RMSE**: 0.1185 years
+- **Validation Gender F1**: 0.9439
+- **Best Epoch**: 8
+
+### Final Metrics (Last Epoch)
+- **Val Loss**: 0.2825
+- **Val Harmonic Mean**: 0.9680
+- **Val Age RMSE**: 0.1185
+- **Val Age MAE**: 0.0850
+- **Val Gender F1**: 0.9432
+
+### Files in this Dataset
+- `pytorch_lightning/metrics_20251110_181006.csv` - Complete training history
+- `summaries/training_summary_20251110_181006.json` - Detailed metrics and config
+- `trackio/trackio_logs_20251110_181006.zip` - TrackIO logs (if available)
+
+### Next Steps
+Use the best checkpoint for inference:
+```python
+checkpoint_path = "checkpoints/efficientnet/effnet-epoch=08-val_harmonic_mean=0.9683.ckpt"
+```