|
|
| ╔══════════════════════════════════════════════════════════════╗ |
| ║ DAVID MODEL SUMMARY ║ |
| ╠══════════════════════════════════════════════════════════════╣ |
| ║ ║ |
| ║ 🎯 VALIDATION ACCURACY: 84.73% ║ |
| ║ ║ |
| ╚══════════════════════════════════════════════════════════════╝ |
|
|
| MODEL: David-partial_shared-deep_efficiency |
| RUN ID: 20251012_181608 |
| BEST EPOCH: 3/10 |
|
|
| ═══════════════════════════════════════════════════════════════ |
|
|
| 📊 PERFORMANCE BREAKDOWN |
|
|
| Final Training Accuracy: 96.34% |
| Best Validation Accuracy: 84.73% |
|
|
| Per-Scale Accuracies: |
| • Scale 384: 84.39% |
| • Scale 512: 84.67% |
| • Scale 768: 84.52% |
| • Scale 1024: 84.71% |
| • Scale 1280: 84.73% |
| • Scale 1536: 84.57% |
| • Scale 1792: 84.58% |
| • Scale 2048: 84.59% |
|
|
| ═══════════════════════════════════════════════════════════════ |
|
|
| 🏗️ ARCHITECTURE |
|
|
| Preset: clip_vit_bigg14 |
| Sharing Mode: partial_shared |
| Fusion Mode: deep_efficiency |
| Scales: 8 scales - [384, 512, 768, 1024, 1280, 1536, 1792, 2048] |
| Feature Dim: 1280 |
| Parameters: 60,814,373 |
|
|
| ═══════════════════════════════════════════════════════════════ |
|
|
| 📈 TRAINING CURVE |
|
|
| Epoch | Train Acc | Val Acc | Learning Rate |
| ------|-----------|----------|-------------- |
| 1 | 82.11% | 83.66% | 9.76e-04 |
| 2 | 87.16% | 84.31% | 9.05e-04 |
| 3 | 88.81% | 84.73% 👑 | 7.94e-04 |
| 4 | 90.27% | 84.51% | 6.55e-04 |
| 5 | 91.61% | 84.49% | 5.01e-04 |
| 6 | 92.98% | 84.60% | 3.46e-04 |
| 7 | 94.16% | 84.44% | 2.07e-04 |
| 8 | 95.16% | 84.39% | 9.64e-05 |
| 9 | 95.89% | 84.26% | 2.54e-05 |
| 10 | 96.34% | 84.23% | 1.00e-03 |
|
|
| ═══════════════════════════════════════════════════════════════ |
|
|
| 📁 FILES |
|
|
| Best Model: best_model_acc84.73.safetensors |
| Config: david_config.json |
| Training Cfg: train_config.json |
| History: training_history.json |
|
|
| ═══════════════════════════════════════════════════════════════ |
|
|
| Generated: 2025-10-12 18:49:27 |
|
|
