{% if favicon %} {% endif %}
{% if logo %} {% endif %}

Knowledge Distillation Report

Model Compression and Knowledge Transfer Analysis

Model: {{ model_name }} Date: {{ timestamp }} Models Tested: {{ total_models }}

📊 Executive Summary

Models Evaluated

{{ total_models }}

Distilled models tested

Best Test Accuracy

{{ "%.2f" | format(best_accuracy * 100) }}%

Highest performing model

Best F1 Score

{{ "%.2f" | format((best_model.metrics.test_f1_score * 100) if best_model.metrics and best_model.metrics.test_f1_score else 0) }}%

Balance of precision/recall

Best AUC-ROC

{{ "%.3f" | format(best_model.metrics.test_auc_roc if best_model.metrics and best_model.metrics.test_auc_roc else 0) }}

Classification quality

🏆 Best Performing Model Configuration

Algorithm: {{ best_model.model_type | replace("ModelType.", "") | replace("_", " ") | title }}

Hyperparameters: Temperature = {{ "%.1f" | format(best_model.temperature) }}, Alpha = {{ "%.1f" | format(best_model.alpha) }}

Performance Metrics: Accuracy: {{ "%.3f" | format(best_model.metrics.test_accuracy) if best_model.metrics and best_model.metrics.test_accuracy else "N/A" }}, Precision: {{ "%.3f" | format(best_model.metrics.test_precision) if best_model.metrics and best_model.metrics.test_precision else "N/A" }}, Recall: {{ "%.3f" | format(best_model.metrics.test_recall) if best_model.metrics and best_model.metrics.test_recall else "N/A" }}

📈 Performance Analysis

{% if charts.radar_chart %}

Original vs Best Distilled Model

Radar comparison chart
{% endif %} {% if charts.performance_heatmap %}

Model Performance Heatmap

Performance heatmap
{% endif %} {% if charts.hyperparameter_surface %}

Hyperparameter Impact

Hyperparameter surface
{% endif %} {% if charts.tradeoff_scatter %}

Accuracy vs Complexity Trade-off

Trade-off scatter plot
{% endif %} {% if charts.metrics_comparison %}

Metrics Comparison

Metrics comparison
{% endif %} {# KS Statistic Distribution chart disabled #} {# {% if charts.ks_distribution %}

KS Statistic Distribution Analysis

KS statistic distribution
{% endif %} #} {% if charts.frequency_distribution %}

Prediction Frequency Distribution

Frequency distribution comparison
{% endif %} {# Model Rankings chart disabled #} {# {% if charts.model_rankings %}

Model Rankings

Model rankings
{% endif %} #}

🏆 Top Models Performance

{% for model in all_models[:10] %} {% endfor %}
Rank Model Temperature Alpha Accuracy Precision Recall F1 Score
#{{ loop.index }} {{ model.model_type }} {{ model.temperature }} {{ model.alpha }} {{ "%.4f" | format(model.metrics.test_accuracy) if model.metrics and model.metrics.test_accuracy else "N/A" }} {{ "%.4f" | format(model.metrics.test_precision) if model.metrics and model.metrics.test_precision else "N/A" }} {{ "%.4f" | format(model.metrics.test_recall) if model.metrics and model.metrics.test_recall else "N/A" }} {{ "%.4f" | format(model.metrics.test_f1_score) if model.metrics and model.metrics.test_f1_score else "N/A" }}

💡 Recommendations

{% for rec in recommendations %}

{{ rec.scenario }}

Model: {{ rec.model }} ({{ rec.config }})

Reason: {{ rec.reason }}

Key Metrics: Accuracy: {{ "%.4f" | format(rec.metrics.accuracy) }}{% if rec.metrics.f1_score %}, F1: {{ "%.4f" | format(rec.metrics.f1_score) }}{% endif %}

{% endfor %}

Generated by DeepBridge Knowledge Distillation Analysis

{{ timestamp }}