Compression Rate

{{ report_data.compression_rate|default("0.0") }}x

{{ report_data.compression_improvement|default("0.0") }}% smaller

Student Accuracy

{{ report_data.student_accuracy|default("0.0") }}%

{{ report_data.accuracy_drop|default("0.0") }}% vs teacher

Speed-up Factor

{{ report_data.speedup_factor|default("0.0") }}x

{{ report_data.inference_time_reduction|default("0.0") }}% faster

Memory Saved

{{ report_data.memory_saved|default("0.0") }} MB

{{ report_data.memory_reduction|default("0.0") }}% reduction

Distillation Process Timeline

Configuration Summary

Distillation Method	{{ report_data.distillation_method\|default("Knowledge Distillation") }}
Teacher Model	{{ report_data.teacher_model\|default("Not specified") }}
Student Architecture	{{ report_data.student_architecture\|default("Not specified") }}
Temperature	{{ report_data.temperature\|default("3.0") }}
Alpha (KD Loss Weight)	{{ report_data.alpha\|default("0.7") }}
Training Epochs	{{ report_data.epochs\|default("100") }}
Batch Size	{{ report_data.batch_size\|default("32") }}
Learning Rate	{{ report_data.learning_rate\|default("0.001") }}

Model Size Comparison

Training Progress

Quick Insights

{% if report_data.insights %} {% for insight in report_data.insights %}

{% endfor %} {% else %}

The distillation process successfully compressed the model by {{ report_data.compression_rate|default("N/A") }}x while maintaining {{ report_data.accuracy_retention|default("N/A") }}% of the original accuracy.

The student model achieves {{ report_data.speedup_factor|default("N/A") }}x faster inference time with {{ report_data.memory_saved|default("N/A") }} MB memory reduction.

{% if report_data.warnings %} {% for warning in report_data.warnings %}

{% endfor %} {% endif %} {% endif %}