Configuration Parsing Warning:Invalid JSON for config file config.json
SOA MODULE — DISTILBERT Benchmark Result
Status: ✅ PASS
Dataset: GLUE SST-2 (Binary)
Architecture: distilbert
Module: soa_module
This repository hosts empirical benchmark results and factorized checkpoints for soa_module applied to distilbert on GLUE SST-2 (Binary).
Trained weights (weights.pt) are included in this repository.
Benchmark Performance Metrics
| Metric | Value |
|---|---|
| Model Family | distilbert |
| Module / Method | soa_module |
| Dataset | GLUE SST-2 (Binary) |
| Validation Status | PASS |
| Validation Accuracy | 89.22% |
| Pass Threshold (3*SE Margin) | 31.63% |
| F1 Score (Macro) | 0.8918 |
| F1 Score (Weighted) | 0.898 |
| Precision | 0.895 |
| Recall | 0.8914 |
| Validation Loss | 0.3687 |
| Compression Factor | 1.1107x |
| Peak GPU VRAM | 293.12 MB |
| Inference Throughput | 13809.54 tokens/sec |
| Evaluation Time | 23.12 s |
| Parameters (Before) | 66955010 |
| Parameters (After) | 60282626 |
| Compressed Layers | 0 |
| LoRA Trainable Params | 405504 |
| Benchmark Timestamp | 2026-09-15T23:43:06.660373 |
Architecture & Module Specification
The soa_module module is evaluated under the Hoosha AI NeuralOps SVD & Linear Attention Suite, benchmarking subquadratic attention and rank-adaptive tensor factorization against full quadratic baselines.
Framework & Verification
Developed and benchmarked using the SVD Linear Attention Framework — Universal GPU Benchmark Suite.
- Repository: tahamajs/SVD_linear_Attention
- Organization: Hooshaai
- Downloads last month
- -