Spaces:

SupraLabs
/

Research-SupraLabs

Running

App Files Files Community

LH-Tech-AI commited on 14 days ago

Commit

3a2a696

verified ·

1 Parent(s): 2b06042

Create curriculum.html

Browse files

Files changed (1) hide show

curriculum.html +315 -0

curriculum.html ADDED Viewed

	@@ -0,0 +1,315 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>SupraLabs | Information Routing: Dynamic Curriculum Shifting</title>
+    <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+    <style>
+        :root {
+            --bg: #0f0f0f;
+            --surface: #1a1a1a;
+            --border: #333;
+            --text: #e0e0e0;
+            --accent: #536bfe; /* Supra Blue */
+            --muted: #888;
+            --success: #00e676;
+            --warning: #ffb300;
+            --font-mono: 'JetBrains Mono', 'Fira Code', monospace;
+        }
+        * { margin: 0; padding: 0; box-sizing: border-box; }
+        body {
+            background-color: var(--bg);
+            color: var(--text);
+            font-family: 'Inter', -apple-system, sans-serif;
+            line-height: 1.6;
+            padding: 2rem;
+        }
+        code, pre, .mono { font-family: var(--font-mono); }
+        .container { max-width: 1000px; margin: 0 auto; }
+        header {
+            border-bottom: 2px solid var(--border);
+            padding-bottom: 2rem;
+            margin-bottom: 3rem;
+            display: flex;
+            justify-content: space-between;
+            align-items: flex-end;
+        }
+        .logo-area a { text-decoration: none; color: inherit; }
+        .logo-area h1 {
+            font-size: 1.2rem;
+            text-transform: uppercase;
+            letter-spacing: 2px;
+            color: var(--accent);
+            line-height: 1;
+            display: flex;
+            align-items: center;
+            gap: 10px;
+        }
+        nav a {
+            color: var(--text);
+            text-decoration: none;
+            margin-left: 1.5rem;
+            font-size: 0.9rem;
+            border-bottom: 1px solid transparent;
+        }
+        nav a:hover { border-bottom: 1px solid var(--accent); }
+        .hero { margin-bottom: 4rem; }
+        .hero h2 { font-size: 3rem; line-height: 1.1; margin-bottom: 1.5rem; font-weight: 800; }
+        .hero p { font-size: 1.2rem; color: var(--muted); max-width: 750px; }
+        .section-label {
+            display: block;
+            font-family: var(--font-mono);
+            color: var(--accent);
+            font-size: 0.8rem;
+            margin-top: 3rem;
+            margin-bottom: 1rem;
+            text-transform: uppercase;
+        }
+        .card { background: var(--surface); border: 1px solid var(--border); padding: 2.5rem; margin-bottom: 2rem; }
+        h3 { font-size: 1.6rem; margin-bottom: 1rem; font-weight: 700; }
+        p { margin-bottom: 1rem; color: #ccc; }
+        ul { margin-left: 1.5rem; margin-bottom: 1.5rem; }
+        li { margin-bottom: 0.5rem; }
+        .winner-badge { color: var(--success); font-weight: bold; font-family: var(--font-mono); }
+        .table-container { overflow-x: auto; margin: 2rem 0; border: 1px solid var(--border); }
+        table { width: 100%; border-collapse: collapse; text-align: left; font-size: 0.95rem; }
+        th, td { padding: 1rem; border-bottom: 1px solid var(--border); }
+        th { background-color: rgba(26, 26, 26, 0.8); font-family: var(--font-mono); color: var(--accent); font-size: 0.85rem; text-transform: uppercase; }
+        tr:hover { background-color: rgba(83, 107, 254, 0.05); }
+        .highlight-row { border-left: 4px solid var(--success); background-color: rgba(0, 230, 118, 0.02); }
+        .chart-box { background: var(--surface); border: 1px solid var(--border); padding: 2rem; margin-bottom: 2rem; }
+        .stats-grid {
+            display: grid;
+            grid-template-columns: 1fr 1fr 1fr;
+            gap: 1rem;
+            margin-top: 4rem;
+            border-top: 1px solid var(--border);
+            padding-top: 2rem;
+        }
+        .stat-box { padding: 1rem; border-left: 2px solid var(--accent); }
+        .stat-box small { display: block; color: var(--muted); font-family: var(--font-mono); }
+        footer { margin-top: 6rem; padding-bottom: 2rem; font-size: 0.8rem; color: var(--muted); text-align: center; }
+        @media (max-width: 768px) {
+            .hero h2 { font-size: 2rem; }
+            header { flex-direction: column; align-items: flex-start; gap: 1rem; }
+            nav a { margin-left: 0; margin-right: 1rem; }
+            .stats-grid { grid-template-columns: 1fr; }
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <header>
+            <div class="logo-area" style="font-size: 1.5em;">
+                <a href="index.html"><h1><img src="./image.png" style="height: 2em" alt="Logo"> SupraLabs_</h1></a>
+            </div>
+            <nav>
+                <a href="#summary">Core Learnings</a>
+                <a href="#benchmarks">Routing Matrix</a>
+                <a href="#charts">Visualizations</a>
+                <a href="https://huggingface.co/SupraLabs" target="_blank">HuggingFace</a>
+            </nav>
+        </header>
+        <section class="hero">
+            <h2>Experiment #7:<br>Information Routing &mdash; Curriculum Shifting</h2>
+            <p>An empirical evaluation of structured knowledge injection schedules inside parameter-constrained spaces. We subjected a optimized <strong>4,196,096 parameter architecture</strong> to a rigid budget of <strong>200,000,000 total tokens</strong> to test multi-distribution blending against raw uniform pooling.</p>
+        </section>
+        <span class="section-label" id="summary">// Syntactic_Preservation_&_Memory_Retainment</span>
+        <div class="card">
+            <h3>Curing Catastrophic Forgetting via Shifting Weights</h3>
+            <p>When training extremely compact language models, data sequencing determines memory stabilization boundaries. Our comparative routing sweep demonstrates that standard dataset pooling bottlenecks the structural capability of micro-networks:</p>
+            <ul>
+                <li><strong>The Failure of Rigid Sequential Partitioning:</strong> Processing data in unblended sequential stages (Hard Blocks) triggers devastating memory overwrites. As the training block moves from base syntax to intense facts, the network suffers a 39% language accuracy collapse (Wikitext PPL: 632.9).</li>
+                <li><strong>The Naive Pooling Limitation:</strong> Shoving all token distributions into a single, uniform mix from the start (Baseline) forces the small weights matrix to stabilize multiple contradictory targets simultaneously, degrading the final linguistic resolution (PPL: 556.7).</li>
+                <li><strong>The Shifting Weight Solution:</strong> Launching with structured syntax (TinyStories/Cosmo), moving into reasoning (Math), and finalizing with facts while preserving a mathematical logic holding current protects the weight paths. Language Perplexity drops cleanly to <strong>453.6</strong>.</li>
+            </ul>
+        </div>
+        <span class="section-label" id="benchmarks">// Knowledge_Injection_Routing_Matrix</span>
+        <div class="card" style="padding: 1.5rem;">
+            <h3>Empirical Scheduling Analytics</h3>
+            <p>All training pipelines utilize an identical 4096 vocabulary architecture. Downstream tracking processed zero-shot. Deceptive optimization targets (apparent pretrain loss) are directly falsified by true language modeling benchmarks.</p>
+            <div class="table-container">
+                <table>
+                    <thead>
+                        <tr>
+                            <th>Benchmark / Metric</th>
+                            <th style="color: var(--success)">Run 1: Shifting Weights (🏆 Win)</th>
+                            <th>Run 2: Hard Sequential Blocks</th>
+                            <th>Run 3: Uniform Baseline Mix</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                        <tr>
+                            <td class="mono">Routing Architecture</td>
+                            <td style="color: var(--success)">Dynamic Weight Stepper</td>
+                            <td>Static Linear Switches</td>
+                            <td>Star Blend Pooling</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">Final Pretrain Step Loss (↓)</td>
+                            <td>2.770</td>
+                            <td class="winner-badge">2.458</td>
+                            <td>2.690</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">Final Pretrain Train Loss (↓)</td>
+                            <td>3.151</td>
+                            <td class="winner-badge">2.817</td>
+                            <td>3.114</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">ARC-Easy Zero-Shot (↑)</td>
+                            <td>29.71%</td>
+                            <td class="winner-badge">30.22%</td>
+                            <td>30.18%</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">ARC-Easy Acc Norm (↑)</td>
+                            <td>30.26%</td>
+                            <td class="winner-badge">30.64%</td>
+                            <td>30.47%</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">Wikitext Byte PPL (↓)</td>
+                            <td class="winner-badge">3.1392</td>
+                            <td>3.3410</td>
+                            <td>3.2618</td>
+                        </tr>
+                        <tr>
+                            <td class="mono">Wikitext Word PPL (↓)</td>
+                            <td class="winner-badge" style="color: var(--success); font-weight: bold;">453.6715</td>
+                            <td>632.9729</td>
+                            <td>556.7454</td>
+                        </tr>
+                        <tr class="highlight-row">
+                            <td style="font-weight: bold;">PRETRAIN COHERENCE</td>
+                            <td style="color: var(--success); font-weight: bold;">SOTA BALANCE ARCHIEVED</td>
+                            <td style="color: var(--warning)">Severe Memory Corruption</td>
+                            <td>Information Dilution</td>
+                        </tr>
+                    </tbody>
+                </table>
+            </div>
+        </div>
+        <span class="section-label" id="charts">// Visualizing_Routing_Mechanics</span>
+        <div class="chart-box">
+            <h3>Linguistic Perplexity Splintering Across Routing Approaches</h3>
+            <div style="position: relative; height:350px; width:100%">
+                <canvas id="curriculumPplChart"></canvas>
+            </div>
+        </div>
+        <div class="chart-box">
+            <h3>The Apparent Loss Paradox: Pretrain Loss vs. True Structural Perplexity</h3>
+            <p style="font-size: 0.85rem; color: var(--muted); margin-bottom: 1.5rem;">Critical discovery: Rigid data blocking pushes the localized training loss down artificially, but causes severe out-of-distribution language collapse on core evaluation matrices.</p>
+            <div style="position: relative; height:350px; width:100%">
+                <canvas id="curriculumParadoxChart"></canvas>
+            </div>
+        </div>
+        <section class="stats-grid" id="hardware">
+            <div class="stat-box">
+                <small>TOTAL COMPUTE EXPOSURE</small>
+                <strong>200M Unified Steps</strong>
+            </div>
+            <div class="stat-box">
+                <small>MODEL GEOMETRY PROFILE</small>
+                <strong>3-Layer Shallow Wide SOTA</strong>
+            </div>
+            <div class="stat-box">
+                <small>SCHEDULING RESOLUTION</small>
+                <strong>4096 Vocab Pareto Bound</strong>
+            </div>
+        </section>
+        <footer>
+            <p>&copy; 2026 SupraLabs. High performance. Small footprints. Proudly open-source.</p>
+        </footer>
+    </div>
+    <script>
+        // Curriculum Perplexity Chart
+        const ctxCurrPpl = document.getElementById('curriculumPplChart').getContext('2d');
+        new Chart(ctxCurrPpl, {
+            type: 'bar',
+            data: {
+                labels: ['Run 1: Dynamic Shifting Weights', 'Run 2: Hard Blocks', 'Run 3: Uniform Baseline Mix'],
+                datasets: [{
+                    label: 'Wikitext Word Perplexity (Lower = Better)',
+                    data: [453.67, 632.97, 556.74],
+                    backgroundColor: ['rgba(0, 230, 118, 0.3)', 'rgba(229, 57, 53, 0.2)', 'rgba(255, 179, 0, 0.2)'],
+                    borderColor: ['#00e676', '#e53935', '#ffb300'],
+                    borderWidth: 2
+                }]
+            },
+            options: {
+                responsive: true,
+                maintainAspectRatio: false,
+                plugins: { legend: { labels: { color: '#bbb' } } },
+                scales: {
+                    y: { grid: { color: '#222' }, ticks: { color: '#888' } },
+                    x: { grid: { display: false }, ticks: { color: '#aaa' } }
+                }
+            }
+        });
+        // Paradox Dual Axis Curve
+        const ctxCurrParadox = document.getElementById('curriculumParadoxChart').getContext('2d');
+        new Chart(ctxCurrParadox, {
+            type: 'line',
+            data: {
+                labels: ['Dynamic Shifting', 'Hard Sequential Blocks', 'Uniform Baseline Mix'],
+                datasets: [
+                    {
+                        label: 'Apparent Pretrain Train Loss (Lower = Deceptive ↓)',
+                        data: [3.151, 2.817, 3.114],
+                        borderColor: 'rgba(229, 57, 53, 0.5)',
+                        backgroundColor: 'transparent',
+                        yAxisID: 'yLoss',
+                        tension: 0.1,
+                        borderWidth: 2
+                    },
+                    {
+                        label: 'True Linguistic Word Perplexity (Lower = Superior ↑)',
+                        data: [453.67, 632.97, 556.74],
+                        borderColor: '#536bfe',
+                        backgroundColor: 'transparent',
+                        yAxisID: 'yPpl',
+                        tension: 0.1,
+                        borderWidth: 3,
+                        borderDash: [3, 3]
+                    }
+                ]
+            },
+            options: {
+                responsive: true,
+                maintainAspectRatio: false,
+                plugins: { legend: { labels: { color: '#bbb' } } },
+                scales: {
+                    x: { grid: { display: false }, ticks: { color: '#aaa' } },
+                    yLoss: {
+                        type: 'linear',
+                        position: 'left',
+                        title: { display: true, text: 'Pretrain Loss Baseline', color: 'rgba(229, 57, 53, 0.8)' },
+                        grid: { color: '#222' },
+                        ticks: { color: '#888' }
+                    },
+                    yPpl: {
+                        type: 'linear',
+                        position: 'right',
+                        title: { display: true, text: 'Linguistic Word Perplexity', color: '#536bfe' },
+                        grid: { display: false },
+                        ticks: { color: '#888' }
+                    }
+                }
+            }
+        });
+    </script>
+</body>
+</html>