LLM Training Dashboard - (AI-Augmented Software Engineering)

📂 Upload Training Data

Upload a .txt, .json, or .jsonl training file. JSON datasets can use records like {"instruction": "...", "output": "..."}.

📊 Training Data Analysis

✓ Ready to Train

Training will use:

⚙️ Training Configuration

Recommended resets the form to the dashboard baseline. Export saves the current dashboard settings as a versioned JSON config. Load applies a previously saved config back into the form and restores the referenced training file when available.

📊 Training Progress

🧬 Molecular Dataset Schema

Molecular dataset records should contain image and/or graph, a valid SMILES string, optional sequence, and at least one target property.

Periodic Table Element

Select element... Clear Selection

Pharmaceutical Base Compound

Select compound... Sync Pharma Library Fetch Live Data

Click image to enlarge

⚙️ Molecular Training Configuration

📊 Molecular Training Logs and Metrics

🔬 Molecular Inference

No prediction yet.

🚀 Distill to LLM

Convert your trained molecular model predictions into LLM training data, then fine-tune your selected base model for chemistry-aware language generation.

Pipeline output will appear here...

🧬 Gene Sequencing Training

A practical sequencing workspace for read QC, assembly, variants, embeddings, model jobs, RAG, and simulation.

🧪 Scientific Graph Dataset Schema

Supports molecules, materials, proteins, circuits, and 3D meshes via a unified graph + multimodal schema.

⚙️ Scientific Graph Training Configuration

📊 Scientific Graph Training Logs and Metrics

🔬 Scientific Graph Inference

No prediction yet.

🚀 Scientific Graph Distill to LLM

Convert your trained scientific graph model predictions into LLM training data, then optionally fine-tune the selected base model on the distilled dataset.

Pipeline output will appear here...

A. Model Selector

B. Dataset Upload Panel

Choose a model to see its supported dataset format.

C. Hyperparameter Panel

Training Actions

D. Training Monitor

🛰️ Phase-3 Vision Transformers and Small Transformers

Train Vision Transformer plus tiny causal LLaMA text models with image-folder or JSONL datasets, live telemetry, ONNX export, ONNX Runtime inference support, and GGUF/Ollama export for the Phase-3 text models.

Waiting to start deployment...

📝 Import Output

Model Coverage (transformer.py + backend/ml_models)

• Phase 1 ML/DL Models - CNN, MLP, and RNN training flows with CSV, JSONL, and image dataset support
• Custom Transformer Blocks - Attention, positional encoding, feed-forward layers, and decoder-oriented experiments
• Phase 2 Classical ML - Random Forest, SVM, and Logistic Regression registries with CSV schema inspection
• Phase 3 Models - Vision Transformer, MicroLLaMA, and MiniLLaMA workflows with optional ONNX export plus GGUF conversion for the text-model path
• Shared Dataset Pipeline - Built-in upload, sample-dataset generation, preview, validation, and run history flows

Training Workflows (finetune.py / finetune_mlx.py / backend/ml_models)

• Gradient Accumulation & MPS Safety - Automatic batch-size and sequence-length adjustments for constrained Apple Silicon memory
• LoRA / QLoRA Backends - PEFT plus bitsandbytes on CUDA and MLX-native quantized fine-tuning on Apple Silicon
• Resume, Validation & Scheduling - Cosine scheduling, gradient checkpointing, resume-from-checkpoint, and epoch validation samples
• Export Paths - SafeTensors, GGUF, ONNX, and artifact bundles for local deployment and comparison
• Telemetry & History - Training status, logs, history, and downloadable artifacts surfaced directly in the dashboard

LLM Training Dashboard progressively exposes the internal logic of large language models through twelve hierarchical layers, moving from high-level semantic geometry down to neuron-level concept discovery.

1. Embedding Galaxy - Constructs the top-level semantic space, mapping tokens into a unified representational geometry.
2. Brain Atlas - Defines the macro-architecture of the model, showing how major regions such as attention, MLP, and embedding blocks interconnect.
3. Tensor Microarchitecture - Visualizes tensor statistics and heatmaps for fine-grained inspection of weight distributions and activation patterns.
4. Head-Aware Q/K/V Decomposition - Separates attention heads to analyze norms, sparsity, and per-head behavior.
5. Activation-Path Visualization - Traces query, key, and value activations through attention weights to reveal how information flows within a layer.
6. Multi-Head Interaction Map - Examines horizontal structure through head-to-head similarity, clustering, redundancy, and specialization, including syntax, induction, and negation heads.
7. Layer-to-Layer Activation Flow - Explores vertical structure by showing how outputs propagate across layers to form emergent circuits and conceptual hierarchies.
8. MLP Neuron Concept Discovery - Discovers concept neurons and feature detectors in MLP layers that respond to interpretable patterns such as numbers, names, and emotions.
9. Feature-Space Geometry - Visualizes principal components, concept directions, neuron clusters, and subspaces for specific behaviors.
10. Time Drift Visualisation - Tracks how embeddings, attention patterns, and neuron behaviours shift across checkpoints to reveal when representations diverge or capabilities emerge.
11. Gradient Flow & Influence Maps - Reveals why a model chose its output by tracing token‑level gradients, attribution signals, and causal influence pathways.
12. Mechanistic Circuits & Subgraph Extraction - A multi‑level framework that reveals how transformer models represent, transform, and reason through their internal mechanisms.

Data Pipeline: CSV / JSONL / image-folder input → preview and validation → dataset builders → training loaders

Training Loop: Phase-1 deep learning loops / Phase-2 classical fit / Phase-3 transformer fine-tuning → telemetry → checkpoints and artifacts

Model Export: SafeTensors / .pkl / ONNX / GGUF → Ollama / ONNX Runtime / local artifact downloads

Dashboard: Flask API ↔ Phase-1/2/3 controls ↔ real-time updates ↔ 3D visualizations ↔ system monitoring