Modelpublic

Abhayn01/arka-advanced-slm-sft-v2-behavior

sourceHugging Faceapache-2.0updated 7d agoView on Hugging Face

0likes255downloads

Model Card

ARKA Advanced SLM — Behavior-First SFT v2

This checkpoint was fine-tuned from Abhayn01/arka-advanced-slm-scitech-stream-500m-v1 with a behavior-first supervised fine-tuning recipe.

Identity

—ARKA: Academic Research Knowledge Assistant
—Creator/developer: Abhay Kumar Rudrapaul
—Model family: ARKA Advanced SLM

Root fixes vs SFT v1

—one canonical User: / Assistant: format
—assistant-style dialogue is the largest source
—ARKA identity is explicitly weighted
—context/unanswerable QA is capped
—benchmark datasets are rendered as natural assistant answers
—prompt tokens are masked exactly and only completion tokens contribute to SFT loss
—dataset mixture is audited before training
—checkpoint behavior generation probes are stored alongside checkpoints

Training summary

json

{
  "total": 64818,
  "source_counts": {
    "sciq": 6000,
    "ultrachat": 32000,
    "mmlu": 8000,
    "electrical_anchor": 1800,
    "squad_answerable": 5000,
    "openbookqa": 4000,
    "arc_easy": 2200,
    "squad_unanswerable": 500,
    "counterfact": 1000,
    "arka_identity": 3200,
    "arc_challenge": 1118
  },
  "kind_counts": {
    "benchmark": 22318,
    "direct": 32000,
    "electrical": 1800,
    "context": 5000,
    "unanswerable": 500,
    "identity": 3200
  },
  "direct_assistant_ratio": 0.49369002437594495,
  "identity_ratio": 0.0493690024375945,
  "context_ratio": 0.08485297293961554,
  "unanswerable_ratio": 0.00771390663087414,
  "most_common_response": "i am arka academic research knowledge assistant",
  "most_common_response_count": 286,
  "most_common_response_ratio": 0.004412354592860008,
  "median_response_chars": 226,
  "p95_response_chars": 2026,
  "version": "2.0-universal-behavior-first",
  "base_model": "Abhayn01/arka-advanced-slm-scitech-stream-500m-v1",
  "output_repo": "Abhayn01/arka-advanced-slm-sft-v2-behavior",
  "train_examples": 63190,
  "validation_examples": 1628,
  "canonical_format": "User:\\n...\\n\\nAssistant:\\n...",
  "seed": 42,
  "mask_audit": {
    "samples": 64,
    "min_supervised_tokens": 10,
    "median_supervised_tokens": 66,
    "max_supervised_tokens": 384,
    "mean_sequence_tokens": 281.296875
  }
}

Canonical inference format

text

User:
What does ARKA stand for?

Assistant:

Do not use the failed SFT-v1 repository as the base for this run; this v2 recipe intentionally starts again from the pre-SFT science base.