deepscaler-1p5b-soft-prompt-len16

DeepScaleR → 16-token soft prompt (negative result)

A 16-token soft prompt distilled from the frozen published RL checkpoint agentica-org/DeepScaleR-1.5B-Preview onto the frozen published base deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B.

No RL was run. The RL step was completed upstream by the Agentica team; this artifact only samples the frozen RL model and trains prompt embeddings on the frozen base.

This prompt does not recover the RL gain. It is published because the negative result, together with the measurements below, is the informative part.

Artifact

Result

Pooled AIME 2024+2025+2026 (90 questions, n=16, temperature 0.6, top_p 0.95, 32K, rm_hub.deepscaler grader, rllm system prompt):

recovery@1 = 3.12%, 95% CI [-25.53%, +24.79%] — indistinguishable from zero.

Why it fails, measured

The training objective was almost fully solved. Measured on 400 held-out teacher trajectories:

The prompt closed 95.2% of the achievable gap. So 16 tokens are not a capacity limitation — the objective itself is the problem. Base and teacher differ by only ~4 percentage points of next-token probability on the teacher's own correct trajectories. The RL gain lives in which trajectories get sampled, not in how a correct one is worded, and correct-only token-level imitation cannot express that.

The clearest symptom is length. RL made responses shorter (46,184 → 28,316 characters, truncation 17.8% → 2.4%); the prompt made them longer (58,462 characters, truncation 29.3%). RL's brevity comes from suppressing rambling incorrect trajectories — information that a correct-only snapshot has thrown away.

Contents

• prompt.safetensors — the step-100 prompt
• metrics.jsonl — per-step loss, gradient norm, token count
• nll_floor.json — the floor measurement above
• math_training_curve.png — loss against the measured floor

Training data: namezz/deepscaler-1p5b-teacher-rollouts