Qwen2.5-Coder-14B SDS Policy Without Hypothesize, Seed 101

This is the frozen step-90 policy for seed 101 from the matched training-time prompt ablation in "Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers." The intervention removes exactly the Hypothesize instruction from the otherwise matched Hero configuration.

Public code commit: https://github.com/IDEALLab/neural-solver-synthesis/commit/07a798e7d7eca736cd1ef13a15209d402d401ef6

Final aggregate evidence and per-seed results: https://huggingface.co/datasets/IDEALLab/Neural-Solver-Synthesis-Final-Evidence-v1

Interpretation and limitations

At step 90, removing the instruction lowers seed-macro feasibility and worsens certified gap, with strong heterogeneity across seeds. Exploratory later checkpoints recover non-monotonically. The evidence therefore supports a sample-efficiency and stability interpretation, not inaccessible knowledge or universal prompt necessity. Only one prompt instruction is isolated.

files.sha256.json records SHA-256 hashes of every inference file uploaded from the frozen checkpoint. Optimizer, scheduler, RNG, and trainer state are excluded.

Downloads last month
23
Safetensors
Model size
15B params
Tensor type
BF16
·
Video Preview
loading

Model tree for IDEALLab/Qwen2.5-Coder-14B-Instruct-GRPO-SDS-NoHypothesize-step90-seed101

Base model

Qwen/Qwen2.5-14B
Finetuned
(131)
this model

Collection including IDEALLab/Qwen2.5-Coder-14B-Instruct-GRPO-SDS-NoHypothesize-step90-seed101