Execution attempt

Sign in with GitHub
← Experiment E1 · Where do small and strong models stand on ZendoBench 1.0.0 dev, and how do they play: how much information do their experiments gain, and how many rule classes are still alive when they submit?

Execution attempt · A7 · planned

E1 arm qwen3.5-4b-mlx: all 460 dev games, run per the accepted plan

Preflight failed · Registered by @stw2 via agent. Reported and received times are kept apart; no computation or result is verified.

Pinned source and configuration

https://github.com/stw2/zendo-lab @ 1a5465257d3325741ecf2a7abdfada884cfa5e49

Reference checked 2026-10-05 10:07 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
bash experiments/E01-dev-baseline/scripts/01_run.sh qwen3.5-4b-mlx
Working directory
.
Configuration paths
experiments/E01-dev-baseline/scripts/checkpoints/qwen3.5-2b.json experiments/E01-dev-baseline/scripts/daytona/serve.sh
Parameters
model=Qwen/Qwen3.5-4B@851bf6e8; backend=mlx batch driver, 36 games in flight, sampler seed 0, --checkpoint 4B; hardware=Apple M4 Max 128 GB; sampling=temperature 1.0, top_p 0.95, top_k 20, min_p 0, presence_penalty 1.5; thinking budget 63487 + answer allowance 2048; max_tokens=65536
Environment
macOS 26 on Apple M4 Max 128 GB; Python 3.13 via uv; ZendoBench 1.0.0 MLX batch driver; mlx 0.32.2, mlx-lm 0.31.3
Output directory
experiments/E01-dev-baseline/results/runs

Inputs

Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.

Delivered events

  1. Registered

    #1

    E1 arm qwen3.5-4b-mlx: all 460 dev games, run per the accepted plan

    reported · received · @stw2 via agent · posted to the Thread

  2. Preflight failed before launch

    #2

    Preflight failed at 10:07:39Z, before any game: ZendoBench refused the local Qwen3.5-4B checkpoint (CheckpointRefused: corrupt shard). Both cached shards of revision 851bf6e8 have the right sizes but SHA-256 values that match neither ZendoBench's pins nor the Hub's LFS hashes (which agree with each other). No run file was written. The shards are re-downloaded and the arm is rerun as a new attempt.

    Exit code 1. Duration 5 s. Error: zendo_bench.backends.mlx_adapter.CheckpointRefused: Corrupt shard, refusing to load: model.safetensors-00001-of-00002.safetensors

    reported · received · @stw2 via agent · posted to the Thread

Report an event

The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.

This attempt has a delivered outcome. A new execution is a new attempt.