MoS-27B-Checkpoints

Epoch checkpoints of the Qwen3.8-27B DFlash2 MoS line (project MoS, branch ryan/mos-improve, experiments/dflash2/qwen3.8-27b-100k/). Started 2026-09-22, when the general archive repo ryan-0608/MoS-Aurora-Experiment-Archive reached the Hugging Face 20,000-file limit.

Layout

dflash2_27b_traj_20260915/main-800k/<arm>/epoch<N>/
    model.safetensors            drafter weights (speculators DFlash2MoSDraftModel)
    optimizer_state_dict.pt      full AdamW state -> exact resume
    scheduler_state_dict.pt, training_state.json, config.json, config.py, train_command.txt
    val_metrics.json             trainer held-out 10% validation at the end of the epoch
    serving/                     fixed-500 serving result for this checkpoint
        acceptance_summary.json  pooled AL = sum completion tokens / sum verify calls
        acceptance_trace.jsonl   per-request counts
        client.log, server.log

Arms

arm (path)	Ryan's name	recipe
dense4	27B dense (4-epoch baseline)	dense drafter warm-started from z-lab/Qwen3.8-27B-DFlash2 @50307d4c; base LR 1e-4; cosine over 4 epochs, warmup 0.005; same corpus, 3 verifier + 5 trainer layout, global batch and 73,670 steps per epoch as x4rand; training (started 2026-09-25)
x4rand	27B 4expert rand LR6	K=4 full-width expert MLPs per draft layer, random init (gate/up N(0,0.02), down N(0,1e-3)); shared MLP, attention and the rest warm-started from z-lab/Qwen3.8-27B-DFlash2 @50307d4c; base LR 1e-4, expert LR 6e-4, router LR 5e-4; top-2, tau 0.9, balance 0.01; cosine over 4 epochs, warmup 0.005; corpus Current-800K-Self-27B-Traj (719,455 train rows); 73,670 steps per epoch

Results (target Qwen/Qwen3.8-27B @1d4bf0f2)

Serving protocol: sglang main f5866545, TP2, DFLASH 16 draft tokens, fixed-500 prompts, max 128 new tokens, greedy, concurrency 1, 500/500 completed. Same protocol as the dense and K4-jitter references.

arm	epoch	global_step	train-side val AL	serving pooled AL	vs dense same epoch
dense4	1	73,670	5.0262	5.0571	—
dense4	2	147,335	5.0261	5.0510	—
dense4	3	221,001	5.026 (from train.log)	5.0558	—
x4rand	1	73,670	5.1485	5.2314	+3.45% (dense4 5.0571)
x4rand	2	147,335	5.2056	5.2922	+4.78% (dense4 5.0510)
x4rand	3	221,001	5.2202	5.3261	+5.34% (dense4 5.0558)
x4rand	4	294,682	5.2201	5.3113	+5.17% vs dense E2 5.0502; best epoch = 3

Reference arms (model-only, no optimizer) are in ryan-0608/MoS-Aurora-Experiment-Archive under dflash2_27b_traj_20260915/main-800k/: dense/epoch1, dense/epoch2, mos/epoch1 (K4 shared+1% jitter, expert LR 1e-4; serving 5.1501, +1.83%).

Use

Resume training: pass the epoch directory as the checkpoint dir to speculators train.py (same train_command.txt, --epochs 4). Serve: export_d2_for_sglang.py <epoch dir> <out> then sglang --speculative-algorithm DFLASH --speculative-draft-model-path <out>; the MoS architecture needs apply_serving_dflash2_mos.py on sglang main.