You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Access requests are reviewed manually.
Log in or Sign Up to review the conditions and access this model content.
execution-midband-RL-v2
Canonical name execution-midband-RL-v2 in the execution-grounded RL series.
Historical run identity: execution-bank-RL-v2-think-r2 (W&B project
execution-bank-RL-v2-think). This is the complete preserved run tree.
Lineage
| Series name | Run identity | Adapter SHA-256 | Notes |
|---|---|---|---|
| Synth-v1 ep50 | iter_0000649 |
4acb7f23c295f45380155c5d9ee6bc59422262f0cb51f0c02f7e550d405b575a |
SFT starting point (checkpoints) |
| execution-midband-RL-v1 | issue111-bank-official-grpo20-20260817T151213Z |
186b0fc5b200fb8bb55bf85ee4416f2682a470580f0231c6f3f2a4d414bd898e |
bank drill, thinking off (archive) |
| execution-midband-RL-v2 (this repo) | execution-bank-RL-v2-think-r2 |
f5c298f5554c6f5fa4a27f3329e4a08c6c2fef76834c0f10147a270ede41148d |
bank drill, thinking on — lineage anchor |
Identity
- Base model: GLM-4.7-Flash, revision
7dd20894a642a0aa287e9827cb1a1f7f91386b67 - Cumulative LoRA rank 16 / alpha 32; serve as base + this adapter only — the adapter already contains the Synth-v1 SFT state (do not stack a second Synth-v1 adapter)
- Final checkpoint:
checkpoints/grpo_lora_r16/iter_0000019/adapter - Training: 20 GRPO updates, 8 exact-task bank-account drill prompts × 32 samples, thinking enabled, response budget 8192, LR 3e-5 (0.1 warmup), KL 0.1 against the frozen starting policy, strict binary execution reward (official GCC 13 oracle in Docker)
- Source commit:
7c70b963425d81ce1a3cd344524b87eb055c5852(tokenbender/browser-is-all-you-need-upstream, branchclient/5-aug-release)
Results
- Training environment pass rate: 33.59% → 55.08% over 20 updates (5,120 executed rollouts, zero infrastructure-invalid samples)
- Official bank-account, 64 independent one-shot samples: 60/64 = 93.75%
- Official fixed26, four trials × 26 tasks,
fixed26-contract-v2, tries=2, thinking enabled, temperature 0.7:- Pass@1: 11, 9, 10, 12 → mean 10.5/26 (40.38%)
- By turn 2: 14, 17, 12, 15 → mean 14.5/26 (55.77%)
- bank-account: 4/4 Pass@1
- Fixed26 evidence:
execution-bank-RL-v2-think-r2/fixed26-mt2-4x-20260818/in this repo (all 104 task receipts;summary.jsonSHA-256d324cccff759f33b64bcbb4176a584f53776bcb1c8a1165d935608220c15fcf7)
Contents
execution-bank-RL-v2-think-r2/— full run tree: checkpoints at updates 5/10/15/20 (native TP4 shards + HF adapters + finiteness receipts), rollout dumps, drill dataset, run logs, online-W&B local records, eval64 evidence, fixed26 four-trial evidence,run_status.txtlaunch-configs/— exact SkyPilot training and eval64 launch configurationsSHA256SUMS— digest of every file in this repo
External evidence
- W&B run: https://wandb.ai/ahm-rimer/execution-bank-RL-v2-think/runs/execution-bank-RL-v2-think-r2
- W&B artifact (GCS-reference bundle): https://wandb.ai/ahm-rimer/execution-bank-RL-v2-think/artifacts/run-bundle/execution-bank-RL-v2-think-r2/v0
- Issue ledger: https://github.com/tokenbender/browser-is-all-you-need/issues/111
Caveats
- The saved
training_state_rank*.ptfiles hold optimizer metadata and scheduler state only — no Adam moment tensors — so exact in-place resume is not possible; any continuation must warm-start from the adapter. - The fixed26 evaluation wrapper exited 141 after the completion marker and summary were written (post-completion log-pipe artifact); no trial was affected.
Model tree for TokenBender/execution-midband-RL-v2
Base model
zai-org/GLM-4.7-Flash