Run dir: [v2_runs]/selfhost_qwen36_23_BetV1_20260424_113757_7323365
| target | program/profile | gen | n_successful | rank_key | best_i_pae | best_plddt | description |
|---|---|---|---|---|---|---|---|
| 23_BetV1 | 29cf0ab15f10 | 3 | 0 | Increase beam_width from 8 to 12 in stage 0 for broader early diversity, reduce nsteps to 200 with matching step_checkpoints to halve per-candidate compute in stage 0, and appen... | |||
| 23_BetV1 | 2c4892e6bfa0 | 4 | Increase stage 0 refinement depth to n_temp=80/n_hard=12, switch refine_targets to all, and add plddt=0.5 reward weight to boost confidence and interface sharpness. | ||||
| 23_BetV1 | 3efdc1348845 | 2 | 0 | 0.32439148 | 0.9182643 | Switch from beam-search to MCTS (n_simulations=50) to leverage the paper's finding that MCTS excels on harder targets, and increase sampling.nsteps from 400 to 600 with matching... | |
| 23_BetV1 | 4213fe45aa1a | 2 | 0 | Increase beam_width from 8 to 12 for broader diversity, increase sampling.nsteps from 400 to 600 for more thorough exploration, align step_checkpoints with new nsteps, and reduc... | |||
| 23_BetV1 | 54e0a7d9fe12 | 3 | 0 | Reducing stage 0 nsteps to 200 and step_checkpoints to match, increasing beam_width to 12 and nsamples to 10 for diversity in cheap exploration, and appending a conditional thir... | |||
| 23_BetV1 | 635c3ca770c7 | 2 | 0 | 0.29303965 | 0.9283373 | Append a second stage conditioned on n_successful>=2; stage 0 reduces beam_width to 4 for more diversity (nsamples=16, nsteps=200), stage 1 deepens refinement (nsamples=8, nstep... | |
| 23_BetV1 | 6d9e1a413d6c | 3 | 0 | Increase beam_width to 12 and nsteps to 600 in stage 0 for broader, higher-quality exploration (with matching step_checkpoints), while raising greedy and temperature iterations ... | |||
| 23_BetV1 | 6dbea9c49eab | 0 | 0 | 0.28482148 | 0.9414049 | seed (balanced baseline) | |
| 23_BetV1 | 74a1d2070875 | 4 | 15 | 0.16020261 | 0.9444216 | Further strengthen stage 2 refinement by increasing n_temp_iters from 60 to 70 and n_hard_iters from 8 to 10, plus switching the stage 2 condition from n_successful >= 2 to a qu... | |
| 23_BetV1 | 761f1bafefd3 | 3 | 8 | 0.18390425 | 0.95171094 | Increase stage 0 beam_width to 16 for broader exploration (batch_size=2 keeps memory at 16×8×2=256), increase stage 1 nsteps to 600 with matching step_checkpoints and n_temp_ite... | |
| 23_BetV1 | 783ccca607e9 | 1 | 0 | Add i_ptm (+0.5) and i_con (+1.0) reward weights from BindCraft's filtering criteria and increase i_pae penalty from -1.0 to -2.0 to push harder on interface accuracy, plus wide... | |||
| 23_BetV1 | 91062ca806d4 | 3 | 0 | Increase beam_width from 8 to 12 and nsamples from 8 to 10 in stage 0 for broader early diversity, halve nsteps from 400 to 200 for cheaper per-sample exploration (12×10×4=480 ≤... | |||
| 23_BetV1 | c20523dd958f | 3 | 18 | 0.1598706 | 0.94889796 | Strengthen refinement by increasing n_temp_iters from 45 to 60 and n_hard_iters from 5 to 8, plus boosting i_pae loss weight from 0.1 to 0.3 to align with the strong -2.0 i_pae ... | |
| 23_BetV1 | caac57428874 | 1 | 6 | 0.14874282 | 0.9489059 | Strengthen i_pae penalty to -2.0 and add contact/interface-contact reward terms (con=0.5, i_con=0.5) to guide interface formation, while enabling sequence_hallucination refineme... | |
| 23_BetV1 | fac00cffd93a | 2 | 11 | 0.1598745 | 0.93689823 | Increase nsamples from 4 to 8 for broader exploration (doubling candidates), halve batch_size from 8 to 4 to keep memory at 8×8×4=256, and append a second refinement stage (clon... |
Generated 2026-04-25