返回

📊 pokemon-tcg-ai-battle

Best win_rate: 0.8478   Best LB: 838.1   Experiments: 165 including running (✓10 ✗26)
GPU: 30.0h
ExpVersionwin_rate LBStatusLinkConsole
exp_0258v10.0—eval_staging_failed🔗
exp_0257v10.0—eval_staging_failed🔗
exp_0256v10.4953—gate_rejected🔗
exp_0255v10.0—eval_staging_failed🔗
exp_0254v10.0—eval_staging_failed🔗
exp_0253v10.0—evaluation_protocol_invalid🔗
exp_0252v10.479—no_divergence_skip🔗
exp_0251v—0.0—idea_proposal_failed—
exp_0250v10.4993—gate_rejected🔗
exp_0249v10.4944—gate_rejected🔗
exp_0248v10.0—gate_rejected🔗
exp_0247v10.0—gate_rejected🔗
exp_0246v10.0—gate_rejected🔗
exp_0245v10.0—gate_rejected🔗
exp_0244v10.4638—gate_rejected🔗
exp_0243v10.0—eval_staging_failed🔗
exp_0242v10.0—gate_rejected🔗
exp_0241v10.0—gate_rejected🔗
exp_0240v10.0—local_promoted_no_submit🔗
exp_0239v—0.0—idea_proposal_failed—
exp_0238v—0.0—failed—
exp_0237v—0.0—idea_proposal_failed—
exp_0236v10.0—capability_discovery_complete🔗
exp_0235v—0.0—failed—
exp_0234v10.0—capability_discovery_complete🔗
exp_0233v10.0—capability_discovery_source_claim_falsified🔗
exp_0232v10.0—build_error🔗
exp_0231v———snapshotting—
exp_0230v———snapshotting—
exp_0229v—0.0—idea_proposal_failed—
exp_0228v—0.0—idea_proposal_failed—
exp_0227v—0.0—failed—
exp_0226v—0.0—capability_discovery_inconclusive—
exp_0225v—0.0—provider_quota—
exp_0224v—0.0—provider_quota—
exp_0223v—0.0—capability_discovery_inconclusive—
exp_0222v10.0—capability_discovery_source_claim_falsified🔗
exp_0221v10.0—capability_discovery_source_claim_falsified🔗
exp_0220v10.0—capability_discovery_source_claim_falsified🔗
exp_0219v—0.0—idea_proposal_failed—
exp_0218v—0.0—static_prescreen_source_claim_falsified—
exp_0217v10.0—capability_discovery_inconclusive🔗
exp_0216v—0.0—static_prescreen_source_claim_falsified—
exp_0215v10.0—capability_discovery_execution_failed🔗
exp_0214v—0.0—static_prescreen_source_claim_falsified—
exp_0213v10.0—capability_discovery_execution_failed🔗
exp_0212v10.0—capability_discovery_falsified🔗
exp_0211v10.0—capability_discovery_falsified🔗
exp_0210v10.0—build_error🔗
exp_0209v—0.0—capability_discovery_inconclusive—
exp_0208v10.0—capability_discovery_inconclusive🔗
exp_0207v10.0—capability_discovery_falsified🔗
exp_0206v10.0—capability_discovery_inconclusive🔗
exp_0205v10.0—capability_discovery_falsified🔗
exp_0204v10.0—no_change_precheck🔗
exp_0203v10.0—no_change_precheck🔗
exp_0202v—0.0—provider_quota—
exp_0201v—0.0—provider_quota—
exp_0200v10.0—build_error🔗
exp_0199v10.0—capability_discovery_complete🔗
exp_0198v10.514—no_divergence_skip🔗
exp_0197v—0.0—provider_quota—
exp_0196v10.46—no_divergence_skip🔗
exp_0195v10.514—targeted_evidence_missing🔗
exp_0194v10.4947—targeted_evidence_missing🔗
exp_0193v10.055—gate_rejected🔗
exp_0192v—0.0—provider_quota—
exp_0191v10.0—error🔗
exp_0190v10.0—capability_discovery_complete🔗
exp_0189v10.0—capability_discovery_inconclusive🔗
exp_0188v10.0—artifact_validation_failed🔗
exp_0187v—0.0—provider_quota—
exp_0186v10.0—build_error🔗
exp_0185v10.3269—no_divergence_skip🔗
exp_0184v10.4978—gate_rejected🔗
exp_0183v—0.0—failed—
exp_0182v———failed—
exp_0181v10.4219—gate_rejected🔗
exp_0180v10.4052—gate_rejected🔗
exp_0179v10.501—gate_rejected🔗
exp_0178v10.4048—no_divergence_skip🔗
exp_0177v—0.0—failed—
exp_0176v10.3966—gate_rejected🔗
exp_0175v10.4778—no_divergence_skip🔗
exp_0174v10.515—no_divergence_skip🔗
exp_0173v—0.0—failed—
exp_0172v10.6385—smoke_passed_no_promote🔗
exp_0171v—0.0—failed—
exp_0170v10.7024—🔗
exp_0169v—0.0—failed—
exp_0168v—0.0—failed—
exp_0167v23——complete🔗
exp_0166v22——complete🔗
exp_0165v21——error🔗
exp_0164v—0.0—provider_quota—
exp_0163v10.4368—gate_rejected🔗
exp_0162-reeval-1v10.527—gate_rejected🔗
exp_0162v10.7656517.5🔗
exp_0161v10.7656472.1🔗
exp_0160v—0.0—idea_proposal_failed—
exp_0159v—0.0—idea_proposal_failed—
exp_0158v—0.0—idea_proposal_failed—
exp_0157v—0.0—idea_proposal_failed—
exp_0156v—0.0—idea_proposal_failed—
exp_0155v—0.0—idea_proposal_failed—
exp_0154v—0.0—idea_proposal_failed—
exp_0153v—0.0—idea_proposal_failed—
exp_0152v—0.0—idea_proposal_failed—
exp_0151v—0.0—idea_proposal_failed—
exp_0150v—0.0—idea_proposal_failed—
exp_0149v—0.0—idea_proposal_failed—
exp_0148v—0.0—idea_proposal_failed—
exp_0147v—0.0—idea_proposal_failed—
exp_0146v—0.0—idea_proposal_failed—
exp_0145v—0.0—idea_proposal_failed—
exp_0144v—0.0—idea_proposal_failed—
exp_0143v—0.0—idea_proposal_failed—
exp_0142v—0.0—idea_proposal_failed—
exp_0141v—0.0—idea_proposal_failed—
exp_0140v—0.0—idea_proposal_failed—
exp_0139v—0.0—idea_proposal_failed—
exp_0138v—0.0—idea_proposal_failed—
exp_0137v—0.0—idea_proposal_failed—
exp_0136v—0.0—idea_proposal_failed—
exp_0135v—0.0—idea_proposal_failed—
exp_0134v—0.0—idea_proposal_failed—
exp_0133v—0.0—idea_proposal_failed—
exp_0132v—0.0—idea_proposal_failed—
exp_0131v10.6765535.8🔗
exp_0130v—0.0—idea_proposal_failed—
exp_0129v—0.0—idea_proposal_failed—
exp_0128v—0.0—idea_proposal_failed—
exp_0127v—0.0—idea_proposal_failed—
exp_0126v—0.0—idea_proposal_failed—
exp_0125v—0.0—idea_proposal_failed—
exp_0124v—0.0—idea_proposal_failed—
exp_0123v—0.0—idea_proposal_failed—
exp_0122v—0.0—idea_proposal_failed—
exp_0121v—0.0—idea_proposal_failed—
exp_0120v—0.0—idea_proposal_failed—
exp_0119v—0.0—idea_proposal_failed—
exp_0118v—0.0—idea_proposal_failed—
exp_0117v—0.0—idea_proposal_failed—
exp_0116v—0.0—idea_proposal_failed—
exp_0115v—0.0—idea_proposal_failed—
exp_0114v10.7024533.3🔗
exp_0113-reeval-1v10.4876—gate_rejected🔗
exp_0113v10.6875—challenger_pending🔗
exp_0112-reeval-1v10.4609—gate_rejected🔗
exp_0112v10.6338—challenger_pending🔗
exp_0111v10.8478523.3🔗
exp_0110-reeval-1v10.5—gate_rejected🔗
exp_0110v10.6977—challenger_pending🔗
exp_0109v10.6837475.4🔗
exp_0108-reeval-1v10.5016—gate_rejected🔗
exp_0108v10.7429—challenger_pending🔗
exp_0107v10.7179551.2🔗
exp_0106v—0.0—timeout—
exp_0105v—0.0—idea_proposal_failed—
exp_0104v10.4659—gate_rejected🔗
exp_0103v10.451—gate_rejected🔗
exp_0102v—0.0—cancelled—
exp_0101v—0.0—timeout—
exp_0100v10.4375—gate_rejected🔗
exp_0099v10.4893—gate_rejected🔗
165 experiments from exp_0099, including running work (newest first)

win_rate = vs champion (moving target, not cross-round comparable)