developer_uid: rirv938
submission_id: blend_nibul_2025-04-14
model_name: rob_ab_test
model_group:
status: torndown
timestamp: 2025-04-14T18:35:28+00:00
num_battles: 5702
num_wins: 2932
celo_rating: 1296.72
family_friendly_score: 0.5524
family_friendly_standard_error: 0.007032129691636808
submission_type: blend
submissions: ['rirv938-0sw-96p-4ff-cha_93234_v1', 'rirv938-0sw-95p-5ff-rin_34350_v1', 'rirv938-ties-40k-2500-b_21634_v5', 'rirv938-anthropic-40k-2_43413_v8', 'zonemercy-lexical-vira_73487_v18', 'nischaydnk-exp14-exp9dp_94555_v3', 'rirv938-94p-6ff-rirv938-_8152_v1', 'rirv938-95p-5ff-rirv938-_6463_v1']
display_name: rob_ab_test
is_internal_developer: True
language_model: rirv938-0sw-96p-4ff-cha_93234_v1,rirv938-0sw-95p-5ff-rin_34350_v1,rirv938-ties-40k-2500-b_21634_v5,rirv938-anthropic-40k-2_43413_v8,zonemercy-lexical-vira_73487_v18,nischaydnk-exp14-exp9dp_94555_v3,rirv938-94p-6ff-rirv938-_8152_v1,rirv938-95p-5ff-rirv938-_6463_v1
model_size: n/a
ranking_group: blended
us_pacific_date: 2025-04-14
win_ratio: 0.5142055419151175
weights: {'rirv938-0sw-96p-4ff-cha_93234_v1': 1.0, 'rirv938-0sw-95p-5ff-rin_34350_v1': 1.0, 'rirv938-ties-40k-2500-b_21634_v5': 1.0, 'rirv938-anthropic-40k-2_43413_v8': 1.0, 'zonemercy-lexical-vira_73487_v18': 1.0, 'nischaydnk-exp14-exp9dp_94555_v3': 1.0, 'rirv938-94p-6ff-rirv938-_8152_v1': 1.0, 'rirv938-95p-5ff-rirv938-_6463_v1': 1.0}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.80s
Shutdown handler de-registered
blend_nibul_2025-04-14 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2932.73s
Shutdown handler de-registered
blend_nibul_2025-04-14 status is now inactive due to auto deactivation removed underperforming models
blend_nibul_2025-04-14 status is now torndown due to DeploymentManager action