developer_uid: azuruce
submission_id: blend_medub_2025-02-25
model_name: baseline
model_group:
status: torndown
timestamp: 2025-02-25T20:01:12+00:00
num_battles: 5175
num_wins: 2614
celo_rating: 1273.53
family_friendly_score: 0.5602
family_friendly_standard_error: 0.007019629050028214
submission_type: blend
submissions: ['chaiml-snugstable1-5-1_59274_v21', 'nitral-ai-captain-bmo-12b_v28', 'rinen0721-dpo-0130-cp3000_v8', 'rirv938-anthropic-40k-2_43413_v8', 'rirv938-mistral-24b-40k_43012_v2', 'rirv938-ties-40k-2500-b_21634_v5', 'zonemercy-lexical-vira_73487_v18', 'alexxi19-ft-v1-nemo-ba_27407_v19']
display_name: baseline
is_internal_developer: False
language_model: chaiml-snugstable1-5-1_59274_v21,nitral-ai-captain-bmo-12b_v28,rinen0721-dpo-0130-cp3000_v8,rirv938-anthropic-40k-2_43413_v8,rirv938-mistral-24b-40k_43012_v2,rirv938-ties-40k-2500-b_21634_v5,zonemercy-lexical-vira_73487_v18,alexxi19-ft-v1-nemo-ba_27407_v19
model_size: n/a
ranking_group: blended
us_pacific_date: 2025-02-25
win_ratio: 0.5051207729468599
weights: {'chaiml-snugstable1-5-1_59274_v21': 1.0, 'nitral-ai-captain-bmo-12b_v28': 1.0, 'rinen0721-dpo-0130-cp3000_v8': 1.0, 'rirv938-anthropic-40k-2_43413_v8': 1.0, 'rirv938-mistral-24b-40k_43012_v2': 1.0, 'rirv938-ties-40k-2500-b_21634_v5': 1.0, 'zonemercy-lexical-vira_73487_v18': 1.0, 'alexxi19-ft-v1-nemo-ba_27407_v19': 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 0.62s
Shutdown handler de-registered
blend_medub_2025-02-25 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 2575.57s
Shutdown handler de-registered
blend_medub_2025-02-25 status is now inactive due to auto deactivation removed underperforming models
blend_medub_2025-02-25 status is now torndown due to DeploymentManager action