developer_uid: rirv938
submission_id: blend_simun_2025-07-09
model_name: rob_ab_test
model_group:
status: torndown
timestamp: 2025-07-09T20:24:48+00:00
num_battles: 7596
num_wins: 3818
celo_rating: 1291.89
family_friendly_score: 0.5394
family_friendly_standard_error: 0.007049079939963797
submission_type: blend
submissions: ['chaiml-exp-grpo-cp312-9_36146_v7', 'chaiml-mistral-24b-dpo-_59605_v3', 'chaiml-0sw-96p-4ff-chai_45017_v3', 'chaiml-0sw-95p-5ff-rin_63828_v16', 'chaiml-anthropic-40k-2_11629_v13', 'nitral-ai-captain-bmo-12b_v67', 'chaiml-nis-qwen32b-sim_98336_v32', 'chaiml-slerpv5-mistral_24540_v21', 'chaiml-mistral31-24b-s_69496_v14', 'chaiml-grok-payloads-gr_12038_v3', 'chaiml-devstral-cp624-9_95911_v1']
display_name: rob_ab_test
is_internal_developer: True
language_model: chaiml-exp-grpo-cp312-9_36146_v7,chaiml-mistral-24b-dpo-_59605_v3,chaiml-0sw-96p-4ff-chai_45017_v3,chaiml-0sw-95p-5ff-rin_63828_v16,chaiml-anthropic-40k-2_11629_v13,nitral-ai-captain-bmo-12b_v67,chaiml-nis-qwen32b-sim_98336_v32,chaiml-slerpv5-mistral_24540_v21,chaiml-mistral31-24b-s_69496_v14,chaiml-grok-payloads-gr_12038_v3,chaiml-devstral-cp624-9_95911_v1
model_size: n/a
ranking_group: blended
us_pacific_date: 2025-07-09
win_ratio: 0.5026329647182728
weights: {'chaiml-exp-grpo-cp312-9_36146_v7': 1.0, 'chaiml-mistral-24b-dpo-_59605_v3': 1.0, 'chaiml-0sw-96p-4ff-chai_45017_v3': 1.0, 'chaiml-0sw-95p-5ff-rin_63828_v16': 1.0, 'chaiml-anthropic-40k-2_11629_v13': 1.0, 'nitral-ai-captain-bmo-12b_v67': 1.0, 'chaiml-nis-qwen32b-sim_98336_v32': 1.0, 'chaiml-slerpv5-mistral_24540_v21': 1.0, 'chaiml-mistral31-24b-s_69496_v14': 1.0, 'chaiml-grok-payloads-gr_12038_v3': 1.0, 'chaiml-devstral-cp624-9_95911_v1': 1.0}
Resubmit modelShutdown 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 0.99s
Shutdown handler de-registered
blend_simun_2025-07-09 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 3166.35s
Shutdown handler de-registered
blend_simun_2025-07-09 status is now inactive due to auto deactivation removed underperforming models
blend_simun_2025-07-09 status is now torndown due to DeploymentManager action