blend_sirof_2025-06-16

developer_uid: chai_backend_admin

submission_id: blend_sirof_2025-06-16

model_name: blend_sirof_2025-06-16

model_group:

status: torndown

timestamp: 2025-06-16T23:18:36+00:00

num_battles: 2331232

num_wins: 1222876

celo_rating: 1302.0

family_friendly_score: 0.4972

family_friendly_standard_error: 0.0070709569366529165

submission_type: blend

submissions: ['chaiml-exp-grpo-cp312-9_36146_v4', 'rirv938-mistral-24b-dpo_29487_v8', 'rirv938-0sw-96p-4ff-cha_93234_v2', 'chaiml-0sw-95p-5ff-rine_63828_v1', 'chaiml-anthropic-40k-24_11629_v1', 'nitral-ai-captain-bmo-12b_v45', 'chaiml-nis-qwen32b-simp_98336_v5', 'chaiml-slerpv5-mistral3_24540_v2', 'chaiml-mistral31-24b-si_69496_v3']

display_name: blend_sirof_2025-06-16

is_internal_developer: True

language_model: chaiml-exp-grpo-cp312-9_36146_v4,rirv938-mistral-24b-dpo_29487_v8,rirv938-0sw-96p-4ff-cha_93234_v2,chaiml-0sw-95p-5ff-rine_63828_v1,chaiml-anthropic-40k-24_11629_v1,nitral-ai-captain-bmo-12b_v45,chaiml-nis-qwen32b-simp_98336_v5,chaiml-slerpv5-mistral3_24540_v2,chaiml-mistral31-24b-si_69496_v3

model_size: n/a

ranking_group: blended

us_pacific_date: 2025-06-16

win_ratio: 0.5245621199434463

overrides: {'chaiml-0sw-95p-5ff-rine_63828_v1': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'chaiml-anthropic-40k-24_11629_v1': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'chaiml-exp-grpo-cp312-9_36146_v4': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'chaiml-mistral31-24b-si_69496_v3': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 98}, 'formatter': {}}, 'chaiml-nis-qwen32b-simp_98336_v5': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'chaiml-slerpv5-mistral3_24540_v2': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'nitral-ai-captain-bmo-12b_v45': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'rirv938-0sw-96p-4ff-cha_93234_v2': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}, 'rirv938-mistral-24b-dpo_29487_v8': {'generation_params': {'best_of': 8, 'max_input_tokens': 5120, 'max_output_tokens': 112}, 'formatter': {}}}

weights: {'chaiml-exp-grpo-cp312-9_36146_v4': 1.0, 'rirv938-mistral-24b-dpo_29487_v8': 1.0, 'rirv938-0sw-96p-4ff-cha_93234_v2': 1.0, 'chaiml-0sw-95p-5ff-rine_63828_v1': 1.0, 'chaiml-anthropic-40k-24_11629_v1': 1.0, 'nitral-ai-captain-bmo-12b_v45': 1.0, 'chaiml-nis-qwen32b-simp_98336_v5': 1.0, 'chaiml-slerpv5-mistral3_24540_v2': 1.0, 'chaiml-mistral31-24b-si_69496_v3': 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 0.69s
Shutdown handler de-registered
blend_sirof_2025-06-16 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 3927.46s
Shutdown handler de-registered
blend_sirof_2025-06-16 status is now inactive due to auto deactivation removed underperforming models
blend_sirof_2025-06-16 status is now torndown due to DeploymentManager action