blend_sigim_2024-11-25

developer_uid: chai_backend_admin

submission_id: blend_sigim_2024-11-25

model_name: blend_sigim_2024-11-25

model_group:

status: inactive

timestamp: 2024-11-25T17:43:16+00:00

num_battles: 1696

num_wins: 895

celo_rating: 1298.15

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: blend

submissions: ['chaiml-lexical-viral-v6a_9285_v1', 'chaiml-lexical-viral-v5a_3966_v1', 'chaiml-small-anthropic-a_1700_v2']

display_name: blend_sigim_2024-11-25

is_internal_developer: True

language_model: chaiml-lexical-viral-v6a_9285_v1,chaiml-lexical-viral-v5a_3966_v1,chaiml-small-anthropic-a_1700_v2

model_size: n/a

ranking_group: blended

reward_model: random

us_pacific_date: 2024-11-25

win_ratio: 0.5277122641509434

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 ProductionBlendMKMLTemplater
Pipeline stage ProductionBlendMKMLTemplater completed in 0.91s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service blend-sigim-2024-11-25
Waiting for inference service blend-sigim-2024-11-25 to be ready
Inference service blend-sigim-2024-11-25 ready after 182.50968194007874s
Pipeline stage MKMLDeployer completed in 184.13s
run pipeline stage %s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.8461949825286865s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.704632043838501s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.030104160308838s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.8562400341033936s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.455082893371582s
5 requests
0 failed requests
5th percentile: 2.7349536418914795
10th percentile: 2.765275239944458
20th percentile: 2.825918436050415
30th percentile: 2.8910128593444826
40th percentile: 2.9605585098266602
50th percentile: 3.030104160308838
60th percentile: 3.2000956535339355
70th percentile: 3.370087146759033
80th percentile: 3.533305311203003
90th percentile: 3.689750146865845
95th percentile: 3.7679725646972657
99th percentile: 3.830550498962402
mean time: 3.1784508228302
Pipeline stage StressChecker completed in 19.63s
Shutdown handler de-registered
blend_sigim_2024-11-25 status is now deployed due to DeploymentManager action