submission_id: blend_bafif_2024-10-07
developer_uid: end_to_end_test
celo_rating: 1261.59
display_name: blend_bafif_2024-10-07
family_friendly_score: 0.5643281001775535
family_friendly_standard_error: 0.0058364266114219205
is_internal_developer: True
language_model: zonemercy-virgo-edit-v1-1e5_v13,chaiml-lexical-nemo-v4-1k1e5_v3,zonemercy-lexical-nemov8_5966_v9,sao10k-mn-12b-lyra-v4a1_v9
model_group:
model_name: blend_bafif_2024-10-07
model_size: n/a
num_battles: 7542
num_wins: 3842
ranking_group: blended
reward_model: random
status: torndown
submission_type: blend
submissions: ['zonemercy-virgo-edit-v1-1e5_v13', 'chaiml-lexical-nemo-v4-1k1e5_v3', 'zonemercy-lexical-nemov8_5966_v9', 'sao10k-mn-12b-lyra-v4a1_v9']
timestamp: 2024-10-07T00:31:53+00:00
us_pacific_date: 2024-10-06
win_ratio: 0.50941394855476
Download Preference Data
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 0.95s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service blend-bafif-2024-10-07
Waiting for inference service blend-bafif-2024-10-07 to be ready
Inference service blend-bafif-2024-10-07 ready after 50.82184600830078s
Pipeline stage MKMLDeployer completed in 51.89s
run pipeline stage %s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.9108352661132812s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.0639970302581787s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.260519027709961s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.0015769004821777s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.9673881530761719s
5 requests
0 failed requests
5th percentile: 1.974225902557373
10th percentile: 1.9810636520385743
20th percentile: 1.9947391510009767
30th percentile: 2.014060926437378
40th percentile: 2.0390289783477784
50th percentile: 2.0639970302581787
60th percentile: 2.1426058292388914
70th percentile: 2.2212146282196046
80th percentile: 2.390582275390625
90th percentile: 2.650708770751953
95th percentile: 2.780772018432617
99th percentile: 2.8848226165771482
mean time: 2.2408632755279543
Pipeline stage StressChecker completed in 14.03s
Shutdown handler de-registered
blend_bafif_2024-10-07 status is now deployed due to DeploymentManager action
blend_bafif_2024-10-07 status is now inactive due to auto deactivation removed underperforming models
blend_bafif_2024-10-07 status is now torndown due to DeploymentManager action