developer_uid: chai_backend_admin
submission_id: function_tufas_2024-10-31
model_name: function_tufas_2024-10-31
model_group:
status: torndown
timestamp: 2024-10-31T18:35:31+00:00
num_battles: 5764
num_wins: 2666
celo_rating: 1215.73
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: function
display_name: function_tufas_2024-10-31
is_internal_developer: True
ranking_group: single
us_pacific_date: 2024-10-31
win_ratio: 0.4625260235947259
generation_params: {'temperature': 1.5, 'top_p': 0.99, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<｜end▁of▁sentence｜>'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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 StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 4.916141748428345s
Received healthy response to inference request in 8.364377737045288s
Received healthy response to inference request in 5.346778392791748s
Received healthy response to inference request in 3.3797290325164795s
Received healthy response to inference request in 4.012296676635742s
5 requests
0 failed requests
5th percentile: 3.506242561340332
10th percentile: 3.6327560901641847
20th percentile: 3.88578314781189
30th percentile: 4.1930656909942625
40th percentile: 4.554603719711304
50th percentile: 4.916141748428345
60th percentile: 5.088396406173706
70th percentile: 5.260651063919068
80th percentile: 5.950298261642456
90th percentile: 7.157337999343873
95th percentile: 7.76085786819458
99th percentile: 8.243673763275146
mean time: 5.203864717483521
%s, retrying in %s seconds...
Received healthy response to inference request in 4.664427757263184s
Received healthy response to inference request in 3.4517245292663574s
Received healthy response to inference request in 3.740264415740967s
Received healthy response to inference request in 4.047989130020142s
Received healthy response to inference request in 3.6198854446411133s
5 requests
0 failed requests
5th percentile: 3.4853567123413085
10th percentile: 3.5189888954162596
20th percentile: 3.586253261566162
30th percentile: 3.643961238861084
40th percentile: 3.6921128273010253
50th percentile: 3.740264415740967
60th percentile: 3.863354301452637
70th percentile: 3.9864441871643064
80th percentile: 4.17127685546875
90th percentile: 4.417852306365967
95th percentile: 4.541140031814575
99th percentile: 4.639770212173462
mean time: 3.9048582553863525
%s, retrying in %s seconds...
Received healthy response to inference request in 4.160478591918945s
Received healthy response to inference request in 5.453698396682739s
Received healthy response to inference request in 4.597431421279907s
Received healthy response to inference request in 3.5319437980651855s
Received healthy response to inference request in 3.8414559364318848s
5 requests
0 failed requests
5th percentile: 3.5938462257385253
10th percentile: 3.655748653411865
20th percentile: 3.779553508758545
30th percentile: 3.905260467529297
40th percentile: 4.032869529724121
50th percentile: 4.160478591918945
60th percentile: 4.33525972366333
70th percentile: 4.5100408554077145
80th percentile: 4.768684816360474
90th percentile: 5.111191606521606
95th percentile: 5.282445001602173
99th percentile: 5.419447717666626
mean time: 4.317001628875732
clean up pipeline due to error=DeploymentChecksError('Unacceptable 70th percentile latency 4.5100408554077145s')
Shutdown handler de-registered
function_tufas_2024-10-31 status is now failed due to DeploymentManager action
function_tufas_2024-10-31 status is now torndown due to DeploymentManager action