submission_id: function_tisol_2024-09-19
developer_uid: chai_backend_admin
celo_rating: 1285.14
display_name: reward_blend_default_full_bon
family_friendly_score: 0.0
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}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: True
model_group:
model_name: reward_blend_default_full_bon
num_battles: 13458
num_wins: 7480
ranking_group: single
status: torndown
submission_type: function
timestamp: 2024-09-19T22:09:20+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5558032397087235
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 StressChecker
Received healthy response to inference request in 4.493822336196899s
Received healthy response to inference request in 5.0188539028167725s
Received healthy response to inference request in 5.762596845626831s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.352877378463745s
Received healthy response to inference request in 7.015752077102661s
5 requests
0 failed requests
5th percentile: 2.781066370010376
10th percentile: 3.2092553615570067
20th percentile: 4.065633344650268
30th percentile: 4.598828649520874
40th percentile: 4.808841276168823
50th percentile: 5.0188539028167725
60th percentile: 5.316351079940796
70th percentile: 5.613848257064819
80th percentile: 6.013227891921997
90th percentile: 6.514489984512329
95th percentile: 6.765121030807495
99th percentile: 6.965625867843628
mean time: 4.928780508041382
%s, retrying in %s seconds...
Received healthy response to inference request in 6.0637359619140625s
Received healthy response to inference request in 3.86366605758667s
Received healthy response to inference request in 4.1678173542022705s
Received healthy response to inference request in 5.259063720703125s
Received healthy response to inference request in 4.81937575340271s
5 requests
0 failed requests
5th percentile: 3.92449631690979
10th percentile: 3.98532657623291
20th percentile: 4.10698709487915
30th percentile: 4.298129034042359
40th percentile: 4.558752393722534
50th percentile: 4.81937575340271
60th percentile: 4.995250940322876
70th percentile: 5.171126127243042
80th percentile: 5.4199981689453125
90th percentile: 5.7418670654296875
95th percentile: 5.902801513671875
99th percentile: 6.031549072265625
mean time: 4.834731769561768
%s, retrying in %s seconds...
Received healthy response to inference request in 4.107841730117798s
Received healthy response to inference request in 5.497103214263916s
Received healthy response to inference request in 4.771284103393555s
Received healthy response to inference request in 4.350191116333008s
Received healthy response to inference request in 3.928861379623413s
5 requests
0 failed requests
5th percentile: 3.96465744972229
10th percentile: 4.000453519821167
20th percentile: 4.0720456600189205
30th percentile: 4.1563116073608395
40th percentile: 4.253251361846924
50th percentile: 4.350191116333008
60th percentile: 4.518628311157227
70th percentile: 4.687065505981446
80th percentile: 4.916447925567627
90th percentile: 5.206775569915772
95th percentile: 5.351939392089844
99th percentile: 5.468070449829102
mean time: 4.531056308746338
Pipeline stage StressChecker completed in 74.09s
Shutdown handler de-registered
function_tisol_2024-09-19 status is now deployed due to DeploymentManager action
function_tisol_2024-09-19 status is now inactive due to auto deactivation removed underperforming models
function_tisol_2024-09-19 status is now torndown due to DeploymentManager action