submission_id: function_banif_2024-10-05
developer_uid: chai_backend_admin
celo_rating: 1270.58
display_name: retune_with_base
family_friendly_score: 0.6054047524926429
family_friendly_standard_error: 0.005585655620284271
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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: True
model_group:
model_name: retune_with_base
num_battles: 7942
num_wins: 4116
ranking_group: single
status: torndown
submission_type: function
timestamp: 2024-10-05T19:25:24+00:00
us_pacific_date: 2024-10-05
win_ratio: 0.5182573659027953
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 3.2764699459075928s
Received healthy response to inference request in 4.034320831298828s
Received healthy response to inference request in 2.6978514194488525s
Received healthy response to inference request in 2.978609085083008s
Received healthy response to inference request in 4.456814765930176s
5 requests
0 failed requests
5th percentile: 2.7540029525756835
10th percentile: 2.8101544857025145
20th percentile: 2.922457551956177
30th percentile: 3.038181257247925
40th percentile: 3.157325601577759
50th percentile: 3.2764699459075928
Connection pool is full, discarding connection: %s. Connection pool size: %s
60th percentile: 3.579610300064087
70th percentile: 3.882750654220581
80th percentile: 4.118819618225098
90th percentile: 4.287817192077637
95th percentile: 4.372315979003906
99th percentile: 4.439915008544922
mean time: 3.4888132095336912
%s, retrying in %s seconds...
Received healthy response to inference request in 4.527576684951782s
Received healthy response to inference request in 4.006428241729736s
Received healthy response to inference request in 3.0500504970550537s
Received healthy response to inference request in 3.1891281604766846s
Received healthy response to inference request in 5.709911584854126s
5 requests
0 failed requests
5th percentile: 3.07786602973938
10th percentile: 3.105681562423706
20th percentile: 3.161312627792358
30th percentile: 3.352588176727295
40th percentile: 3.6795082092285156
50th percentile: 4.006428241729736
60th percentile: 4.214887619018555
70th percentile: 4.423346996307373
80th percentile: 4.7640436649322515
90th percentile: 5.236977624893188
95th percentile: 5.473444604873657
99th percentile: 5.6626181888580325
mean time: 4.096619033813477
%s, retrying in %s seconds...
Received healthy response to inference request in 3.6615445613861084s
Received healthy response to inference request in 2.231931447982788s
Received healthy response to inference request in 2.4635071754455566s
Received healthy response to inference request in 2.768085479736328s
Received healthy response to inference request in 3.8503620624542236s
5 requests
0 failed requests
5th percentile: 2.278246593475342
10th percentile: 2.3245617389678954
20th percentile: 2.4171920299530028
30th percentile: 2.524422836303711
40th percentile: 2.6462541580200196
50th percentile: 2.768085479736328
60th percentile: 3.12546911239624
70th percentile: 3.482852745056152
80th percentile: 3.6993080615997314
90th percentile: 3.7748350620269777
95th percentile: 3.8125985622406007
99th percentile: 3.842809362411499
mean time: 2.995086145401001
Pipeline stage StressChecker completed in 56.84s
Shutdown handler de-registered
function_banif_2024-10-05 status is now deployed due to DeploymentManager action
function_banif_2024-10-05 status is now inactive due to auto deactivation removed underperforming models
function_banif_2024-10-05 status is now torndown due to DeploymentManager action