submission_id: function_nilur_2024-08-15
developer_uid: chai_backend_admin
celo_rating: 1234.03
display_name: gpt4-tl
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': 1.0, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 10926
num_wins: 5285
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-15T17:23:22+00:00
us_pacific_date: 2024-08-15
win_ratio: 0.4837085850265422
Download Preferencedata
Resubmit model
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.0982377529144287s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.3633878231048584s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.260803699493408s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.0255658626556396s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.2538163661956787s
5 requests
0 failed requests
5th percentile: 2.0401002407073974
10th percentile: 2.054634618759155
20th percentile: 2.083703374862671
30th percentile: 2.129353475570679
40th percentile: 2.191584920883179
50th percentile: 2.2538163661956787
60th percentile: 2.2566112995147707
70th percentile: 2.259406232833862
80th percentile: 2.2813205242156984
90th percentile: 2.3223541736602784
95th percentile: 2.342870998382568
99th percentile: 2.3592844581604004
mean time: 2.200362300872803
Pipeline stage StressChecker completed in 14.24s
function_nilur_2024-08-15 status is now deployed due to DeploymentManager action
function_nilur_2024-08-15 status is now inactive due to admin request
function_nilur_2024-08-15 status is now torndown due to DeploymentManager action