submission_id: function_tosok_2024-08-20
developer_uid: chai_backend_admin
alignment_samples: 25
display_name: gpt4-tl
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}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 25
num_wins: 11
propriety_score: 1.0
propriety_total_count: 1.0
ranking_group: single
status: torndown
submission_type: function
timestamp: 2024-08-20T16:44:36+00:00
us_pacific_date: 2024-08-20
win_ratio: 0.44
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 1.818284511566162s
Received healthy response to inference request in 2.9283535480499268s
Received healthy response to inference request in 3.1528990268707275s
Received healthy response to inference request in 3.1950631141662598s
Received healthy response to inference request in 2.7889630794525146s
5 requests
0 failed requests
5th percentile: 2.0124202251434324
10th percentile: 2.206555938720703
20th percentile: 2.5948273658752443
30th percentile: 2.816841173171997
40th percentile: 2.872597360610962
50th percentile: 2.9283535480499268
60th percentile: 3.0181717395782472
70th percentile: 3.1079899311065673
80th percentile: 3.161331844329834
90th percentile: 3.178197479248047
95th percentile: 3.186630296707153
99th percentile: 3.1933765506744383
mean time: 2.776712656021118
Pipeline stage StressChecker completed in 14.42s
function_tosok_2024-08-20 status is now deployed due to DeploymentManager action
function_tosok_2024-08-20 status is now inactive due to admin request
function_tosok_2024-08-20 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics