submission_id: function_disur_2024-08-15
developer_uid: chai_backend_admin
alignment_samples: 4395
alignment_score: 1.4291446800897425
celo_rating: 1226.15
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, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 4395
num_wins: 2054
propriety_score: 0.7939914163090128
propriety_total_count: 466.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-15T21:16:30+00:00
us_pacific_date: 2024-08-15
win_ratio: 0.46734926052332193
Download Preferencedata
Resubmit model
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.987178087234497s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.520928144454956s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6880662441253662s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.187380790710449s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.207749605178833s
5 requests
0 failed requests
5th percentile: 1.554355764389038
10th percentile: 1.5877833843231202
20th percentile: 1.6546386241912843
30th percentile: 1.7478886127471924
40th percentile: 1.8675333499908446
50th percentile: 1.987178087234497
60th percentile: 2.067259168624878
70th percentile: 2.147340250015259
80th percentile: 2.191454553604126
90th percentile: 2.1996020793914797
95th percentile: 2.2036758422851563
99th percentile: 2.2069348526000976
mean time: 1.9182605743408203
Pipeline stage StressChecker completed in 12.66s
function_disur_2024-08-15 status is now deployed due to DeploymentManager action
function_disur_2024-08-15 status is now inactive due to admin request
function_disur_2024-08-15 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics