submission_id: function_nuhum_2024-08-16
developer_uid: chai_backend_admin
alignment_samples: 6655
alignment_score: 2.9557761881901534
celo_rating: 1215.67
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': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 6655
num_wins: 3115
propriety_score: 0.7789473684210526
propriety_total_count: 760.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-16T00:10:44+00:00
us_pacific_date: 2024-08-15
win_ratio: 0.46806912096168296
Download Preferencedata
Resubmit model
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 9.64323616027832s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.5740206241607666s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.8686208724975586s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.923729419708252s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.6589322090148926s
5 requests
0 failed requests
5th percentile: 1.632940673828125
10th percentile: 1.6918607234954834
20th percentile: 1.8097008228302003
30th percentile: 1.8796425819396974
40th percentile: 1.9016860008239747
50th percentile: 1.923729419708252
60th percentile: 2.217810535430908
70th percentile: 2.5118916511535643
80th percentile: 4.055792999267579
90th percentile: 6.84951457977295
95th percentile: 8.246375370025634
99th percentile: 9.363864002227784
mean time: 3.533707857131958
Pipeline stage StressChecker completed in 20.84s
function_nuhum_2024-08-16 status is now deployed due to DeploymentManager action
function_nuhum_2024-08-16 status is now inactive due to admin request
function_nuhum_2024-08-16 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics