submission_id: function_haben_2024-08-20
developer_uid: chai_backend_admin
alignment_samples: 9
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: 9
num_wins: 7
propriety_score: 0.0
propriety_total_count: 0.0
ranking_group: single
status: torndown
submission_type: function
timestamp: 2024-08-20T18:15:19+00:00
us_pacific_date: 2024-08-20
win_ratio: 0.7777777777777778
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1411685943603516s
Received healthy response to inference request in 1.9556913375854492s
Received healthy response to inference request in 3.9225828647613525s
Received healthy response to inference request in 2.0000898838043213s
Received healthy response to inference request in 2.351555585861206s
5 requests
0 failed requests
5th percentile: 1.9645710468292237
10th percentile: 1.9734507560729981
20th percentile: 1.9912101745605468
30th percentile: 2.0283056259155274
40th percentile: 2.0847371101379393
50th percentile: 2.1411685943603516
60th percentile: 2.2253233909606935
70th percentile: 2.309478187561035
80th percentile: 2.6657610416412356
90th percentile: 3.2941719532012943
95th percentile: 3.608377408981323
99th percentile: 3.8597417736053465
mean time: 2.474217653274536
Pipeline stage StressChecker completed in 13.06s
function_haben_2024-08-20 status is now deployed due to DeploymentManager action
function_haben_2024-08-20 status is now inactive due to admin request
function_haben_2024-08-20 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics