submission_id: function_kajum_2024-08-09
developer_uid: chai_backend_admin
alignment_samples: 0
display_name: gpt-4o
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': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt-4o
num_battles: 71
num_wins: 17
propriety_score: 0.75
propriety_total_count: 4.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-09T16:58:16+00:00
us_pacific_date: 2024-08-09
win_ratio: 0.23943661971830985
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 4.138583660125732s
Received healthy response to inference request in 2.9804086685180664s
Received healthy response to inference request in 3.3476428985595703s
Received healthy response to inference request in 3.0484042167663574s
Received healthy response to inference request in 4.210904836654663s
5 requests
0 failed requests
5th percentile: 2.994007778167725
10th percentile: 3.0076068878173827
20th percentile: 3.034805107116699
30th percentile: 3.108251953125
40th percentile: 3.2279474258422853
50th percentile: 3.3476428985595703
60th percentile: 3.6640192031860352
70th percentile: 3.9803955078124997
80th percentile: 4.153047895431518
90th percentile: 4.181976366043091
95th percentile: 4.196440601348877
99th percentile: 4.208011989593506
mean time: 3.545188856124878
Pipeline stage StressChecker completed in 18.30s
function_kajum_2024-08-09 status is now deployed due to DeploymentManager action
function_kajum_2024-08-09 status is now inactive due to admin request
function_kajum_2024-08-09 status is now torndown due to DeploymentManager action
function_kajum_2024-08-09 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics