submission_id: function_diham_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: 46
num_wins: 16
propriety_score: 0.25
propriety_total_count: 4.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-09T16:39:41+00:00
us_pacific_date: 2024-08-09
win_ratio: 0.34782608695652173
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 4.376416206359863s
Received healthy response to inference request in 4.334317207336426s
Received healthy response to inference request in 4.597395658493042s
Received healthy response to inference request in 4.097092866897583s
Received healthy response to inference request in 4.166703701019287s
5 requests
0 failed requests
5th percentile: 4.111015033721924
10th percentile: 4.124937200546265
20th percentile: 4.152781534194946
30th percentile: 4.2002264022827145
40th percentile: 4.26727180480957
50th percentile: 4.334317207336426
60th percentile: 4.3511568069458
70th percentile: 4.367996406555176
80th percentile: 4.420612096786499
90th percentile: 4.5090038776397705
95th percentile: 4.553199768066406
99th percentile: 4.588556480407715
mean time: 4.31438512802124
Pipeline stage StressChecker completed in 22.21s
function_diham_2024-08-09 status is now deployed due to DeploymentManager action
function_diham_2024-08-09 status is now inactive due to admin request
function_diham_2024-08-09 status is now torndown due to DeploymentManager action
function_diham_2024-08-09 status is now torndown due to DeploymentManager action