submission_id: function_regus_2024-08-10
developer_uid: chai_backend_admin
alignment_samples: 94860
alignment_score: 5.238929814813356
celo_rating: 1128.84
display_name: gpt4o-mini-raise-on-assist
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': 1.5, '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: gpt4o-mini-raise-on-assist
num_battles: 94855
num_wins: 35327
propriety_score: 0.8012827038582918
propriety_total_count: 9823.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-10T01:17:36+00:00
us_pacific_date: 2024-08-09
win_ratio: 0.37243160613568077
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 0.60595703125s
Received healthy response to inference request in 0.4783968925476074s
Received healthy response to inference request in 0.557441234588623s
Received healthy response to inference request in 1.0907597541809082s
Received healthy response to inference request in 0.49655938148498535s
5 requests
0 failed requests
5th percentile: 0.482029390335083
10th percentile: 0.4856618881225586
20th percentile: 0.49292688369750975
30th percentile: 0.5087357521057129
40th percentile: 0.533088493347168
50th percentile: 0.557441234588623
60th percentile: 0.5768475532531738
70th percentile: 0.5962538719177246
80th percentile: 0.7029175758361818
90th percentile: 0.8968386650085449
95th percentile: 0.9937992095947265
99th percentile: 1.0713676452636718
mean time: 0.6458228588104248
Pipeline stage StressChecker completed in 3.76s
function_regus_2024-08-10 status is now deployed due to DeploymentManager action
function_regus_2024-08-10 status is now inactive due to auto deactivation removed underperforming models
function_regus_2024-08-10 status is now deployed due to admin request
function_regus_2024-08-10 status is now inactive due to auto deactivation removed underperforming models
function_regus_2024-08-10 status is now torndown due to DeploymentManager action
function_regus_2024-08-10 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics