submission_id: function_sibut_2024-08-09
developer_uid: chai_backend_admin
alignment_samples: 1517
alignment_score: 10.422310715379972
celo_rating: 1066.53
display_name: gpt-3-5
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-3-5
num_battles: 14349
num_wins: 4815
propriety_score: 0.7328548644338118
propriety_total_count: 1254.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-09T18:47:21+00:00
us_pacific_date: 2024-08-09
win_ratio: 0.3355634538992264
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4536559581756592s
Received healthy response to inference request in 1.355109453201294s
Received healthy response to inference request in 0.6010262966156006s
Received healthy response to inference request in 0.612940788269043s
Received healthy response to inference request in 0.4743161201477051s
5 requests
0 failed requests
5th percentile: 0.49965815544128417
10th percentile: 0.5250001907348633
20th percentile: 0.5756842613220214
30th percentile: 0.6034091949462891
40th percentile: 0.608174991607666
50th percentile: 0.612940788269043
60th percentile: 0.9098082542419432
70th percentile: 1.2066757202148437
80th percentile: 1.374818754196167
90th percentile: 1.4142373561859132
95th percentile: 1.4339466571807862
99th percentile: 1.4497140979766845
mean time: 0.8994097232818603
Pipeline stage StressChecker completed in 5.12s
function_sibut_2024-08-09 status is now deployed due to DeploymentManager action
function_sibut_2024-08-09 status is now deployed due to admin request
function_sibut_2024-08-09 status is now inactive due to auto deactivation removed underperforming models
function_sibut_2024-08-09 status is now torndown due to DeploymentManager action
function_sibut_2024-08-09 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics