submission_id: function_biham_2024-08-09
developer_uid: chai_backend_admin
alignment_samples: 1561
alignment_score: 10.614420853565196
celo_rating: 1070.91
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: 14256
num_wins: 4876
propriety_score: 0.7203947368421053
propriety_total_count: 1216.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-09T18:35:50+00:00
us_pacific_date: 2024-08-09
win_ratio: 0.3420314253647587
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 0.8528931140899658s
Received healthy response to inference request in 0.8952622413635254s
Received healthy response to inference request in 0.8112730979919434s
Received healthy response to inference request in 0.45624494552612305s
Received healthy response to inference request in 0.5945107936859131s
5 requests
0 failed requests
5th percentile: 0.48389811515808107
10th percentile: 0.5115512847900391
20th percentile: 0.5668576240539551
30th percentile: 0.6378632545471191
40th percentile: 0.7245681762695313
50th percentile: 0.8112730979919434
60th percentile: 0.8279211044311523
70th percentile: 0.8445691108703614
80th percentile: 0.8613669395446777
90th percentile: 0.8783145904541015
95th percentile: 0.8867884159088135
99th percentile: 0.893567476272583
mean time: 0.7220368385314941
Pipeline stage StressChecker completed in 4.12s
function_biham_2024-08-09 status is now deployed due to DeploymentManager action
function_biham_2024-08-09 status is now inactive due to auto deactivation removed underperforming models
function_biham_2024-08-09 status is now deployed due to admin request
function_biham_2024-08-09 status is now inactive due to auto deactivation removed underperforming models
function_biham_2024-08-09 status is now torndown due to DeploymentManager action
function_biham_2024-08-09 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics