submission_id: function_lapuk_2024-08-30
developer_uid: chai_backend_admin
celo_rating: 1232.45
display_name: elo_alignment_amd_calibrated
family_friendly_score: 0.0
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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: True
model_group:
model_name: elo_alignment_amd_calibrated
num_battles: 9053
num_wins: 4473
ranking_group: single
status: torndown
submission_type: function
timestamp: 2024-08-30T18:30:57+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.49409035678780516
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5905961990356445s
Received healthy response to inference request in 1.2461004257202148s
Received healthy response to inference request in 1.2876591682434082s
Received healthy response to inference request in 1.8619685173034668s
Received healthy response to inference request in 1.1361980438232422s
5 requests
0 failed requests
5th percentile: 1.1581785202026367
10th percentile: 1.1801589965820312
20th percentile: 1.2241199493408204
30th percentile: 1.2544121742248535
40th percentile: 1.2710356712341309
50th percentile: 1.2876591682434082
60th percentile: 1.4088339805603027
70th percentile: 1.5300087928771973
80th percentile: 1.6448706626892091
90th percentile: 1.7534195899963378
95th percentile: 1.8076940536499022
99th percentile: 1.851113624572754
mean time: 1.4245044708251953
Pipeline stage StressChecker completed in 8.44s
function_lapuk_2024-08-30 status is now deployed due to DeploymentManager action
function_lapuk_2024-08-30 status is now inactive due to admin request
function_lapuk_2024-08-30 status is now torndown due to DeploymentManager action