submission_id: function_junum_2024-08-15
developer_uid: chai_backend_admin
alignment_samples: 6683
alignment_score: 2.171971165301418
celo_rating: 1145.66
display_name: gpt4-tl
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': 0.1, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 6683
num_wins: 2719
propriety_score: 0.8
propriety_total_count: 645.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-15T01:30:17+00:00
us_pacific_date: 2024-08-14
win_ratio: 0.4068532096363908
Download Preferencedata
Resubmit model
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.1754608154296875s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.5652408599853516s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.4515166282653809s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.6971526145935059s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.5063979625701904s
5 requests
0 failed requests
5th percentile: 1.2306719779968263
10th percentile: 1.2858831405639648
20th percentile: 1.396305465698242
30th percentile: 1.4624928951263427
40th percentile: 1.4844454288482667
50th percentile: 1.5063979625701904
60th percentile: 1.5299351215362549
70th percentile: 1.5534722805023193
80th percentile: 1.5916232109069823
90th percentile: 1.644387912750244
95th percentile: 1.670770263671875
99th percentile: 1.6918761444091797
mean time: 1.4791537761688232
Pipeline stage StressChecker completed in 11.02s
function_junum_2024-08-15 status is now deployed due to DeploymentManager action
function_junum_2024-08-15 status is now inactive due to admin request
function_junum_2024-08-15 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics