submission_id: function_tujut_2024-08-15
developer_uid: chai_backend_admin
alignment_samples: 11005
alignment_score: 3.0856535584893905
celo_rating: 1172.95
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': 1.0, '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': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
model_group:
model_name: gpt4-tl
num_battles: 11005
num_wins: 4731
propriety_score: 0.7849765258215963
propriety_total_count: 1065.0
ranking_group: single
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: function
timestamp: 2024-08-15T03:04:47+00:00
us_pacific_date: 2024-08-14
win_ratio: 0.4298955020445252
Download Preferencedata
Resubmit model
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.1066019535064697s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.7914066314697266s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.266146421432495s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.8917186260223389s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.2435739040374756s
5 requests
0 failed requests
5th percentile: 1.811469030380249
10th percentile: 1.8315314292907714
20th percentile: 1.8716562271118165
30th percentile: 1.934695291519165
40th percentile: 2.0206486225128173
50th percentile: 2.1066019535064697
60th percentile: 2.1613907337188722
70th percentile: 2.2161795139312743
80th percentile: 2.2480884075164793
90th percentile: 2.257117414474487
95th percentile: 2.2616319179534914
99th percentile: 2.2652435207366945
mean time: 2.0598895072937013
Pipeline stage StressChecker completed in 13.49s
function_tujut_2024-08-15 status is now deployed due to DeploymentManager action
function_tujut_2024-08-15 status is now inactive due to auto deactivation removed underperforming models
function_tujut_2024-08-15 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics