submission_id: function_nadin_2024-08-27
developer_uid: chai_backend_admin
alignment_samples: 11691
alignment_score: -0.9110765559340303
celo_rating: 1228.47
display_name: elo_alignment_amd_fp8_weights
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_fp8_weights
num_battles: 11691
num_wins: 5709
propriety_score: 0.7355289421157685
propriety_total_count: 1002.0
ranking_group: single
status: inactive
submission_type: function
timestamp: 2024-08-27T14:45:12+00:00
us_pacific_date: 2024-08-27
win_ratio: 0.4883243520656916
Download Preference Data
Resubmit model
Running pipeline stage StressChecker
Received healthy response to inference request in 1.990372657775879s
Received healthy response to inference request in 1.9086112976074219s
Received healthy response to inference request in 1.8361916542053223s
Received healthy response to inference request in 1.7775709629058838s
Received healthy response to inference request in 2.155378580093384s
5 requests
0 failed requests
5th percentile: 1.7892951011657714
10th percentile: 1.8010192394256592
20th percentile: 1.8244675159454347
30th percentile: 1.8506755828857422
40th percentile: 1.879643440246582
50th percentile: 1.9086112976074219
60th percentile: 1.9413158416748046
70th percentile: 1.9740203857421874
80th percentile: 2.02337384223938
90th percentile: 2.089376211166382
95th percentile: 2.122377395629883
99th percentile: 2.1487783432006835
mean time: 1.9336250305175782
Pipeline stage StressChecker completed in 10.62s
function_nadin_2024-08-27 status is now deployed due to DeploymentManager action
function_nadin_2024-08-27 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics