submission_id: function_kigof_2024-09-14
developer_uid: chai_backend_admin
alignment_samples: 19155
alignment_score: -1.0625315151374197
celo_rating: 1264.61
display_name: dpo_with_ava_reward_650k_v1
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: dpo_with_ava_reward_650k_v1
num_battles: 19154
num_wins: 9762
propriety_score: 0.7450199203187251
propriety_total_count: 1757.0
ranking_group: single
status: inactive
submission_type: function
timestamp: 2024-09-14T20:51:22+00:00
us_pacific_date: 2024-09-14
win_ratio: 0.5096585569593819
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 4.468459129333496s
Received healthy response to inference request in 2.6508290767669678s
Received healthy response to inference request in 2.3933377265930176s
Received healthy response to inference request in 2.0618436336517334s
Received healthy response to inference request in 3.6746463775634766s
5 requests
0 failed requests
5th percentile: 2.1281424522399903
10th percentile: 2.1944412708282472
20th percentile: 2.3270389080047607
30th percentile: 2.4448359966278077
40th percentile: 2.5478325366973875
50th percentile: 2.6508290767669678
60th percentile: 3.0603559970855714
70th percentile: 3.4698829174041745
80th percentile: 3.8334089279174806
90th percentile: 4.150934028625488
95th percentile: 4.309696578979492
99th percentile: 4.436706619262695
mean time: 3.049823188781738
Pipeline stage StressChecker completed in 16.69s
Shutdown handler de-registered
function_kigof_2024-09-14 status is now deployed due to DeploymentManager action
function_kigof_2024-09-14 status is now inactive due to auto deactivation removed underperforming models