submission_id: function_tagak_2024-09-14
developer_uid: chai_backend_admin
alignment_samples: 10915
alignment_score: -1.6472457184092388
celo_rating: 1262.14
display_name: dpo_with_ava_reward_100k_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_100k_v1
num_battles: 10915
num_wins: 5573
propriety_score: 0.7533960292580982
propriety_total_count: 957.0
ranking_group: single
status: inactive
submission_type: function
timestamp: 2024-09-14T21:07:56+00:00
us_pacific_date: 2024-09-14
win_ratio: 0.5105817682088869
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
Received healthy response to inference request in 3.711719274520874s
Received healthy response to inference request in 3.7520859241485596s
Received healthy response to inference request in 3.771306037902832s
Received healthy response to inference request in 5.498477458953857s
Received healthy response to inference request in 5.946103811264038s
5 requests
0 failed requests
5th percentile: 3.719792604446411
10th percentile: 3.7278659343719482
20th percentile: 3.7440125942230225
30th percentile: 3.755929946899414
40th percentile: 3.763617992401123
50th percentile: 3.771306037902832
60th percentile: 4.462174606323242
70th percentile: 5.153043174743652
80th percentile: 5.588002729415893
90th percentile: 5.767053270339966
95th percentile: 5.856578540802002
99th percentile: 5.928198757171631
mean time: 4.535938501358032
%s, retrying in %s seconds...
Received healthy response to inference request in 4.2221879959106445s
Received healthy response to inference request in 4.75258207321167s
Received healthy response to inference request in 4.842185020446777s
Received healthy response to inference request in 4.9871063232421875s
Received healthy response to inference request in 6.905688524246216s
5 requests
0 failed requests
5th percentile: 4.32826681137085
10th percentile: 4.434345626831055
20th percentile: 4.646503257751465
30th percentile: 4.770502662658691
40th percentile: 4.806343841552734
50th percentile: 4.842185020446777
60th percentile: 4.900153541564942
70th percentile: 4.958122062683105
80th percentile: 5.370822763442994
90th percentile: 6.138255643844604
95th percentile: 6.52197208404541
99th percentile: 6.828945236206055
mean time: 5.141949987411499
Pipeline stage StressChecker completed in 49.54s
Shutdown handler de-registered
function_tagak_2024-09-14 status is now deployed due to DeploymentManager action
function_tagak_2024-09-14 status is now inactive due to auto deactivation removed underperforming models