alexdaoud-trainer-bagir_85370

developer_uid: chai_backend_admin

submission_id: alexdaoud-trainer-bagir_85370_v2

model_name: alexdaoud-trainer-bagir_85370_v2

model_group: alexdaoud/trainer_bagir_

status: torndown

timestamp: 2025-01-20T04:37:16+00:00

num_battles: 10989

num_wins: 5866

celo_rating: 1292.58

family_friendly_score: 0.5656

family_friendly_standard_error: 0.007009944935589723

submission_type: basic

model_repo: alexdaoud/trainer_bagir_2024-12-11-checkpoint-71

model_architecture: LlamaForSequenceClassification

model_num_parameters: 8030261248.0

best_of: 1

max_input_tokens: 256

max_output_tokens: 1

reward_model: default

display_name: alexdaoud-trainer-bagir_85370_v2

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: alexdaoud/trainer_bagir_2024-12-11-checkpoint-71

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-19

win_ratio: 0.5338065338065338

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 256, 'best_of': 1, 'max_output_tokens': 1}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}

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 MKMLizer
Starting job with name alexdaoud-trainer-bagir-85370-v2-mkmlizer
Waiting for job on alexdaoud-trainer-bagir-85370-v2-mkmlizer to finish
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║     _____            __           __                                ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║       /___/                                                         ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  belonging to:                                                      ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-85370-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexdaoud-trainer-bagir-85370-v2-mkmlizer: Downloaded to shared memory in 32.218s
alexdaoud-trainer-bagir-85370-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmptqob4xgl, device:0
alexdaoud-trainer-bagir-85370-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexdaoud-trainer-bagir-85370-v2-mkmlizer: quantized model in 84.639s
alexdaoud-trainer-bagir-85370-v2-mkmlizer: Processed model alexdaoud/trainer_bagir_2024-12-11-checkpoint-71 in 116.858s
alexdaoud-trainer-bagir-85370-v2-mkmlizer: creating bucket guanaco-mkml-models
alexdaoud-trainer-bagir-85370-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexdaoud-trainer-bagir-85370-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2
alexdaoud-trainer-bagir-85370-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2/config.json
alexdaoud-trainer-bagir-85370-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2/special_tokens_map.json
alexdaoud-trainer-bagir-85370-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2/tokenizer_config.json
alexdaoud-trainer-bagir-85370-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2/tokenizer.json
alexdaoud-trainer-bagir-85370-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexdaoud-trainer-bagir-85370-v2/flywheel_model.0.safetensors
Job alexdaoud-trainer-bagir-85370-v2-mkmlizer completed after 145.66s with status: succeeded
Stopping job with name alexdaoud-trainer-bagir-85370-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexdaoud-trainer-bagir-85370-v2
Waiting for inference service alexdaoud-trainer-bagir-85370-v2 to be ready
Inference service alexdaoud-trainer-bagir-85370-v2 ready after 120.56090497970581s
Pipeline stage MKMLDeployer completed in 121.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.962474584579468s
Received healthy response to inference request in 3.6424217224121094s
Received healthy response to inference request in 1.9617133140563965s
Received healthy response to inference request in 4.652254104614258s
Received healthy response to inference request in 4.033230543136597s
5 requests
0 failed requests
5th percentile: 2.297854995727539
10th percentile: 2.633996677398682
20th percentile: 3.3062800407409667
30th percentile: 3.7205834865570067
40th percentile: 3.8769070148468017
50th percentile: 4.033230543136597
60th percentile: 4.280839967727661
70th percentile: 4.528449392318725
80th percentile: 4.7142982006073
90th percentile: 4.838386392593383
95th percentile: 4.900430488586426
99th percentile: 4.9500657653808595
mean time: 3.8504188537597654
%s, retrying in %s seconds...
Received healthy response to inference request in 6.082963943481445s
Received healthy response to inference request in 3.9432432651519775s
Received healthy response to inference request in 2.557500123977661s
Received healthy response to inference request in 4.833761692047119s
Received healthy response to inference request in 4.066228151321411s
5 requests
0 failed requests
5th percentile: 2.8346487522125243
10th percentile: 3.1117973804473875
20th percentile: 3.6660946369171143
30th percentile: 3.967840242385864
40th percentile: 4.017034196853638
50th percentile: 4.066228151321411
60th percentile: 4.373241567611695
70th percentile: 4.680254983901977
80th percentile: 5.0836021423339846
90th percentile: 5.5832830429077145
95th percentile: 5.83312349319458
99th percentile: 6.032995853424072
mean time: 4.2967394351959225
%s, retrying in %s seconds...
Received healthy response to inference request in 3.0082004070281982s
Received healthy response to inference request in 2.312130928039551s
Received healthy response to inference request in 3.488546848297119s
Received healthy response to inference request in 3.7188637256622314s
Received healthy response to inference request in 4.75985860824585s
5 requests
0 failed requests
5th percentile: 2.4513448238372804
10th percentile: 2.59055871963501
20th percentile: 2.8689865112304687
30th percentile: 3.1042696952819826
40th percentile: 3.296408271789551
50th percentile: 3.488546848297119
60th percentile: 3.580673599243164
70th percentile: 3.672800350189209
80th percentile: 3.9270627021789553
90th percentile: 4.343460655212402
95th percentile: 4.551659631729126
99th percentile: 4.718218812942505
mean time: 3.45752010345459
Pipeline stage StressChecker completed in 62.05s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.73s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 1.02s
Shutdown handler de-registered
alexdaoud-trainer-bagir_85370_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3642.99s
Shutdown handler de-registered
alexdaoud-trainer-bagir_85370_v2 status is now inactive due to auto deactivation removed underperforming models
alexdaoud-trainer-bagir_85370_v2 status is now torndown due to DeploymentManager action