alexdaoud-trainer-bagir-_9705

developer_uid: chai_backend_admin
submission_id: alexdaoud-trainer-bagir-_9705_v1
model_name: alexdaoud-trainer-bagir-_9705_v1
model_group: alexdaoud/trainer_bagir_
status: inactive
timestamp: 2024-12-16T01:51:35+00:00
num_battles: 30188
num_wins: 15182
celo_rating: 1263.82
family_friendly_score: 0.5788
family_friendly_standard_error: 0.006982700910106346
submission_type: basic
model_repo: alexdaoud/trainer_bagir_2024-12-11-checkpoint-48
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: alexdaoud-trainer-bagir-_9705_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: alexdaoud/trainer_bagir_2024-12-11-checkpoint-48
model_size: 8B
ranking_group: single
us_pacific_date: 2024-12-15
win_ratio: 0.5029150655889758
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-9705-v1-mkmlizer
Waiting for job on alexdaoud-trainer-bagir-9705-v1-mkmlizer to finish
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║     _____            __           __                                ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║       /___/                                                         ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  belonging to:                                                      ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-bagir-9705-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexdaoud-trainer-bagir-9705-v1-mkmlizer: Downloaded to shared memory in 34.831s
alexdaoud-trainer-bagir-9705-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpit9p55by, device:0
alexdaoud-trainer-bagir-9705-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
alexdaoud-trainer-bagir-9705-v1-mkmlizer: quantized model in 85.485s
alexdaoud-trainer-bagir-9705-v1-mkmlizer: Processed model alexdaoud/trainer_bagir_2024-12-11-checkpoint-48 in 120.317s
alexdaoud-trainer-bagir-9705-v1-mkmlizer: creating bucket guanaco-mkml-models
alexdaoud-trainer-bagir-9705-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexdaoud-trainer-bagir-9705-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1
alexdaoud-trainer-bagir-9705-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1/config.json
alexdaoud-trainer-bagir-9705-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1/special_tokens_map.json
alexdaoud-trainer-bagir-9705-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1/tokenizer_config.json
alexdaoud-trainer-bagir-9705-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1/tokenizer.json
alexdaoud-trainer-bagir-9705-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexdaoud-trainer-bagir-9705-v1/flywheel_model.0.safetensors
Job alexdaoud-trainer-bagir-9705-v1-mkmlizer completed after 145.94s with status: succeeded
Stopping job with name alexdaoud-trainer-bagir-9705-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexdaoud-trainer-bagir-9705-v1
Waiting for inference service alexdaoud-trainer-bagir-9705-v1 to be ready
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
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
Inference service alexdaoud-trainer-bagir-9705-v1 ready after 211.22318863868713s
Pipeline stage MKMLDeployer completed in 212.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.361868143081665s
Received healthy response to inference request in 2.308701276779175s
Received healthy response to inference request in 3.159391164779663s
Received healthy response to inference request in 2.88665771484375s
Received healthy response to inference request in 2.3182692527770996s
5 requests
0 failed requests
5th percentile: 2.3106148719787596
10th percentile: 2.312528467178345
20th percentile: 2.316355657577515
30th percentile: 2.43194694519043
40th percentile: 2.65930233001709
50th percentile: 2.88665771484375
60th percentile: 2.9957510948181154
70th percentile: 3.1048444747924804
80th percentile: 3.3998865604400637
90th percentile: 3.8808773517608643
95th percentile: 4.1213727474212645
99th percentile: 4.313769063949585
mean time: 3.0069775104522707
Pipeline stage StressChecker completed in 16.54s
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 2.56s
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 2.72s
Shutdown handler de-registered
alexdaoud-trainer-bagir-_9705_v1 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
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-9705-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.45s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexdaoud-trainer-bagir-9705-v1-profiler
Waiting for inference service alexdaoud-trainer-bagir-9705-v1-profiler to be ready
Inference service alexdaoud-trainer-bagir-9705-v1-profiler ready after 50.2152783870697s
Pipeline stage MKMLProfilerDeployer completed in 50.47s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplo6kncj:/code/chaiverse_profiler_1734317988 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplo6kncj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734317988 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734317988/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplo6kncj:/code/chaiverse_profiler_1734320786 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplo6kncj:/code/chaiverse_profiler_1734320787 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplo6kncj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734320787 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734320787/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-9705-v1-profiler is running
Tearing down inference service alexdaoud-trainer-bagir-9705-v1-profiler
Service alexdaoud-trainer-bagir-9705-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.29s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-9705-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexdaoud-trainer-bagir-9705-v1-profiler
Waiting for inference service alexdaoud-trainer-bagir-9705-v1-profiler to be ready
Inference service alexdaoud-trainer-bagir-9705-v1-profiler ready after 80.1939926147461s
Pipeline stage MKMLProfilerDeployer completed in 80.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplorw9gb:/code/chaiverse_profiler_1734321643 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplorw9gb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734321643 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734321643/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplorw9gb:/code/chaiverse_profiler_1734324441 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplorw9gb:/code/chaiverse_profiler_1734324442 --namespace tenant-chaiml-guanaco
kubectl exec -it alexdaoud-trainer-bae60edc821ce1384d907d0d53386f7ff9-deplorw9gb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734324442 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734324442/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service alexdaoud-trainer-bagir-9705-v1-profiler is running
Tearing down inference service alexdaoud-trainer-bagir-9705-v1-profiler
Service alexdaoud-trainer-bagir-9705-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.33s
Shutdown handler de-registered
alexdaoud-trainer-bagir-_9705_v1 status is now inactive due to auto deactivation removed underperforming models