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 sao10k-mn-12b-lyra-v2a1-v7-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v2a1-v7-mkmlizer to finish
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ Version: 0.12.8 ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: Downloaded to shared memory in 39.842s
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpem3oqdec, device:0
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: quantized model in 36.289s
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v2a1 in 76.133s
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7/config.json
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7/special_tokens_map.json
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7/tokenizer_config.json
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7/tokenizer.json
sao10k-mn-12b-lyra-v2a1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v2a1-v7/flywheel_model.0.safetensors
Job sao10k-mn-12b-lyra-v2a1-v7-mkmlizer completed after 104.34s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v2a1-v7-mkmlizer
Pipeline stage MKMLizer completed in 104.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v2a1-v7
Waiting for inference service sao10k-mn-12b-lyra-v2a1-v7 to be ready
Inference service sao10k-mn-12b-lyra-v2a1-v7 ready after 160.74983644485474s
Pipeline stage MKMLDeployer completed in 161.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3219778537750244s
Received healthy response to inference request in 1.970932960510254s
Received healthy response to inference request in 1.864123821258545s
Received healthy response to inference request in 1.6981167793273926s
Received healthy response to inference request in 1.596301555633545s
5 requests
0 failed requests
5th percentile: 1.6166646003723144
10th percentile: 1.637027645111084
20th percentile: 1.677753734588623
30th percentile: 1.731318187713623
40th percentile: 1.797721004486084
50th percentile: 1.864123821258545
60th percentile: 1.9068474769592285
70th percentile: 1.949571132659912
80th percentile: 2.041141939163208
90th percentile: 2.1815598964691163
95th percentile: 2.25176887512207
99th percentile: 2.3079360580444335
mean time: 1.8902905941009522
Pipeline stage StressChecker completed in 10.73s
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 0.98s
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 0.64s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v2a1_v7 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 3130.51s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v2a1_v7 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v2a1_v7 status is now torndown due to DeploymentManager action