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 chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer
Waiting for job on chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer to finish
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-roan-knight-_7016_v3: HTTPConnectionPool(host='jellywibble-roan-knight-7016-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: Downloaded to shared memory in 115.935s
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps62qvrc6, device:0
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-roan-knight-_7016_v3: HTTPConnectionPool(host='jellywibble-roan-knight-7016-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: quantized model in 62.978s
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: Processed model ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k in 178.913s
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/config.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/added_tokens.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/special_tokens_map.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/merges.txt
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/tokenizer_config.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/tokenizer.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/vocab.json
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/flywheel_model.2.safetensors
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/flywheel_model.0.safetensors
chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v1/flywheel_model.1.safetensors
Job chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer completed after 217.9s with status: succeeded
Stopping job with name chaiml-qwen32b-sft-exp1-16150-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.39s
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 chaiml-qwen32b-sft-exp1-16150-v1
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v1 to be ready
Inference service chaiml-qwen32b-sft-exp1-16150-v1 ready after 120.43348240852356s
Pipeline stage MKMLDeployer completed in 120.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.015500068664551s
Received healthy response to inference request in 3.448762893676758s
Received healthy response to inference request in 3.8681085109710693s
Received healthy response to inference request in 3.5601730346679688s
Received healthy response to inference request in 3.4351298809051514s
5 requests
0 failed requests
5th percentile: 3.4378564834594725
10th percentile: 3.440583086013794
20th percentile: 3.4460362911224367
30th percentile: 3.471044921875
40th percentile: 3.5156089782714846
50th percentile: 3.5601730346679688
60th percentile: 3.683347225189209
70th percentile: 3.806521415710449
80th percentile: 3.8975868225097656
90th percentile: 3.956543445587158
95th percentile: 3.9860217571258545
99th percentile: 4.009604406356812
mean time: 3.6655348777770995
%s, retrying in %s seconds...
Received healthy response to inference request in 3.6867477893829346s
Received healthy response to inference request in 3.6615374088287354s
Received healthy response to inference request in 3.352322816848755s
Received healthy response to inference request in 3.5086779594421387s
Received healthy response to inference request in 3.5287463665008545s
5 requests
0 failed requests
5th percentile: 3.3835938453674315
10th percentile: 3.4148648738861085
20th percentile: 3.477406930923462
30th percentile: 3.5126916408538817
40th percentile: 3.5207190036773683
50th percentile: 3.5287463665008545
60th percentile: 3.581862783432007
70th percentile: 3.6349792003631594
80th percentile: 3.666579484939575
90th percentile: 3.676663637161255
95th percentile: 3.6817057132720947
99th percentile: 3.6857393741607667
mean time: 3.5476064682006836
Pipeline stage StressChecker completed in 38.63s
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 0.76s
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 0.63s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen32b-sft-exp1-16150-v1-profiler
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v1-profiler to be ready
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 3535.33s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sft-exp1_16150_v1 status is now torndown due to DeploymentManager action