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-arli-24b-sft-exp-26998-v1-mkmlizer
Waiting for job on chaiml-arli-24b-sft-exp-26998-v1-mkmlizer to finish
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ _____ __ __ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ /___/ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ belonging to: ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ║ ║
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: Downloaded to shared memory in 77.954s
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3skarc1w, device:0
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: quantized model in 53.606s
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: Processed model ChaiML/arli-24b-sft-exp2-combo-retry-ss-grok-3k-sft in 131.560s
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/config.json
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/special_tokens_map.json
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/tokenizer_config.json
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/tokenizer.json
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/flywheel_model.1.safetensors
chaiml-arli-24b-sft-exp-26998-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-arli-24b-sft-exp-26998-v1/flywheel_model.0.safetensors
Job chaiml-arli-24b-sft-exp-26998-v1-mkmlizer completed after 165.72s with status: succeeded
Stopping job with name chaiml-arli-24b-sft-exp-26998-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.20s
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-arli-24b-sft-exp-26998-v1
Waiting for inference service chaiml-arli-24b-sft-exp-26998-v1 to be ready
Inference service chaiml-arli-24b-sft-exp-26998-v1 ready after 140.4545910358429s
Pipeline stage MKMLDeployer completed in 140.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7307121753692627s
Received healthy response to inference request in 2.0420186519622803s
Received healthy response to inference request in 2.1499693393707275s
Received healthy response to inference request in 1.9156913757324219s
Received healthy response to inference request in 2.1333470344543457s
5 requests
0 failed requests
5th percentile: 1.9409568309783936
10th percentile: 1.9662222862243652
20th percentile: 2.0167531967163086
30th percentile: 2.0602843284606935
40th percentile: 2.0968156814575196
50th percentile: 2.1333470344543457
60th percentile: 2.1399959564208983
70th percentile: 2.146644878387451
80th percentile: 2.2661179065704347
90th percentile: 2.4984150409698485
95th percentile: 2.6145636081695556
99th percentile: 2.707482461929321
mean time: 2.1943477153778077
Pipeline stage StressChecker completed in 12.33s
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 0.72s
Shutdown handler de-registered
chaiml-arli-24b-sft-exp_26998_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-arli-24b-sft-exp-26998-v1-profiler
Waiting for inference service chaiml-arli-24b-sft-exp-26998-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4662.68s
Shutdown handler de-registered
chaiml-arli-24b-sft-exp_26998_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-arli-24b-sft-exp_26998_v1 status is now torndown due to DeploymentManager action