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-mistral-nemo-dpo-8283-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8283-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: Downloaded to shared memory in 54.966s
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy3f3uf8c, device:0
chaiml-mistral-nemo-dpo-8283-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: quantized model in 37.538s
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v1-checkpoint-1104 in 92.505s
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1/config.json
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1/tokenizer.json
chaiml-mistral-nemo-dpo-8283-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8283-v1/flywheel_model.0.safetensors
Job chaiml-mistral-nemo-dpo-8283-v1-mkmlizer completed after 124.48s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8283-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-8283-v1
Waiting for inference service chaiml-mistral-nemo-dpo-8283-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-8283-v1 ready after 261.31458163261414s
Pipeline stage MKMLDeployer completed in 261.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8054850101470947s
Received healthy response to inference request in 1.5414574146270752s
Received healthy response to inference request in 1.2818107604980469s
Received healthy response to inference request in 1.211599588394165s
Received healthy response to inference request in 1.4149951934814453s
5 requests
0 failed requests
5th percentile: 1.2256418228149415
10th percentile: 1.2396840572357177
20th percentile: 1.2677685260772704
30th percentile: 1.3084476470947266
40th percentile: 1.3617214202880858
50th percentile: 1.4149951934814453
60th percentile: 1.4655800819396974
70th percentile: 1.5161649703979492
80th percentile: 1.5942629337310792
90th percentile: 1.699873971939087
95th percentile: 1.7526794910430907
99th percentile: 1.7949239063262938
mean time: 1.4510695934295654
Pipeline stage StressChecker completed in 8.65s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8283_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 2214.63s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8283_v1 status is now inactive due to auto deactivation removed underperforming models