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-nemo-20241016-bre-9520-v4-mkmlizer
Waiting for job on chaiml-nemo-20241016-bre-9520-v4-mkmlizer to finish
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ /___/ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ║ ║
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: Downloaded to shared memory in 28.931s
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkehjydlc, device:0
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: quantized model in 38.263s
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: Processed model ChaiML/nemo-20241016-breadcrumbs-remerge_v1_5merge-albert in 67.194s
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4/config.json
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4/special_tokens_map.json
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4/tokenizer_config.json
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4/tokenizer.json
chaiml-nemo-20241016-bre-9520-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241016-bre-9520-v4/flywheel_model.0.safetensors
Job chaiml-nemo-20241016-bre-9520-v4-mkmlizer completed after 114.33s with status: succeeded
Stopping job with name chaiml-nemo-20241016-bre-9520-v4-mkmlizer
Pipeline stage MKMLizer completed in 114.92s
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 chaiml-nemo-20241016-bre-9520-v4
Waiting for inference service chaiml-nemo-20241016-bre-9520-v4 to be ready
Inference service chaiml-nemo-20241016-bre-9520-v4 ready after 180.77910494804382s
Pipeline stage MKMLDeployer completed in 181.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1133155822753906s
Received healthy response to inference request in 1.4147660732269287s
Received healthy response to inference request in 1.6506257057189941s
Received healthy response to inference request in 1.3290021419525146s
Received healthy response to inference request in 1.4566969871520996s
5 requests
0 failed requests
5th percentile: 1.3461549282073975
10th percentile: 1.3633077144622803
20th percentile: 1.397613286972046
30th percentile: 1.423152256011963
40th percentile: 1.4399246215820312
50th percentile: 1.4566969871520996
60th percentile: 1.5342684745788575
70th percentile: 1.6118399620056152
80th percentile: 1.7431636810302735
90th percentile: 1.928239631652832
95th percentile: 2.0207776069641112
99th percentile: 2.0948079872131347
mean time: 1.5928812980651856
Pipeline stage StressChecker completed in 9.53s
Shutdown handler de-registered
chaiml-nemo-20241016-bre_9520_v4 status is now deployed due to DeploymentManager action
chaiml-nemo-20241016-bre_9520_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241016-bre_9520_v4 status is now torndown due to DeploymentManager action