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-20241010-tie-5991-v7-mkmlizer
Waiting for job on chaiml-nemo-20241010-tie-5991-v7-mkmlizer to finish
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ║ ║
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: Downloaded to shared memory in 47.984s
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpusbv2esa, device:0
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: quantized model in 36.049s
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 84.033s
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7/config.json
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7/special_tokens_map.json
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7/tokenizer_config.json
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7/tokenizer.json
chaiml-nemo-20241010-tie-5991-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-5991-v7/flywheel_model.0.safetensors
Job chaiml-nemo-20241010-tie-5991-v7-mkmlizer completed after 114.88s with status: succeeded
Stopping job with name chaiml-nemo-20241010-tie-5991-v7-mkmlizer
Pipeline stage MKMLizer completed in 115.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-tie-5991-v7
Waiting for inference service chaiml-nemo-20241010-tie-5991-v7 to be ready
Inference service chaiml-nemo-20241010-tie-5991-v7 ready after 150.7639307975769s
Pipeline stage MKMLDeployer completed in 151.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.901848316192627s
Received healthy response to inference request in 1.3916325569152832s
Received healthy response to inference request in 1.5794949531555176s
Received healthy response to inference request in 1.728999137878418s
Received healthy response to inference request in 1.409475326538086s
5 requests
0 failed requests
5th percentile: 1.3952011108398437
10th percentile: 1.3987696647644043
20th percentile: 1.4059067726135255
30th percentile: 1.4434792518615722
40th percentile: 1.511487102508545
50th percentile: 1.5794949531555176
60th percentile: 1.6392966270446778
70th percentile: 1.6990983009338378
80th percentile: 1.7635689735412599
90th percentile: 1.8327086448669434
95th percentile: 1.867278480529785
99th percentile: 1.8949343490600585
mean time: 1.6022900581359862
Pipeline stage StressChecker completed in 9.74s
Shutdown handler de-registered
chaiml-nemo-20241010-tie_5991_v7 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-tie_5991_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-tie_5991_v7 status is now torndown due to DeploymentManager action