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-slerp-esao-b-5695-v3-mkmlizer
Waiting for job on chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer to finish
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ /___/ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ belonging to: ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ║ ║
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: Downloaded to shared memory in 46.638s
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn_gwh5_s, device:0
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: quantized model in 40.089s
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: Processed model ChaiML/nemo-slerp-esao-be-albert in 86.727s
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-slerp-esao-b-5695-v3
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-slerp-esao-b-5695-v3/special_tokens_map.json
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-slerp-esao-b-5695-v3/config.json
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-slerp-esao-b-5695-v3/tokenizer_config.json
chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-slerp-esao-b-5695-v3/tokenizer.json
Job chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer completed after 175.09s with status: succeeded
Stopping job with name chaiml-nemo-slerp-esao-b-5695-v3-mkmlizer
Pipeline stage MKMLizer completed in 179.58s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-slerp-esao-b-5695-v3
Waiting for inference service chaiml-nemo-slerp-esao-b-5695-v3 to be ready
Failed to get response for submission chaiml-elo-alignment-run-3_v44: ('http://chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33504->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-nemo-slerp-esao-b-5695-v3 ready after 120.41363453865051s
Pipeline stage MKMLDeployer completed in 121.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.363560676574707s
Received healthy response to inference request in 1.9255235195159912s
Received healthy response to inference request in 1.692197322845459s
Received healthy response to inference request in 1.7279696464538574s
Received healthy response to inference request in 1.4010725021362305s
5 requests
0 failed requests
5th percentile: 1.4592974662780762
10th percentile: 1.517522430419922
20th percentile: 1.6339723587036132
30th percentile: 1.6993517875671387
40th percentile: 1.713660717010498
50th percentile: 1.7279696464538574
60th percentile: 1.806991195678711
70th percentile: 1.8860127449035644
80th percentile: 2.0131309509277346
90th percentile: 2.1883458137512206
95th percentile: 2.2759532451629636
99th percentile: 2.3460391902923585
mean time: 1.8220647335052491
Pipeline stage StressChecker completed in 10.49s
Shutdown handler de-registered
chaiml-nemo-slerp-esao-b_5695_v3 status is now deployed due to DeploymentManager action
chaiml-nemo-slerp-esao-b_5695_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-slerp-esao-b_5695_v3 status is now deployed due to admin request
chaiml-nemo-slerp-esao-b_5695_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-nemo-slerp-esao-b_5695_v3
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service chaiml-nemo-slerp-esao-b-5695-v3 is running
Tearing down inference service chaiml-nemo-slerp-esao-b-5695-v3
Service chaiml-nemo-slerp-esao-b-5695-v3 has been torndown
Pipeline stage MKMLDeleter completed in 3.55s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-nemo-slerp-esao-b-5695-v3/config.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-slerp-esao-b-5695-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-nemo-slerp-esao-b-5695-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-slerp-esao-b-5695-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-nemo-slerp-esao-b-5695-v3/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 1.93s
Shutdown handler de-registered
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-slerp-esao-b_5695_v3 status is now torndown due to DeploymentManager action