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 cgato-nemo-12b-thespice-8302-v1-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-8302-v1-mkmlizer to finish
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ _____ __ __ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ /___/ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ Version: 0.11.12 ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ https://mk1.ai ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ belonging to: ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ║ ║
cgato-nemo-12b-thespice-8302-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-thespice-8302-v1-mkmlizer: Downloaded to shared memory in 47.060s
cgato-nemo-12b-thespice-8302-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe_4ibuft, device:0
cgato-nemo-12b-thespice-8302-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
cgato-nemo-12b-thespice-8302-v1-mkmlizer: quantized model in 36.378s
cgato-nemo-12b-thespice-8302-v1-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2 in 83.438s
cgato-nemo-12b-thespice-8302-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-8302-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-8302-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1
cgato-nemo-12b-thespice-8302-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1/config.json
cgato-nemo-12b-thespice-8302-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1/special_tokens_map.json
cgato-nemo-12b-thespice-8302-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1/tokenizer_config.json
cgato-nemo-12b-thespice-8302-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1/tokenizer.json
cgato-nemo-12b-thespice-8302-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-8302-v1/flywheel_model.0.safetensors
Job cgato-nemo-12b-thespice-8302-v1-mkmlizer completed after 114.96s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-8302-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.54s
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 cgato-nemo-12b-thespice-8302-v1
Waiting for inference service cgato-nemo-12b-thespice-8302-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service cgato-nemo-12b-thespice-8302-v1 ready after 120.49739480018616s
Pipeline stage MKMLDeployer completed in 121.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.937962055206299s
Received healthy response to inference request in 1.6532683372497559s
Received healthy response to inference request in 1.906273365020752s
Received healthy response to inference request in 1.6595220565795898s
Received healthy response to inference request in 1.8117704391479492s
5 requests
0 failed requests
5th percentile: 1.6545190811157227
10th percentile: 1.6557698249816895
20th percentile: 1.658271312713623
30th percentile: 1.6899717330932618
40th percentile: 1.7508710861206054
50th percentile: 1.8117704391479492
60th percentile: 1.8495716094970702
70th percentile: 1.8873727798461915
80th percentile: 2.1126111030578616
90th percentile: 2.52528657913208
95th percentile: 2.731624317169189
99th percentile: 2.896694507598877
mean time: 1.9937592506408692
Pipeline stage StressChecker completed in 11.38s
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 2.31s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_8302_v1 status is now deployed due to DeploymentManager action
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://meta-llama-llama-guard-3-8b-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
cgato-nemo-12b-thespice-_8302_v1 status is now inactive due to auto deactivation removed underperforming models