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 delta-vector-control-8b-v1-1-v2-mkmlizer
Waiting for job on delta-vector-control-8b-v1-1-v2-mkmlizer to finish
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
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
delta-vector-control-8b-v1-1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ _____ __ __ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ /___/ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ Version: 0.11.12 ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ https://mk1.ai ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ belonging to: ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ Chai Research Corp. ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ║ ║
delta-vector-control-8b-v1-1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
delta-vector-control-8b-v1-1-v2-mkmlizer: Downloaded to shared memory in 22.670s
delta-vector-control-8b-v1-1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuvjz69nj, device:0
delta-vector-control-8b-v1-1-v2-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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
delta-vector-control-8b-v1-1-v2-mkmlizer: quantized model in 25.391s
delta-vector-control-8b-v1-1-v2-mkmlizer: Processed model Delta-Vector/Control-8B-V1.1 in 48.061s
delta-vector-control-8b-v1-1-v2-mkmlizer: creating bucket guanaco-mkml-models
delta-vector-control-8b-v1-1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
delta-vector-control-8b-v1-1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2
delta-vector-control-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2/config.json
delta-vector-control-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2/special_tokens_map.json
delta-vector-control-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2/tokenizer_config.json
delta-vector-control-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2/tokenizer.json
delta-vector-control-8b-v1-1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/delta-vector-control-8b-v1-1-v2/flywheel_model.0.safetensors
Job delta-vector-control-8b-v1-1-v2-mkmlizer completed after 73.4s with status: succeeded
Stopping job with name delta-vector-control-8b-v1-1-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.96s
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 delta-vector-control-8b-v1-1-v2
Waiting for inference service delta-vector-control-8b-v1-1-v2 to be ready
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
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
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
Inference service delta-vector-control-8b-v1-1-v2 ready after 150.545254945755s
Pipeline stage MKMLDeployer completed in 151.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8162040710449219s
Received healthy response to inference request in 1.4448473453521729s
Received healthy response to inference request in 1.43613600730896s
Received healthy response to inference request in 1.4406180381774902s
Received healthy response to inference request in 1.293708086013794s
5 requests
0 failed requests
5th percentile: 1.3221936702728272
10th percentile: 1.3506792545318604
20th percentile: 1.4076504230499267
30th percentile: 1.437032413482666
40th percentile: 1.4388252258300782
50th percentile: 1.4406180381774902
60th percentile: 1.4423097610473632
70th percentile: 1.4440014839172364
80th percentile: 1.5191186904907228
90th percentile: 1.6676613807678222
95th percentile: 1.741932725906372
99th percentile: 1.8013498020172118
mean time: 1.4863027095794679
Pipeline stage StressChecker completed in 8.86s
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 2.45s
Shutdown handler de-registered
delta-vector-control-8b-v1-1_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2193.85s
Shutdown handler de-registered
delta-vector-control-8b-v1-1_v2 status is now inactive due to auto deactivation removed underperforming models