Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bq-e-v0-c2-v1-mkmlizer
Waiting for job on cycy233-l3-bq-e-v0-c2-v1-mkmlizer to finish
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ║ ║
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: Downloaded to shared memory in 34.267s
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxn2_vmlc, device:0
cycy233-l3-bq-e-v0-c2-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
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
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: quantized model in 25.546s
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: Processed model cycy233/L3-bq-e-v0-c2 in 59.813s
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1/special_tokens_map.json
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1/config.json
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1/tokenizer_config.json
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1/tokenizer.json
cycy233-l3-bq-e-v0-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bq-e-v0-c2-v1/flywheel_model.0.safetensors
Job cycy233-l3-bq-e-v0-c2-v1-mkmlizer completed after 85.58s with status: succeeded
Stopping job with name cycy233-l3-bq-e-v0-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bq-e-v0-c2-v1
Waiting for inference service cycy233-l3-bq-e-v0-c2-v1 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
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
Failed to get response for submission blend_koran_2024-08-16: ('http://neversleep-noromaid-v0-8068-v149-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service cycy233-l3-bq-e-v0-c2-v1 ready after 150.52564597129822s
Pipeline stage ISVCDeployer completed in 151.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.060580253601074s
Received healthy response to inference request in 1.361750602722168s
Received healthy response to inference request in 4.349916696548462s
Received healthy response to inference request in 1.3950557708740234s
Received healthy response to inference request in 1.951542615890503s
5 requests
0 failed requests
5th percentile: 1.3684116363525392
10th percentile: 1.3750726699829101
20th percentile: 1.3883947372436523
30th percentile: 1.5063531398773193
40th percentile: 1.7289478778839111
50th percentile: 1.951542615890503
60th percentile: 1.9951576709747314
70th percentile: 2.03877272605896
80th percentile: 2.518447542190552
90th percentile: 3.434182119369507
95th percentile: 3.892049407958984
99th percentile: 4.258343238830566
mean time: 2.223769187927246
Pipeline stage StressChecker completed in 12.18s
cycy233-l3-bq-e-v0-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bq-e-v0-c2_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bq-e-v0-c2_v1 status is now torndown due to DeploymentManager action
cycy233-l3-bq-e-v0-c2_v1 status is now torndown due to DeploymentManager action