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-qwen32b-sft-20k-28534-v1-mkmlizer
Waiting for job on chaiml-qwen32b-sft-20k-28534-v1-mkmlizer to finish
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: Downloaded to shared memory in 112.417s
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprjd1pxss, device:0
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: quantized model in 66.839s
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: Processed model ChaiML/qwen32b-sft-20k-ffsys-5e-exp1 in 179.258s
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/config.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/added_tokens.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/special_tokens_map.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/tokenizer_config.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/merges.txt
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/vocab.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/tokenizer.json
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/flywheel_model.2.safetensors
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v1/flywheel_model.1.safetensors
chaiml-qwen32b-sft-20k-28534-v1-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:19, 39.21it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:10, 75.43it/s]
Loading 0: 4%|▎ | 27/771 [00:00<00:08, 88.39it/s]
Loading 0: 5%|▍ | 37/771 [00:00<00:08, 90.03it/s]
Loading 0: 6%|▌ | 47/771 [00:00<00:14, 50.78it/s]
Loading 0: 7%|▋ | 54/771 [00:00<00:15, 46.36it/s]
Loading 0: 8%|▊ | 64/771 [00:01<00:12, 56.51it/s]
Loading 0: 10%|▉ | 75/771 [00:01<00:10, 67.75it/s]
Loading 0: 11%|█ | 84/771 [00:01<00:09, 72.91it/s]
Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 69.30it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 60.49it/s]
Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 58.40it/s]
Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 59.29it/s]
Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 70.32it/s]
Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 77.32it/s]
Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 83.02it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:07, 77.94it/s]
Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 54.94it/s]
Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 54.47it/s]
Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 56.30it/s]
Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 68.15it/s]
Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 77.59it/s]
Loading 0: 28%|██▊ | 217/771 [00:03<00:06, 83.17it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.83it/s]
Loading 0: 30%|███ | 234/771 [00:03<00:10, 53.29it/s]
Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 59.97it/s]
Loading 0: 33%|███▎ | 256/771 [00:03<00:07, 69.98it/s]
Loading 0: 35%|███▍ | 267/771 [00:04<00:06, 78.60it/s]
Loading 0: 36%|███▌ | 276/771 [00:04<00:06, 81.05it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 61.14it/s]
Loading 0: 38%|███▊ | 294/771 [00:04<00:09, 52.91it/s]
Loading 0: 39%|███▉ | 303/771 [00:19<03:58, 1.96it/s]
Loading 0: 40%|███▉ | 308/771 [00:20<03:13, 2.39it/s]
Loading 0: 41%|████ | 316/771 [00:20<02:15, 3.37it/s]
Loading 0: 42%|████▏ | 327/771 [00:20<01:24, 5.26it/s]
Loading 0: 43%|████▎ | 335/771 [00:20<01:01, 7.11it/s]
Loading 0: 45%|████▍ | 346/771 [00:20<00:43, 9.87it/s]
Loading 0: 46%|████▌ | 353/771 [00:20<00:36, 11.46it/s]
Loading 0: 47%|████▋ | 364/771 [00:21<00:24, 16.62it/s]
Loading 0: 49%|████▊ | 375/771 [00:21<00:17, 22.89it/s]
Loading 0: 50%|████▉ | 383/771 [00:21<00:13, 28.02it/s]
Loading 0: 51%|█████ | 391/771 [00:21<00:11, 31.94it/s]
Loading 0: 53%|█████▎ | 406/771 [00:21<00:10, 36.35it/s]
Loading 0: 54%|█████▎ | 413/771 [00:22<00:10, 35.28it/s]
Loading 0: 55%|█████▍ | 424/771 [00:22<00:07, 44.88it/s]
Loading 0: 56%|█████▋ | 435/771 [00:22<00:06, 54.52it/s]
Loading 0: 57%|█████▋ | 443/771 [00:22<00:05, 57.97it/s]
Loading 0: 58%|█████▊ | 451/771 [00:22<00:05, 59.38it/s]
Loading 0: 60%|██████ | 466/771 [00:22<00:05, 58.24it/s]
Loading 0: 61%|██████▏ | 473/771 [00:22<00:05, 49.69it/s]
Loading 0: 63%|██████▎ | 485/771 [00:23<00:04, 58.30it/s]
Loading 0: 64%|██████▍ | 497/771 [00:23<00:04, 65.28it/s]
Loading 0: 66%|██████▌ | 508/771 [00:23<00:03, 74.41it/s]
Loading 0: 67%|██████▋ | 518/771 [00:23<00:03, 79.66it/s]
Loading 0: 68%|██████▊ | 527/771 [00:23<00:04, 60.96it/s]
Loading 0: 69%|██████▉ | 535/771 [00:23<00:04, 57.30it/s]
Loading 0: 71%|███████ | 545/771 [00:23<00:03, 61.51it/s]
Loading 0: 72%|███████▏ | 557/771 [00:24<00:03, 68.37it/s]
Loading 0: 74%|███████▎ | 568/771 [00:24<00:02, 77.14it/s]
Loading 0: 75%|███████▌ | 579/771 [00:24<00:02, 84.68it/s]
Loading 0: 76%|███████▋ | 589/771 [00:24<00:03, 58.65it/s]
Loading 0: 77%|███████▋ | 597/771 [00:24<00:03, 56.56it/s]
Loading 0: 78%|███████▊ | 605/771 [00:24<00:02, 56.95it/s]
Loading 0: 80%|███████▉ | 616/771 [00:25<00:02, 67.37it/s]
Loading 0: 81%|████████ | 626/771 [00:40<00:02, 67.37it/s]
Loading 0: 81%|████████▏ | 627/771 [00:40<01:07, 2.15it/s]
Loading 0: 82%|████████▏ | 633/771 [00:40<00:51, 2.67it/s]
Loading 0: 84%|████████▍ | 646/771 [00:40<00:30, 4.15it/s]
Loading 0: 85%|████████▍ | 653/771 [00:41<00:23, 5.11it/s]
Loading 0: 86%|████████▌ | 664/771 [00:41<00:14, 7.53it/s]
Loading 0: 88%|████████▊ | 675/771 [00:41<00:08, 10.78it/s]
Loading 0: 89%|████████▊ | 683/771 [00:41<00:06, 13.77it/s]
Loading 0: 90%|████████▉ | 691/771 [00:41<00:04, 17.30it/s]
Loading 0: 92%|█████████▏| 706/771 [00:41<00:02, 24.18it/s]
Loading 0: 92%|█████████▏| 713/771 [00:42<00:02, 25.86it/s]
Loading 0: 94%|█████████▍| 725/771 [00:42<00:01, 34.19it/s]
Loading 0: 96%|█████████▌| 737/771 [00:42<00:00, 42.73it/s]
Loading 0: 97%|█████████▋| 749/771 [00:42<00:00, 51.08it/s]
Loading 0: 99%|█████████▉| 766/771 [00:50<00:01, 4.93it/s]
Job chaiml-qwen32b-sft-20k-28534-v1-mkmlizer completed after 218.95s with status: succeeded
Stopping job with name chaiml-qwen32b-sft-20k-28534-v1-mkmlizer
Pipeline stage MKMLizer completed in 219.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-sft-20k-28534-v1
Waiting for inference service chaiml-qwen32b-sft-20k-28534-v1 to be ready
Inference service chaiml-qwen32b-sft-20k-28534-v1 ready after 130.5419602394104s
Pipeline stage MKMLDeployer completed in 131.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.597169876098633s
Received healthy response to inference request in 3.046785831451416s
Received healthy response to inference request in 2.850543737411499s
Received healthy response to inference request in 3.0418927669525146s
Received healthy response to inference request in 3.0488805770874023s
5 requests
0 failed requests
5th percentile: 2.888813543319702
10th percentile: 2.9270833492279054
20th percentile: 3.0036229610443117
30th percentile: 3.042871379852295
40th percentile: 3.0448286056518556
50th percentile: 3.046785831451416
60th percentile: 3.0476237297058106
70th percentile: 3.0484616279602053
80th percentile: 3.1585384368896485
90th percentile: 3.3778541564941404
95th percentile: 3.4875120162963866
99th percentile: 3.5752383041381837
mean time: 3.117054557800293
Pipeline stage StressChecker completed in 17.10s
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 0.81s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.76s
Shutdown handler de-registered
chaiml-qwen32b-sft-20k-_28534_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3151.88s
Shutdown handler de-registered
chaiml-qwen32b-sft-20k-_28534_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sft-20k-_28534_v1 status is now torndown due to DeploymentManager action