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-cogito32b-newsft-71503-v1-mkmlizer
Waiting for job on chaiml-cogito32b-newsft-71503-v1-mkmlizer to finish
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Version: 0.27.1+vampire_v3 ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ belonging to: ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ║ ║
chaiml-cogito32b-newsft-71503-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
chaiml-cogito32b-newsft-71503-v1-mkmlizer: Downloaded to shared memory in 109.330s
chaiml-cogito32b-newsft-71503-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe3zntgq0, device:0
chaiml-cogito32b-newsft-71503-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
chaiml-cogito32b-newsft-71503-v1-mkmlizer: quantized model in 56.564s
chaiml-cogito32b-newsft-71503-v1-mkmlizer: Processed model ChaiML/cogito32b-newsft-blend-v1-exp1-1 in 165.894s
chaiml-cogito32b-newsft-71503-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-newsft-71503-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-newsft-71503-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/config.json
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/added_tokens.json
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/vocab.json
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/tokenizer.json
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/flywheel_model.2.safetensors
Failed to get response for submission blend_samof_2025-05-31: 'NoneType' object is not iterable
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/flywheel_model.1.safetensors
chaiml-cogito32b-newsft-71503-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-newsft-71503-v1/flywheel_model.0.safetensors
chaiml-cogito32b-newsft-71503-v1-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:19, 38.85it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:10, 74.97it/s]
Loading 0: 4%|▎ | 27/771 [00:00<00:08, 89.13it/s]
Loading 0: 5%|▍ | 37/771 [00:00<00:07, 92.56it/s]
Loading 0: 6%|▌ | 47/771 [00:00<00:12, 56.01it/s]
Loading 0: 7%|▋ | 55/771 [00:00<00:13, 53.52it/s]
Loading 0: 8%|▊ | 64/771 [00:01<00:11, 61.44it/s]
Loading 0: 10%|▉ | 75/771 [00:01<00:09, 72.25it/s]
Loading 0: 11%|█ | 84/771 [00:01<00:08, 76.42it/s]
Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 73.55it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 63.41it/s]
Loading 0: 15%|█▍ | 114/771 [00:01<00:10, 61.96it/s]
Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 59.61it/s]
Loading 0: 17%|█▋ | 132/771 [00:01<00:09, 70.36it/s]
Loading 0: 19%|█▊ | 144/771 [00:02<00:07, 82.19it/s]
Loading 0: 20%|██ | 155/771 [00:02<00:07, 83.25it/s]
Loading 0: 22%|██▏ | 166/771 [00:02<00:09, 63.11it/s]
Loading 0: 23%|██▎ | 174/771 [00:02<00:10, 54.75it/s]
Loading 0: 24%|██▍ | 185/771 [00:02<00:09, 60.71it/s]
Loading 0: 25%|██▌ | 196/771 [00:02<00:08, 70.47it/s]
Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 79.03it/s]
Loading 0: 28%|██▊ | 216/771 [00:03<00:06, 81.54it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 63.70it/s]
Loading 0: 30%|███ | 234/771 [00:03<00:09, 54.72it/s]
Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 61.91it/s]
Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 69.05it/s]
Loading 0: 35%|███▍ | 269/771 [00:03<00:06, 73.96it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 72.02it/s]
Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 61.05it/s]
Loading 0: 39%|███▉ | 303/771 [00:19<03:18, 2.36it/s]
Loading 0: 41%|████ | 313/771 [00:19<02:19, 3.28it/s]
Loading 0: 42%|████▏ | 321/771 [00:19<01:45, 4.28it/s]
Loading 0: 43%|████▎ | 329/771 [00:19<01:18, 5.65it/s]
Loading 0: 45%|████▍ | 346/771 [00:19<00:45, 9.44it/s]
Loading 0: 46%|████▌ | 353/771 [00:19<00:39, 10.66it/s]
Loading 0: 47%|████▋ | 365/771 [00:20<00:26, 15.13it/s]
Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.69it/s]
Loading 0: 50%|█████ | 389/771 [00:20<00:14, 27.28it/s]
Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 35.81it/s]
Loading 0: 54%|█████▎ | 414/771 [00:20<00:09, 36.05it/s]
Loading 0: 55%|█████▌ | 425/771 [00:20<00:08, 42.90it/s]
Loading 0: 57%|█████▋ | 437/771 [00:21<00:06, 51.08it/s]
Loading 0: 58%|█████▊ | 448/771 [00:21<00:05, 60.22it/s]
Loading 0: 59%|█████▉ | 458/771 [00:21<00:04, 67.18it/s]
Loading 0: 61%|██████ | 467/771 [00:21<00:05, 55.39it/s]
Loading 0: 62%|██████▏ | 475/771 [00:21<00:05, 53.03it/s]
Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 58.09it/s]
Loading 0: 64%|██████▍ | 497/771 [00:22<00:04, 66.27it/s]
Loading 0: 66%|██████▌ | 509/771 [00:22<00:03, 71.66it/s]
Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 70.19it/s]
Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 59.79it/s]
Loading 0: 71%|███████ | 544/771 [00:22<00:03, 67.17it/s]
Loading 0: 72%|███████▏ | 555/771 [00:22<00:02, 75.99it/s]
Loading 0: 73%|███████▎ | 564/771 [00:22<00:02, 79.13it/s]
Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 75.21it/s]
Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 65.23it/s]
Loading 0: 77%|███████▋ | 594/771 [00:23<00:03, 56.23it/s]
Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 62.19it/s]
Loading 0: 80%|████████ | 617/771 [00:23<00:02, 68.46it/s]
Loading 0: 81%|████████▏ | 627/771 [00:38<01:02, 2.31it/s]
Loading 0: 83%|████████▎ | 637/771 [00:38<00:41, 3.22it/s]
Loading 0: 84%|████████▍ | 646/771 [00:39<00:29, 4.26it/s]
Loading 0: 85%|████████▍ | 653/771 [00:39<00:22, 5.21it/s]
Loading 0: 86%|████████▌ | 664/771 [00:39<00:13, 7.70it/s]
Loading 0: 88%|████████▊ | 675/771 [00:39<00:08, 11.08it/s]
Loading 0: 89%|████████▉ | 685/771 [00:39<00:05, 15.07it/s]
Loading 0: 90%|█████████ | 694/771 [00:39<00:03, 19.26it/s]
Loading 0: 92%|█████████▏| 706/771 [00:40<00:02, 24.17it/s]
Loading 0: 93%|█████████▎| 714/771 [00:40<00:02, 26.63it/s]
Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 34.06it/s]
Loading 0: 96%|█████████▌| 737/771 [00:40<00:00, 42.82it/s]
Loading 0: 97%|█████████▋| 749/771 [00:40<00:00, 51.26it/s]
Loading 0: 99%|█████████▉| 766/771 [00:41<00:00, 43.89it/s]
Job chaiml-cogito32b-newsft-71503-v1-mkmlizer completed after 196.66s with status: succeeded
Stopping job with name chaiml-cogito32b-newsft-71503-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.18s
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-cogito32b-newsft-71503-v1
Waiting for inference service chaiml-cogito32b-newsft-71503-v1 to be ready
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
Inference service chaiml-cogito32b-newsft-71503-v1 ready after 130.58567428588867s
Pipeline stage MKMLDeployer completed in 131.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.190182685852051s
Received healthy response to inference request in 2.5275659561157227s
1 validation error for ABTest
__root__
exposed_user_rate must be between 0 and 1 (type=assertion_error)
Received healthy response to inference request in 2.8847415447235107s
Received healthy response to inference request in 2.6368730068206787s
Received healthy response to inference request in 2.6753032207489014s
5 requests
0 failed requests
5th percentile: 2.549427366256714
10th percentile: 2.5712887763977053
20th percentile: 2.6150115966796874
30th percentile: 2.644559049606323
40th percentile: 2.6599311351776125
50th percentile: 2.6753032207489014
60th percentile: 2.759078550338745
70th percentile: 2.842853879928589
80th percentile: 2.9458297729492187
90th percentile: 3.068006229400635
95th percentile: 3.129094457626343
99th percentile: 3.1779650402069093
mean time: 2.7829332828521727
Pipeline stage StressChecker completed in 15.45s
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 0.73s
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 0.68s
Shutdown handler de-registered
chaiml-cogito32b-newsft_71503_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cogito32b-newsft-71503-v1-profiler
Waiting for inference service chaiml-cogito32b-newsft-71503-v1-profiler to be ready
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 3210.12s
Shutdown handler de-registered
chaiml-cogito32b-newsft_71503_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-newsft_71503_v1 status is now torndown due to DeploymentManager action