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-20250611-retune-50947-v3-mkmlizer
Waiting for job on chaiml-20250611-retune-50947-v3-mkmlizer to finish
chaiml-20250611-retune-50947-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Version: 0.29.1 ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ belonging to: ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-20250611-retune-50947-v3-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250611-retune-50947-v3-mkmlizer: Downloaded to shared memory in 24.510s
chaiml-20250611-retune-50947-v3-mkmlizer: Checking if ChaiML/20250611_retune_long_user_messages already exists in ChaiML
chaiml-20250611-retune-50947-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp9w0h5f7g, device:0
chaiml-20250611-retune-50947-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250611-retune-50947-v3-mkmlizer: quantized model in 19.502s
chaiml-20250611-retune-50947-v3-mkmlizer: Processed model ChaiML/20250611_retune_long_user_messages in 44.012s
chaiml-20250611-retune-50947-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250611-retune-50947-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250611-retune-50947-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3
chaiml-20250611-retune-50947-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3/special_tokens_map.json
chaiml-20250611-retune-50947-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3/config.json
chaiml-20250611-retune-50947-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3/tokenizer_config.json
chaiml-20250611-retune-50947-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3/tokenizer.json
chaiml-20250611-retune-50947-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v3/flywheel_model.0.safetensors
chaiml-20250611-retune-50947-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.25it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 56.48it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.12it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 44.12it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.53it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 46.10it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 44.70it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 49.91it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 44.39it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 42.43it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 47.89it/s]
Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 47.97it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 39.43it/s]
Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 30.39it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 29.82it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 37.02it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 37.61it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.28it/s]
Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 43.12it/s]
Loading 0: 40%|███▉ | 116/291 [00:02<00:04, 43.41it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.72it/s]
Loading 0: 43%|████▎ | 126/291 [00:02<00:03, 44.81it/s]
Loading 0: 45%|████▌ | 131/291 [00:03<00:04, 37.56it/s]
Loading 0: 47%|████▋ | 138/291 [00:03<00:03, 44.93it/s]
Loading 0: 49%|████▉ | 143/291 [00:03<00:03, 45.81it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 46.26it/s]
Loading 0: 53%|█████▎ | 153/291 [00:03<00:02, 46.14it/s]
Loading 0: 54%|█████▍ | 158/291 [00:03<00:03, 39.01it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 47.76it/s]
Loading 0: 59%|█████▉ | 172/291 [00:04<00:02, 43.74it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 48.52it/s]
Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 50.38it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 31.04it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 33.49it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 37.90it/s]
Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 37.35it/s]
Loading 0: 73%|███████▎ | 213/291 [00:05<00:02, 38.27it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 43.75it/s]
Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 41.26it/s]
Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 40.23it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 45.55it/s]
Loading 0: 84%|████████▎ | 243/291 [00:05<00:01, 46.44it/s]
Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 38.39it/s]
Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 46.17it/s]
Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 43.14it/s]
Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 42.18it/s]
Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 47.40it/s]
Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 42.88it/s]
Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 42.97it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 31.58it/s]
Job chaiml-20250611-retune-50947-v3-mkmlizer completed after 73.77s with status: succeeded
Stopping job with name chaiml-20250611-retune-50947-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-20250611-retune-50947-v3
Waiting for inference service chaiml-20250611-retune-50947-v3 to be ready
Inference service chaiml-20250611-retune-50947-v3 ready after 120.56220316886902s
Pipeline stage MKMLDeployer completed in 121.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.280953884124756s
Received healthy response to inference request in 4.062910556793213s
Received healthy response to inference request in 5.573237657546997s
Received healthy response to inference request in 6.050230503082275s
Received healthy response to inference request in 2.8646090030670166s
5 requests
0 failed requests
5th percentile: 2.9478779792785645
10th percentile: 3.0311469554901125
20th percentile: 3.197684907913208
30th percentile: 3.4373452186584474
40th percentile: 3.75012788772583
50th percentile: 4.062910556793213
60th percentile: 4.667041397094726
70th percentile: 5.2711722373962395
80th percentile: 5.668636226654053
90th percentile: 5.859433364868164
95th percentile: 5.954831933975219
99th percentile: 6.031150789260864
mean time: 4.366388320922852
%s, retrying in %s seconds...
Received healthy response to inference request in 6.551198720932007s
Received healthy response to inference request in 5.137822866439819s
Received healthy response to inference request in 4.983991861343384s
Received healthy response to inference request in 1.4753272533416748s
Received healthy response to inference request in 2.9570579528808594s
5 requests
0 failed requests
5th percentile: 1.7716733932495117
10th percentile: 2.0680195331573485
20th percentile: 2.6607118129730223
30th percentile: 3.3624447345733643
40th percentile: 4.173218297958374
50th percentile: 4.983991861343384
60th percentile: 5.045524263381958
70th percentile: 5.107056665420532
80th percentile: 5.420498037338257
90th percentile: 5.985848379135132
95th percentile: 6.268523550033569
99th percentile: 6.494663686752319
mean time: 4.221079730987549
%s, retrying in %s seconds...
Received healthy response to inference request in 3.7974836826324463s
Received healthy response to inference request in 2.5833075046539307s
Received healthy response to inference request in 3.1128249168395996s
Received healthy response to inference request in 3.1996679306030273s
Received healthy response to inference request in 4.7819108963012695s
5 requests
0 failed requests
5th percentile: 2.6892109870910645
10th percentile: 2.7951144695281984
20th percentile: 3.0069214344024657
30th percentile: 3.130193519592285
40th percentile: 3.164930725097656
50th percentile: 3.1996679306030273
60th percentile: 3.438794231414795
70th percentile: 3.6779205322265622
80th percentile: 3.994369125366211
90th percentile: 4.38814001083374
95th percentile: 4.585025453567504
99th percentile: 4.7425338077545165
mean time: 3.4950389862060547
Pipeline stage StressChecker completed in 64.18s
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 0.87s
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 0.70s
Shutdown handler de-registered
chaiml-20250611-retune-_50947_v3 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-50947-v3-profiler
Waiting for inference service chaiml-20250611-retune-50947-v3-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 8600.80s
Shutdown handler de-registered
chaiml-20250611-retune-_50947_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250611-retune-_50947_v3 status is now torndown due to DeploymentManager action