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-qwen3-14base-sft-52255-v1-mkmlizer
Waiting for job on chaiml-qwen3-14base-sft-52255-v1-mkmlizer to finish
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Version: 0.29.8 ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ║ ║
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: Downloaded to shared memory in 51.387s
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: Checking if ChaiML/qwen3-14base-sftexp1-s1-40knewhighq-pred already exists in ChaiML
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc3a9qm7t, device:0
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: quantized model in 35.025s
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: Processed model ChaiML/qwen3-14base-sftexp1-s1-40knewhighq-pred in 86.413s
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/config.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/added_tokens.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/special_tokens_map.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/tokenizer_config.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/merges.txt
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/vocab.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/tokenizer.json
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/flywheel_model.1.safetensors
chaiml-qwen3-14base-sft-52255-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen3-14base-sft-52255-v1/nvidia/flywheel_model.0.safetensors
chaiml-qwen3-14base-sft-52255-v1-mkmlizer:
Loading 0: 0%| | 0/443 [00:00<?, ?it/s]
Loading 0: 1%| | 5/443 [00:00<00:14, 29.39it/s]
Loading 0: 3%|▎ | 14/443 [00:00<00:07, 56.08it/s]
Loading 0: 5%|▍ | 21/443 [00:00<00:07, 56.66it/s]
Loading 0: 6%|▋ | 28/443 [00:00<00:09, 44.69it/s]
Loading 0: 8%|▊ | 36/443 [00:00<00:07, 53.66it/s]
Loading 0: 10%|▉ | 43/443 [00:00<00:07, 54.60it/s]
Loading 0: 11%|█ | 49/443 [00:01<00:09, 43.06it/s]
Loading 0: 14%|█▍ | 61/443 [00:01<00:06, 60.40it/s]
Loading 0: 16%|█▌ | 69/443 [00:01<00:10, 37.31it/s]
Loading 0: 17%|█▋ | 75/443 [00:01<00:08, 40.97it/s]
Loading 0: 18%|█▊ | 81/443 [00:01<00:08, 42.12it/s]
Loading 0: 20%|█▉ | 87/443 [00:01<00:09, 38.82it/s]
Loading 0: 21%|██ | 94/443 [00:02<00:07, 44.09it/s]
Loading 0: 23%|██▎ | 100/443 [00:02<00:08, 41.37it/s]
Loading 0: 24%|██▎ | 105/443 [00:02<00:07, 42.75it/s]
Loading 0: 25%|██▌ | 111/443 [00:02<00:07, 44.33it/s]
Loading 0: 26%|██▌ | 116/443 [00:02<00:07, 45.16it/s]
Loading 0: 28%|██▊ | 122/443 [00:02<00:06, 46.46it/s]
Loading 0: 29%|██▊ | 127/443 [00:02<00:06, 47.23it/s]
Loading 0: 30%|███ | 133/443 [00:02<00:06, 47.23it/s]
Loading 0: 31%|███ | 138/443 [00:03<00:06, 46.68it/s]
Loading 0: 32%|███▏ | 143/443 [00:03<00:09, 32.11it/s]
Loading 0: 33%|███▎ | 148/443 [00:03<00:09, 32.21it/s]
Loading 0: 35%|███▌ | 157/443 [00:03<00:06, 42.32it/s]
Loading 0: 37%|███▋ | 162/443 [00:03<00:06, 42.37it/s]
Loading 0: 38%|███▊ | 168/443 [00:03<00:06, 45.49it/s]
Loading 0: 39%|███▉ | 173/443 [00:03<00:06, 44.62it/s]
Loading 0: 40%|████ | 179/443 [00:04<00:05, 46.05it/s]
Loading 0: 42%|████▏ | 184/443 [00:04<00:05, 44.94it/s]
Loading 0: 43%|████▎ | 190/443 [00:04<00:05, 46.90it/s]
Loading 0: 44%|████▍ | 195/443 [00:04<00:05, 44.86it/s]
Loading 0: 45%|████▌ | 201/443 [00:04<00:05, 45.77it/s]
Loading 0: 47%|████▋ | 206/443 [00:04<00:05, 44.91it/s]
Loading 0: 48%|████▊ | 212/443 [00:04<00:04, 47.67it/s]
Loading 0: 49%|████▉ | 217/443 [00:04<00:04, 46.18it/s]
Loading 0: 51%|█████ | 226/443 [00:04<00:03, 57.05it/s]
Loading 0: 52%|█████▏ | 232/443 [00:05<00:06, 32.36it/s]
Loading 0: 53%|█████▎ | 237/443 [00:05<00:06, 32.38it/s]
Loading 0: 55%|█████▌ | 245/443 [00:05<00:05, 39.26it/s]
Loading 0: 56%|█████▋ | 250/443 [00:05<00:04, 39.61it/s]
Loading 0: 58%|█████▊ | 256/443 [00:05<00:04, 42.33it/s]
Loading 0: 59%|█████▉ | 261/443 [00:06<00:04, 41.35it/s]
Loading 0: 60%|██████ | 267/443 [00:06<00:04, 43.73it/s]
Loading 0: 61%|██████▏ | 272/443 [00:06<00:03, 43.19it/s]
Loading 0: 63%|██████▎ | 278/443 [00:06<00:03, 45.72it/s]
Loading 0: 64%|██████▍ | 283/443 [00:06<00:03, 45.38it/s]
Loading 0: 65%|██████▌ | 289/443 [00:06<00:03, 47.61it/s]
Loading 0: 66%|██████▋ | 294/443 [00:06<00:03, 46.33it/s]
Loading 0: 67%|██████▋ | 299/443 [00:06<00:03, 45.46it/s]
Loading 0: 69%|██████▊ | 304/443 [00:06<00:03, 45.59it/s]
Loading 0: 70%|██████▉ | 309/443 [00:07<00:04, 32.60it/s]
Loading 0: 71%|███████ | 313/443 [00:07<00:04, 31.23it/s]
Loading 0: 73%|███████▎ | 322/443 [00:07<00:02, 40.98it/s]
Loading 0: 74%|███████▍ | 327/443 [00:07<00:02, 40.75it/s]
Loading 0: 75%|███████▍ | 332/443 [00:07<00:02, 42.78it/s]
Loading 0: 76%|███████▌ | 337/443 [00:07<00:02, 39.45it/s]
Loading 0: 78%|███████▊ | 344/443 [00:07<00:02, 44.27it/s]
Loading 0: 79%|███████▉ | 349/443 [00:08<00:02, 44.10it/s]
Loading 0: 80%|████████ | 355/443 [00:08<00:01, 46.04it/s]
Loading 0: 81%|████████▏ | 360/443 [00:08<00:01, 45.15it/s]
Loading 0: 83%|████████▎ | 366/443 [00:08<00:01, 46.93it/s]
Loading 0: 84%|████████▎ | 371/443 [00:08<00:01, 45.84it/s]
Loading 0: 85%|████████▌ | 377/443 [00:08<00:01, 47.80it/s]
Loading 0: 86%|████████▌ | 382/443 [00:08<00:01, 45.88it/s]
Loading 0: 88%|████████▊ | 389/443 [00:08<00:01, 51.80it/s]
Loading 0: 88%|████████▊ | 392/443 [00:22<00:00, 51.80it/s]
Loading 0: 89%|████████▊ | 393/443 [00:22<00:39, 1.25it/s]
Loading 0: 90%|████████▉ | 397/443 [00:23<00:28, 1.62it/s]
Loading 0: 91%|█████████ | 402/443 [00:23<00:18, 2.21it/s]
Loading 0: 93%|█████████▎| 411/443 [00:23<00:08, 3.84it/s]
Loading 0: 94%|█████████▍| 416/443 [00:23<00:05, 5.01it/s]
Loading 0: 95%|█████████▌| 422/443 [00:23<00:03, 6.95it/s]
Loading 0: 96%|█████████▋| 427/443 [00:23<00:01, 8.96it/s]
Loading 0: 98%|█████████▊| 433/443 [00:24<00:00, 12.09it/s]
Loading 0: 99%|█████████▉| 438/443 [00:24<00:00, 15.02it/s]
Job chaiml-qwen3-14base-sft-52255-v1-mkmlizer completed after 115.31s with status: succeeded
Stopping job with name chaiml-qwen3-14base-sft-52255-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen3-14base-sft-52255-v1
Waiting for inference service chaiml-qwen3-14base-sft-52255-v1 to be ready
Inference service chaiml-qwen3-14base-sft-52255-v1 ready after 220.8187882900238s
Pipeline stage MKMLDeployer completed in 221.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5642144680023193s
Received healthy response to inference request in 1.8482036590576172s
Received healthy response to inference request in 1.781830072402954s
Received healthy response to inference request in 2.0606508255004883s
Received healthy response to inference request in 1.931471824645996s
5 requests
0 failed requests
5th percentile: 1.7951047897338868
10th percentile: 1.8083795070648194
20th percentile: 1.8349289417266845
30th percentile: 1.864857292175293
40th percentile: 1.8981645584106446
50th percentile: 1.931471824645996
60th percentile: 1.983143424987793
70th percentile: 2.03481502532959
80th percentile: 2.1613635540008547
90th percentile: 2.362789011001587
95th percentile: 2.463501739501953
99th percentile: 2.544071922302246
mean time: 2.037274169921875
Pipeline stage StressChecker completed in 12.29s
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 0.72s
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-qwen3-14base-sft_52255_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5854.62s
Shutdown handler de-registered
chaiml-qwen3-14base-sft_52255_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen3-14base-sft_52255_v1 status is now torndown due to DeploymentManager action