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-llama-8b-nis-ftt-14497-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer to finish
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: Downloaded to shared memory in 28.016s
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_fttry2_new1m_50ksamp_512seq_1ep_merged already exists in ChaiML
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpcld3br_3, device:0
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: quantized model in 19.848s
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_fttry2_new1m_50ksamp_512seq_1ep_merged in 47.864s
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-14497-v1/nvidia
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-14497-v1/nvidia/config.json
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-14497-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-14497-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-14497-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 35.86it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 57.83it/s]
Loading 0: 7%|▋ | 20/291 [00:00<00:04, 54.96it/s]
Loading 0: 9%|▉ | 26/291 [00:00<00:05, 52.40it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:06, 42.26it/s]
Loading 0: 13%|█▎ | 39/291 [00:00<00:05, 49.18it/s]
Loading 0: 15%|█▌ | 45/291 [00:00<00:04, 49.39it/s]
Loading 0: 18%|█▊ | 51/291 [00:01<00:05, 43.50it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 48.75it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 46.01it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 44.89it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 49.93it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 44.93it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 29.23it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 34.01it/s]
Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 35.96it/s]
Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 35.00it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.80it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:03, 43.91it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 43.32it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 49.36it/s]
Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 45.79it/s]
Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 45.35it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:02, 50.62it/s]
Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 46.60it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 44.17it/s]
Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 47.86it/s]
Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 46.00it/s]
Loading 0: 61%|██████ | 177/291 [00:04<00:02, 44.99it/s]
Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 43.79it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 32.15it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 33.44it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:02, 33.59it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.73it/s]
Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 40.23it/s]
Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 41.06it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 46.12it/s]
Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 44.54it/s]
Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 44.76it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 51.05it/s]
Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 46.60it/s]
Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 45.22it/s]
Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 47.85it/s]
Loading 0: 90%|████████▉ | 261/291 [00:05<00:00, 50.93it/s]
Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 46.14it/s]
Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 49.56it/s]
Loading 0: 96%|█████████▌| 279/291 [00:06<00:00, 49.11it/s]
Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 43.39it/s]
Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 31.88it/s]
Job chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer completed after 73.88s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ftt-14497-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-ftt-14497-v1
Waiting for inference service chaiml-llama-8b-nis-ftt-14497-v1 to be ready
Inference service chaiml-llama-8b-nis-ftt-14497-v1 ready after 220.78162288665771s
Pipeline stage MKMLDeployer completed in 221.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.650313138961792s
Received healthy response to inference request in 2.4083547592163086s
Received healthy response to inference request in 2.638864040374756s
Received healthy response to inference request in 5.073624134063721s
Received healthy response to inference request in 4.44324517250061s
5 requests
0 failed requests
5th percentile: 2.454456615447998
10th percentile: 2.5005584716796876
20th percentile: 2.5927621841430666
30th percentile: 2.841153860092163
40th percentile: 3.2457334995269775
50th percentile: 3.650313138961792
60th percentile: 3.967485952377319
70th percentile: 4.284658765792846
80th percentile: 4.569320964813232
90th percentile: 4.821472549438477
95th percentile: 4.947548341751099
99th percentile: 5.0484089756011965
mean time: 3.6428802490234373
Pipeline stage StressChecker completed in 19.62s
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 0.57s
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 0.88s
Shutdown handler de-registered
chaiml-llama-8b-nis-ftt_14497_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 0.13s
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-llama-8b-nis-ftt-14497-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-ftt-14497-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 3911.63s
Shutdown handler de-registered
chaiml-llama-8b-nis-ftt_14497_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-ftt_14497_v1 status is now torndown due to DeploymentManager action