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-ret-28950-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ret-28950-v1-mkmlizer to finish
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: Downloaded to shared memory in 28.753s
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_retune_512seq_ftgrok_36klenfilter_60ksamp_jul10_lora450_574 already exists in ChaiML
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp3_i8kpsk, device:0
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: quantized model in 19.977s
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_retune_512seq_ftgrok_36klenfilter_60ksamp_jul10_lora450_574 in 48.730s
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia/config.json
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-ret-28950-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-ret-28950-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 32.59it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.10it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:06, 44.26it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 44.48it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.10it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 44.37it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 44.23it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:05, 48.22it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:05, 46.53it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:05, 45.72it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:05, 42.74it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:05, 42.05it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 47.92it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 44.80it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 28.61it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 34.96it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 35.43it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:05, 37.00it/s]
Loading 0: 38%|███▊ | 110/291 [00:02<00:04, 39.14it/s]
Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 39.56it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 43.39it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:03, 41.42it/s]
Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 41.60it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 47.26it/s]
Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 42.75it/s]
Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 42.88it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 47.58it/s]
Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 47.89it/s]
Loading 0: 57%|█████▋ | 167/291 [00:03<00:03, 39.24it/s]
Loading 0: 60%|██████ | 175/291 [00:04<00:02, 48.48it/s]
Loading 0: 62%|██████▏ | 181/291 [00:04<00:02, 41.45it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 32.50it/s]
Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 34.50it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 35.31it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.16it/s]
Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 40.17it/s]
Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 41.11it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 46.81it/s]
Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 43.71it/s]
Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 43.66it/s]
Loading 0: 81%|████████▏ | 237/291 [00:05<00:01, 47.49it/s]
Loading 0: 83%|████████▎ | 242/291 [00:05<00:01, 47.20it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.41it/s]
Loading 0: 87%|████████▋ | 252/291 [00:05<00:00, 47.69it/s]
Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 37.33it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 46.43it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 43.97it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 43.54it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 40.73it/s]
Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 31.06it/s]
Job chaiml-llama-8b-nis-ret-28950-v1-mkmlizer completed after 74.86s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ret-28950-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.35s
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-llama-8b-nis-ret-28950-v1
Waiting for inference service chaiml-llama-8b-nis-ret-28950-v1 to be ready
Inference service chaiml-llama-8b-nis-ret-28950-v1 ready after 200.67759490013123s
Pipeline stage MKMLDeployer completed in 201.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.116683721542358s
Received healthy response to inference request in 2.3864314556121826s
Received healthy response to inference request in 2.7044641971588135s
Received healthy response to inference request in 3.209578037261963s
Received healthy response to inference request in 3.3932735919952393s
5 requests
0 failed requests
5th percentile: 2.4500380039215086
10th percentile: 2.513644552230835
20th percentile: 2.6408576488494875
30th percentile: 2.805486965179443
40th percentile: 3.007532501220703
50th percentile: 3.209578037261963
60th percentile: 3.2830562591552734
70th percentile: 3.356534481048584
80th percentile: 3.7379556179046634
90th percentile: 4.427319669723511
95th percentile: 4.772001695632934
99th percentile: 5.047747316360473
mean time: 3.3620862007141112
Pipeline stage StressChecker completed in 18.12s
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 0.86s
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-llama-8b-nis-ret_28950_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-nis-ret-28950-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-ret-28950-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Received signal 15, running shutdown handler
Shutdown handler de-registered
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 3173.91s
Shutdown handler de-registered
chaiml-llama-8b-nis-ret_28950_v1 status is now torndown due to DeploymentManager action