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-llama8b-60m-rm-p-20581-v1-mkmlizer
Waiting for job on chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer to finish
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ belonging to: ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ║ ║
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: Downloaded to shared memory in 45.125s
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: Checking if ChaiML/llama8b-60m-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512f already exists in ChaiML
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpj_3v7ly8, device:0
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: quantized model in 19.992s
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: Processed model ChaiML/llama8b-60m-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512f in 65.117s
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-60m-rm-p-20581-v1/special_tokens_map.json
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-60m-rm-p-20581-v1/config.json
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-60m-rm-p-20581-v1/tokenizer_config.json
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-60m-rm-p-20581-v1/tokenizer.json
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama8b-60m-rm-p-20581-v1/flywheel_model.0.safetensors
chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 33.35it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 53.79it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 45.49it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 43.59it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 49.02it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 43.15it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 42.79it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:05, 47.16it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:05, 47.18it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 47.74it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:05, 43.97it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:05, 43.00it/s]
Loading 0: 26%|██▌ | 75/291 [00:01<00:04, 46.58it/s]
Loading 0: 27%|██▋ | 80/291 [00:01<00:04, 44.58it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:06, 30.21it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:05, 34.07it/s]
Loading 0: 33%|███▎ | 95/291 [00:02<00:06, 31.58it/s]
Loading 0: 35%|███▌ | 102/291 [00:02<00:04, 39.49it/s]
Loading 0: 37%|███▋ | 107/291 [00:02<00:04, 38.66it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.54it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:04, 38.93it/s]
Loading 0: 42%|████▏ | 123/291 [00:03<00:04, 38.62it/s]
Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 44.31it/s]
Loading 0: 46%|████▋ | 135/291 [00:03<00:03, 45.41it/s]
Loading 0: 48%|████▊ | 140/291 [00:03<00:04, 37.17it/s]
Loading 0: 51%|█████ | 147/291 [00:03<00:03, 44.54it/s]
Loading 0: 52%|█████▏ | 152/291 [00:03<00:03, 44.00it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 44.77it/s]
Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 45.43it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 37.77it/s]
Loading 0: 60%|█████▉ | 174/291 [00:04<00:02, 45.26it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 43.89it/s]
Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 43.07it/s]
Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 25.84it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 28.61it/s]
Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 36.30it/s]
Loading 0: 71%|███████ | 206/291 [00:05<00:02, 38.14it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 39.49it/s]
Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 41.87it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 36.01it/s]
Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 43.81it/s]
Loading 0: 80%|████████ | 233/291 [00:05<00:01, 43.41it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 44.18it/s]
Loading 0: 84%|████████▍ | 244/291 [00:06<00:01, 41.57it/s]
Loading 0: 86%|████████▌ | 249/291 [00:06<00:01, 40.97it/s]
Loading 0: 88%|████████▊ | 255/291 [00:06<00:00, 45.63it/s]
Loading 0: 89%|████████▉ | 260/291 [00:06<00:00, 45.38it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 45.72it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 42.30it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 40.91it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 38.12it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.51it/s]
Job chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer completed after 84.2s with status: succeeded
Stopping job with name chaiml-llama8b-60m-rm-p-20581-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama8b-60m-rm-p-20581-v1
Waiting for inference service chaiml-llama8b-60m-rm-p-20581-v1 to be ready
Inference service chaiml-llama8b-60m-rm-p-20581-v1 ready after 120.47333335876465s
Pipeline stage MKMLDeployer completed in 121.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1912543773651123s
Received healthy response to inference request in 2.1784303188323975s
Received healthy response to inference request in 3.7643675804138184s
Received healthy response to inference request in 3.5071427822113037s
Received healthy response to inference request in 2.4073476791381836s
5 requests
0 failed requests
5th percentile: 2.224213790893555
10th percentile: 2.269997262954712
20th percentile: 2.361564207077026
30th percentile: 2.5641290187835692
40th percentile: 2.877691698074341
50th percentile: 3.1912543773651123
60th percentile: 3.317609739303589
70th percentile: 3.4439651012420653
80th percentile: 3.558587741851807
90th percentile: 3.6614776611328126
95th percentile: 3.7129226207733153
99th percentile: 3.7540785884857177
mean time: 3.009708547592163
Pipeline stage StressChecker completed in 17.12s
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 0.74s
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 0.74s
Shutdown handler de-registered
chaiml-llama8b-60m-rm-p_20581_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-60m-rm-p-20581-v1-profiler
Waiting for inference service chaiml-llama8b-60m-rm-p-20581-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 4229.01s
Shutdown handler de-registered
chaiml-llama8b-60m-rm-p_20581_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-60m-rm-p_20581_v1 status is now torndown due to DeploymentManager action