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-gy-exp209-sft-ne-39467-v1-mkmlizer
Waiting for job on chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer to finish
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ║ ║
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: Downloaded to shared memory in 47.085s
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: Checking if ChaiML/gy-exp209-sft-nemo12b-grok-payloads-0705-only-wins-lastmsgloss-ep2 already exists in ChaiML
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5qot0d1v, device:0
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission zhouzr-sft-clean-10k_v1: HTTPConnectionPool(host='zhouzr-sft-clean-10k-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: quantized model in 30.415s
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: Processed model ChaiML/gy-exp209-sft-nemo12b-grok-payloads-0705-only-wins-lastmsgloss-ep2 in 77.500s
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia/config.json
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia/special_tokens_map.json
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia/tokenizer_config.json
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia/tokenizer.json
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp209-sft-ne-39467-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.74it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.19it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.36it/s]
Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.58it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:06, 47.75it/s]
Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.66it/s]
Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 42.46it/s]
Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 47.40it/s]
Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 47.04it/s]
Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 44.19it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 27.52it/s]
Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 33.18it/s]
Loading 0: 21%|██ | 76/363 [00:01<00:08, 35.35it/s]
Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 37.37it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 40.22it/s]
Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 35.12it/s]
Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 43.26it/s]
Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 44.74it/s]
Loading 0: 30%|███ | 110/363 [00:02<00:05, 43.18it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 44.20it/s]
Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 42.78it/s]
Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 45.06it/s]
Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 45.99it/s]
Loading 0: 37%|███▋ | 136/363 [00:03<00:06, 36.37it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:07, 30.89it/s]
Loading 0: 40%|████ | 146/363 [00:03<00:06, 31.61it/s]
Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 30.84it/s]
Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.40it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 35.13it/s]
Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 39.07it/s]
Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 40.27it/s]
Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 34.79it/s]
Loading 0: 50%|█████ | 183/363 [00:04<00:04, 42.07it/s]
Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 40.45it/s]
Loading 0: 53%|█████▎ | 193/363 [00:04<00:04, 40.68it/s]
Loading 0: 55%|█████▍ | 198/363 [00:05<00:03, 42.41it/s]
Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 36.62it/s]
Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 43.96it/s]
Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 43.34it/s]
Loading 0: 61%|██████ | 221/363 [00:05<00:03, 46.84it/s]
Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.98it/s]
Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 29.14it/s]
Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 36.58it/s]
Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.96it/s]
Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.59it/s]
Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.64it/s]
Loading 0: 71%|███████ | 257/363 [00:06<00:02, 35.63it/s]
Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.81it/s]
Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 41.17it/s]
Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 41.81it/s]
Loading 0: 77%|███████▋ | 279/363 [00:07<00:01, 43.19it/s]
Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 36.71it/s]
Loading 0: 80%|████████ | 291/363 [00:07<00:01, 43.63it/s]
Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 43.27it/s]
Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 46.98it/s]
Loading 0: 85%|████████▍ | 307/363 [00:08<00:02, 21.80it/s]
Loading 0: 86%|████████▌ | 312/363 [00:08<00:02, 23.88it/s]
Loading 0: 88%|████████▊ | 320/363 [00:08<00:01, 32.41it/s]
Loading 0: 90%|████████▉ | 326/363 [00:08<00:01, 34.30it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 36.20it/s]
Loading 0: 93%|█████████▎| 338/363 [00:08<00:00, 42.20it/s]
Loading 0: 95%|█████████▍| 344/363 [00:08<00:00, 41.67it/s]
Loading 0: 96%|█████████▌| 349/363 [00:09<00:00, 41.05it/s]
Loading 0: 98%|█████████▊| 356/363 [00:09<00:00, 45.98it/s]
Loading 0: 99%|█████████▉| 361/363 [00:09<00:00, 46.38it/s]
Job chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer completed after 106.13s with status: succeeded
Stopping job with name chaiml-gy-exp209-sft-ne-39467-v1-mkmlizer
Pipeline stage MKMLizer completed in 106.63s
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-gy-exp209-sft-ne-39467-v1
Waiting for inference service chaiml-gy-exp209-sft-ne-39467-v1 to be ready
Failed to get response for submission chaiml-gy-exp204-debug-n_6008_v1: HTTPConnectionPool(host='chaiml-gy-exp204-debug-n-6008-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp204-debug-n_6008_v2: HTTPConnectionPool(host='chaiml-gy-exp204-debug-n-6008-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp204-debug-n_6008_v2: HTTPConnectionPool(host='chaiml-gy-exp204-debug-n-6008-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zhouzr-sft-clean-10k_v1: HTTPConnectionPool(host='zhouzr-sft-clean-10k-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp209-sft-ne-39467-v1 ready after 312.49159598350525s
Pipeline stage MKMLDeployer completed in 312.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7834970951080322s
Received healthy response to inference request in 1.7206776142120361s
Received healthy response to inference request in 1.651798963546753s
Received healthy response to inference request in 1.729860544204712s
Received healthy response to inference request in 2.251400947570801s
5 requests
0 failed requests
5th percentile: 1.6655746936798095
10th percentile: 1.6793504238128663
20th percentile: 1.7069018840789796
30th percentile: 1.7225142002105713
40th percentile: 1.7261873722076415
50th percentile: 1.729860544204712
60th percentile: 1.9384767055511474
70th percentile: 2.147092866897583
80th percentile: 2.357820177078247
90th percentile: 2.57065863609314
95th percentile: 2.677077865600586
99th percentile: 2.762213249206543
mean time: 2.0274470329284666
Pipeline stage StressChecker completed in 11.33s
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 0.68s
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 1.50s
Shutdown handler de-registered
chaiml-gy-exp209-sft-ne_39467_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
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-gy-exp209-sft-ne-39467-v1-profiler
Waiting for inference service chaiml-gy-exp209-sft-ne-39467-v1-profiler to be ready
Inference service chaiml-gy-exp209-sft-ne-39467-v1-profiler ready after 323.14969778060913s
Pipeline stage MKMLProfilerDeployer completed in 324.00s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-gy-exp209-sft7f37c339e3bb8262bc35018c526b9986-deploxs2td:/code/chaiverse_profiler_1753109581 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-gy-exp209-sft7f37c339e3bb8262bc35018c526b9986-deploxs2td --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1753109581 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1753109581/summary.json'
kubectl exec -it chaiml-gy-exp209-sft7f37c339e3bb8262bc35018c526b9986-deploxs2td --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1753109581/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1124.53s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-gy-exp209-sft-ne-39467-v1-profiler is running
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 2525.47s
Shutdown handler de-registered
chaiml-gy-exp209-sft-ne_39467_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp209-sft-ne_39467_v1 status is now torndown due to DeploymentManager action