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-nemo-20241017-t-80987-v15-mkmlizer
Waiting for job on chaiml-nemo-20241017-t-80987-v15-mkmlizer to finish
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ /___/ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ║ ║
chaiml-nemo-20241017-t-80987-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-t-80987-v15-mkmlizer: Downloaded to shared memory in 35.193s
chaiml-nemo-20241017-t-80987-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzz8_18vo, device:0
chaiml-nemo-20241017-t-80987-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-t-80987-v15-mkmlizer: quantized model in 41.331s
chaiml-nemo-20241017-t-80987-v15-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 76.524s
chaiml-nemo-20241017-t-80987-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-t-80987-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-t-80987-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15
chaiml-nemo-20241017-t-80987-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15/config.json
chaiml-nemo-20241017-t-80987-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15/special_tokens_map.json
chaiml-nemo-20241017-t-80987-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15/tokenizer_config.json
chaiml-nemo-20241017-t-80987-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15/tokenizer.json
chaiml-nemo-20241017-t-80987-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-t-80987-v15/flywheel_model.0.safetensors
chaiml-nemo-20241017-t-80987-v15-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:06<20:25, 3.39s/it]
Loading 0: 2%|▏ | 6/363 [00:06<05:25, 1.10it/s]
Loading 0: 3%|▎ | 11/363 [00:07<02:23, 2.46it/s]
Loading 0: 4%|▍ | 15/363 [00:07<01:30, 3.82it/s]
Loading 0: 6%|▌ | 21/363 [00:07<00:51, 6.69it/s]
Loading 0: 7%|▋ | 25/363 [00:07<00:39, 8.60it/s]
Loading 0: 9%|▊ | 31/363 [00:07<00:26, 12.75it/s]
Loading 0: 10%|▉ | 35/363 [00:07<00:21, 15.22it/s]
Loading 0: 11%|█ | 40/363 [00:08<00:22, 14.46it/s]
Loading 0: 12%|█▏ | 43/363 [00:08<00:20, 15.91it/s]
Loading 0: 13%|█▎ | 47/363 [00:08<00:16, 19.31it/s]
Loading 0: 14%|█▍ | 51/363 [00:08<00:14, 20.92it/s]
Loading 0: 15%|█▌ | 56/363 [00:08<00:11, 26.03it/s]
Loading 0: 17%|█▋ | 60/363 [00:08<00:11, 25.83it/s]
Loading 0: 18%|█▊ | 65/363 [00:08<00:09, 30.51it/s]
Loading 0: 19%|█▉ | 69/363 [00:09<00:10, 29.28it/s]
Loading 0: 20%|██ | 74/363 [00:09<00:08, 33.78it/s]
Loading 0: 21%|██▏ | 78/363 [00:09<00:08, 31.68it/s]
Loading 0: 23%|██▎ | 83/363 [00:09<00:07, 35.76it/s]
Loading 0: 24%|██▍ | 87/363 [00:09<00:08, 31.90it/s]
Loading 0: 25%|██▌ | 92/363 [00:09<00:07, 35.80it/s]
Loading 0: 26%|██▋ | 96/363 [00:09<00:08, 32.35it/s]
Loading 0: 28%|██▊ | 101/363 [00:09<00:07, 36.11it/s]
Loading 0: 29%|██▉ | 105/363 [00:10<00:08, 31.41it/s]
Loading 0: 30%|███ | 110/363 [00:10<00:07, 34.70it/s]
Loading 0: 31%|███▏ | 114/363 [00:10<00:08, 31.06it/s]
Loading 0: 33%|███▎ | 119/363 [00:10<00:07, 34.44it/s]
Loading 0: 34%|███▍ | 123/363 [00:10<00:12, 19.47it/s]
Loading 0: 35%|███▌ | 128/363 [00:11<00:09, 23.82it/s]
Loading 0: 36%|███▋ | 132/363 [00:11<00:09, 24.06it/s]
Loading 0: 38%|███▊ | 137/363 [00:11<00:07, 28.29it/s]
Loading 0: 39%|███▉ | 141/363 [00:11<00:08, 26.94it/s]
Loading 0: 40%|████ | 146/363 [00:11<00:07, 30.98it/s]
Loading 0: 41%|████▏ | 150/363 [00:11<00:07, 28.90it/s]
Loading 0: 43%|████▎ | 155/363 [00:11<00:06, 32.33it/s]
Loading 0: 44%|████▍ | 159/363 [00:12<00:06, 29.50it/s]
Loading 0: 45%|████▌ | 164/363 [00:12<00:05, 33.77it/s]
Loading 0: 46%|████▋ | 168/363 [00:12<00:06, 31.30it/s]
Loading 0: 48%|████▊ | 173/363 [00:12<00:05, 35.20it/s]
Loading 0: 49%|████▉ | 177/363 [00:12<00:05, 32.44it/s]
Loading 0: 51%|█████ | 184/363 [00:12<00:04, 39.52it/s]
Loading 0: 52%|█████▏ | 189/363 [00:12<00:04, 39.25it/s]
Loading 0: 53%|█████▎ | 194/363 [00:12<00:04, 37.65it/s]
Loading 0: 55%|█████▍ | 198/363 [00:13<00:04, 35.60it/s]
Loading 0: 56%|█████▌ | 202/363 [00:13<00:07, 22.47it/s]
Loading 0: 56%|█████▋ | 205/363 [00:13<00:06, 22.74it/s]
Loading 0: 58%|█████▊ | 211/363 [00:13<00:05, 28.87it/s]
Loading 0: 59%|█████▉ | 215/363 [00:13<00:05, 28.73it/s]
Loading 0: 60%|██████ | 219/363 [00:13<00:04, 31.13it/s]
Loading 0: 61%|██████▏ | 223/363 [00:14<00:04, 29.32it/s]
Loading 0: 63%|██████▎ | 227/363 [00:14<00:04, 30.76it/s]
Loading 0: 64%|██████▎ | 231/363 [00:14<00:04, 29.19it/s]
Loading 0: 65%|██████▌ | 236/363 [00:14<00:03, 33.38it/s]
Loading 0: 66%|██████▌ | 240/363 [00:14<00:04, 30.68it/s]
Loading 0: 67%|██████▋ | 245/363 [00:14<00:03, 34.63it/s]
Loading 0: 69%|██████▊ | 249/363 [00:14<00:03, 30.85it/s]
Loading 0: 70%|██████▉ | 254/363 [00:14<00:03, 34.14it/s]
Loading 0: 71%|███████ | 258/363 [00:15<00:03, 30.06it/s]
Loading 0: 72%|███████▏ | 263/363 [00:15<00:02, 33.62it/s]
Loading 0: 74%|███████▎ | 267/363 [00:15<00:03, 29.19it/s]
Loading 0: 75%|███████▍ | 272/363 [00:15<00:02, 31.95it/s]
Loading 0: 76%|███████▌ | 276/363 [00:15<00:03, 28.55it/s]
Loading 0: 77%|███████▋ | 281/363 [00:15<00:02, 32.54it/s]
Loading 0: 79%|███████▊ | 285/363 [00:16<00:04, 19.08it/s]
Loading 0: 80%|███████▉ | 290/363 [00:16<00:03, 22.77it/s]
Loading 0: 81%|████████ | 294/363 [00:16<00:03, 22.76it/s]
Loading 0: 82%|████████▏ | 299/363 [00:16<00:02, 27.30it/s]
Loading 0: 83%|████████▎ | 303/363 [00:16<00:02, 26.31it/s]
Loading 0: 85%|████████▍ | 308/363 [00:17<00:01, 30.02it/s]
Loading 0: 86%|████████▌ | 312/363 [00:17<00:01, 28.15it/s]
Loading 0: 87%|████████▋ | 317/363 [00:17<00:01, 32.16it/s]
Loading 0: 88%|████████▊ | 321/363 [00:17<00:01, 29.78it/s]
Loading 0: 90%|████████▉ | 326/363 [00:17<00:01, 32.03it/s]
Loading 0: 91%|█████████ | 330/363 [00:17<00:01, 29.46it/s]
Loading 0: 92%|█████████▏| 335/363 [00:17<00:00, 33.56it/s]
Loading 0: 93%|█████████▎| 339/363 [00:18<00:00, 31.07it/s]
Loading 0: 95%|█████████▍| 344/363 [00:18<00:00, 35.22it/s]
Loading 0: 96%|█████████▌| 348/363 [00:18<00:00, 33.18it/s]
Loading 0: 98%|█████████▊| 355/363 [00:18<00:00, 40.25it/s]
Loading 0: 99%|█████████▉| 360/363 [00:18<00:00, 39.39it/s]
Job chaiml-nemo-20241017-t-80987-v15-mkmlizer completed after 189.32s with status: succeeded
Stopping job with name chaiml-nemo-20241017-t-80987-v15-mkmlizer
Pipeline stage MKMLizer completed in 189.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-t-80987-v15
Waiting for inference service chaiml-nemo-20241017-t-80987-v15 to be ready
Inference service chaiml-nemo-20241017-t-80987-v15 ready after 220.7446644306183s
Pipeline stage MKMLDeployer completed in 221.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8345232009887695s
Received healthy response to inference request in 1.4783313274383545s
Received healthy response to inference request in 1.552361011505127s
Received healthy response to inference request in 1.3919568061828613s
Received healthy response to inference request in 1.4682073593139648s
5 requests
0 failed requests
5th percentile: 1.407206916809082
10th percentile: 1.4224570274353028
20th percentile: 1.4529572486877442
30th percentile: 1.4702321529388427
40th percentile: 1.4742817401885986
50th percentile: 1.4783313274383545
60th percentile: 1.5079432010650635
70th percentile: 1.5375550746917725
80th percentile: 1.6087934494018554
90th percentile: 1.7216583251953126
95th percentile: 1.778090763092041
99th percentile: 1.8232367134094238
mean time: 1.5450759410858155
Pipeline stage StressChecker completed in 8.91s
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 0.75s
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 0.63s
Shutdown handler de-registered
chaiml-nemo-20241017-t_80987_v15 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2677.57s
Shutdown handler de-registered
chaiml-nemo-20241017-t_80987_v15 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-t_80987_v15 status is now torndown due to DeploymentManager action