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-gemma2-27b-gemma-11672-v2-mkmlizer
Waiting for job on chaiml-gemma2-27b-gemma-11672-v2-mkmlizer to finish
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ _____ __ __ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ /___/ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ belonging to: ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ║ ║
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: Downloaded to shared memory in 69.817s
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpttur2lu6, device:0
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: quantized model in 67.006s
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: Processed model ChaiML/gemma2-27b-gemmapretsft25k-nofilter-3e in 136.823s
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/config.json
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/special_tokens_map.json
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/tokenizer_config.json
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/tokenizer.model
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/tokenizer.json
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/flywheel_model.2.safetensors
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/flywheel_model.0.safetensors
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gemma2-27b-gemma-11672-v2/flywheel_model.1.safetensors
chaiml-gemma2-27b-gemma-11672-v2-mkmlizer:
Loading 0: 0%| | 0/508 [00:00<?, ?it/s]
Loading 0: 1%| | 5/508 [00:00<00:14, 34.70it/s]
Loading 0: 2%|▏ | 12/508 [00:00<00:09, 50.08it/s]
Loading 0: 4%|▎ | 18/508 [00:00<00:12, 39.36it/s]
Loading 0: 5%|▌ | 27/508 [00:00<00:10, 46.75it/s]
Loading 0: 6%|▋ | 32/508 [00:00<00:15, 30.93it/s]
Loading 0: 7%|▋ | 38/508 [00:01<00:13, 33.75it/s]
Loading 0: 9%|▉ | 47/508 [00:01<00:11, 41.52it/s]
Loading 0: 10%|█ | 53/508 [00:01<00:10, 45.38it/s]
Loading 0: 12%|█▏ | 59/508 [00:01<00:11, 40.79it/s]
Loading 0: 13%|█▎ | 67/508 [00:01<00:09, 45.21it/s]
Loading 0: 14%|█▍ | 72/508 [00:01<00:10, 41.66it/s]
Loading 0: 15%|█▌ | 77/508 [00:02<00:13, 31.04it/s]
Loading 0: 16%|█▌ | 81/508 [00:02<00:15, 27.70it/s]
Loading 0: 17%|█▋ | 88/508 [00:02<00:12, 33.01it/s]
Loading 0: 19%|█▉ | 97/508 [00:02<00:10, 40.46it/s]
Loading 0: 20%|██ | 104/508 [00:02<00:08, 46.12it/s]
Loading 0: 22%|██▏ | 110/508 [00:02<00:10, 37.75it/s]
Loading 0: 23%|██▎ | 118/508 [00:03<00:10, 36.02it/s]
Loading 0: 24%|██▍ | 124/508 [00:03<00:09, 40.34it/s]
Loading 0: 26%|██▌ | 130/508 [00:03<00:08, 44.23it/s]
Loading 0: 27%|██▋ | 136/508 [00:03<00:09, 38.35it/s]
Loading 0: 28%|██▊ | 144/508 [00:03<00:08, 44.13it/s]
Loading 0: 29%|██▉ | 149/508 [00:03<00:09, 39.71it/s]
Loading 0: 31%|███ | 157/508 [00:03<00:08, 43.29it/s]
Loading 0: 32%|███▏ | 163/508 [00:04<00:07, 46.64it/s]
Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 46.20it/s]
Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 29.57it/s]
Loading 0: 35%|███▌ | 180/508 [00:04<00:09, 34.18it/s]
Loading 0: 37%|███▋ | 188/508 [00:04<00:07, 40.45it/s]
Loading 0: 38%|███▊ | 193/508 [00:19<03:44, 1.40it/s]
Loading 0: 39%|███▉ | 199/508 [00:19<02:37, 1.97it/s]
Loading 0: 40%|████ | 204/508 [00:19<02:00, 2.52it/s]
Loading 0: 42%|████▏ | 211/508 [00:19<01:19, 3.72it/s]
Loading 0: 43%|████▎ | 216/508 [00:20<01:01, 4.71it/s]
Loading 0: 44%|████▍ | 223/508 [00:20<00:41, 6.81it/s]
Loading 0: 45%|████▌ | 230/508 [00:20<00:28, 9.65it/s]
Loading 0: 46%|████▋ | 235/508 [00:20<00:23, 11.40it/s]
Loading 0: 48%|████▊ | 243/508 [00:20<00:16, 16.14it/s]
Loading 0: 49%|████▉ | 248/508 [00:20<00:14, 18.23it/s]
Loading 0: 50%|█████ | 255/508 [00:20<00:11, 22.40it/s]
Loading 0: 51%|█████ | 260/508 [00:21<00:09, 25.20it/s]
Loading 0: 52%|█████▏ | 265/508 [00:21<00:09, 24.57it/s]
Loading 0: 53%|█████▎ | 269/508 [00:21<00:09, 25.34it/s]
Loading 0: 55%|█████▍ | 278/508 [00:21<00:06, 33.90it/s]
Loading 0: 56%|█████▌ | 283/508 [00:21<00:06, 36.83it/s]
Loading 0: 57%|█████▋ | 289/508 [00:21<00:05, 37.81it/s]
Loading 0: 58%|█████▊ | 296/508 [00:21<00:04, 44.38it/s]
Loading 0: 59%|█████▉ | 302/508 [00:22<00:05, 36.00it/s]
Loading 0: 61%|██████ | 310/508 [00:22<00:04, 44.15it/s]
Loading 0: 62%|██████▏ | 316/508 [00:22<00:06, 31.64it/s]
Loading 0: 64%|██████▎ | 323/508 [00:22<00:05, 35.59it/s]
Loading 0: 65%|██████▌ | 331/508 [00:22<00:04, 41.71it/s]
Loading 0: 66%|██████▌ | 336/508 [00:23<00:04, 38.52it/s]
Loading 0: 68%|██████▊ | 344/508 [00:23<00:03, 42.76it/s]
Loading 0: 69%|██████▉ | 350/508 [00:23<00:03, 46.20it/s]
Loading 0: 70%|███████ | 356/508 [00:23<00:03, 42.89it/s]
Loading 0: 71%|███████ | 361/508 [00:23<00:05, 29.25it/s]
Loading 0: 72%|███████▏ | 368/508 [00:23<00:04, 33.56it/s]
Loading 0: 74%|███████▍ | 377/508 [00:24<00:03, 39.82it/s]
Loading 0: 75%|███████▌ | 383/508 [00:24<00:02, 43.58it/s]
Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 40.01it/s]
Loading 0: 78%|███████▊ | 394/508 [00:24<00:02, 44.30it/s]
Loading 0: 79%|███████▊ | 399/508 [00:24<00:02, 37.20it/s]
Loading 0: 80%|███████▉ | 404/508 [00:24<00:03, 30.32it/s]
Loading 0: 81%|████████ | 411/508 [00:25<00:02, 34.86it/s]
Loading 0: 82%|████████▏ | 419/508 [00:25<00:02, 40.78it/s]
Loading 0: 83%|████████▎ | 424/508 [00:25<00:02, 36.39it/s]
Loading 0: 85%|████████▌ | 432/508 [00:25<00:01, 40.93it/s]
Loading 0: 86%|████████▌ | 438/508 [00:25<00:01, 44.74it/s]
Loading 0: 87%|████████▋ | 443/508 [00:25<00:01, 41.14it/s]
Loading 0: 89%|████████▊ | 450/508 [00:25<00:01, 47.16it/s]
Loading 0: 90%|████████▉ | 455/508 [00:40<00:01, 47.16it/s]
Loading 0: 90%|████████▉ | 456/508 [00:40<00:36, 1.43it/s]
Loading 0: 90%|████████▉ | 457/508 [00:40<00:33, 1.50it/s]
Loading 0: 91%|█████████ | 461/508 [00:40<00:23, 2.01it/s]
Loading 0: 92%|█████████▏| 467/508 [00:40<00:13, 3.09it/s]
Loading 0: 94%|█████████▎| 476/508 [00:40<00:06, 5.28it/s]
Loading 0: 95%|█████████▍| 482/508 [00:40<00:03, 7.22it/s]
Loading 0: 96%|█████████▌| 487/508 [00:40<00:02, 9.07it/s]
Loading 0: 97%|█████████▋| 493/508 [00:41<00:01, 12.27it/s]
Loading 0: 98%|█████████▊| 498/508 [00:41<00:00, 14.64it/s]
Loading 0: 99%|█████████▉| 503/508 [00:41<00:00, 15.19it/s]
Job chaiml-gemma2-27b-gemma-11672-v2-mkmlizer completed after 166.96s with status: succeeded
Stopping job with name chaiml-gemma2-27b-gemma-11672-v2-mkmlizer
Pipeline stage MKMLizer completed in 167.45s
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-gemma2-27b-gemma-11672-v2
Waiting for inference service chaiml-gemma2-27b-gemma-11672-v2 to be ready
Inference service chaiml-gemma2-27b-gemma-11672-v2 ready after 150.632337808609s
Pipeline stage MKMLDeployer completed in 151.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4590983390808105s
Received healthy response to inference request in 2.8035295009613037s
Received healthy response to inference request in 2.759653091430664s
Received healthy response to inference request in 2.556929349899292s
Received healthy response to inference request in 3.1444640159606934s
5 requests
0 failed requests
5th percentile: 2.5974740982055664
10th percentile: 2.638018846511841
20th percentile: 2.7191083431243896
30th percentile: 2.768428373336792
40th percentile: 2.7859789371490478
50th percentile: 2.8035295009613037
60th percentile: 2.9399033069610594
70th percentile: 3.0762771129608155
80th percentile: 3.207390880584717
90th percentile: 3.3332446098327635
95th percentile: 3.396171474456787
99th percentile: 3.4465129661560057
mean time: 2.9447348594665526
Pipeline stage StressChecker completed in 16.14s
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 1.24s
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 0.75s
Shutdown handler de-registered
chaiml-gemma2-27b-gemma_11672_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gemma2-27b-gemma-11672-v2-profiler
Waiting for inference service chaiml-gemma2-27b-gemma-11672-v2-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
clean up pipeline due to error=DeploymentChecksError('None: None')
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
%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
clean up pipeline due to error=DeploymentChecksError('None: None')
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
%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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5465.67s
Shutdown handler de-registered
chaiml-gemma2-27b-gemma_11672_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gemma2-27b-gemma_11672_v2 status is now torndown due to DeploymentManager action