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 sometimesanotion-lamarck-6304-v5-mkmlizer
Waiting for job on sometimesanotion-lamarck-6304-v5-mkmlizer to finish
sometimesanotion-lamarck-6304-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ _____ __ __ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ /___/ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ Version: 0.12.8 ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ https://mk1.ai ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ The license key for the current software has been verified as ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ belonging to: ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ Chai Research Corp. ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ║ ║
sometimesanotion-lamarck-6304-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sometimesanotion-lamarck-6304-v5-mkmlizer: Downloaded to shared memory in 40.328s
sometimesanotion-lamarck-6304-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpba6sezsi, device:0
sometimesanotion-lamarck-6304-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sometimesanotion-lamarck-6304-v5-mkmlizer: quantized model in 37.555s
sometimesanotion-lamarck-6304-v5-mkmlizer: Processed model sometimesanotion/Lamarck-14B-v0.7 in 77.884s
sometimesanotion-lamarck-6304-v5-mkmlizer: creating bucket guanaco-mkml-models
sometimesanotion-lamarck-6304-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sometimesanotion-lamarck-6304-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/added_tokens.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/config.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/special_tokens_map.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/tokenizer_config.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/merges.txt
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/vocab.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/tokenizer.json
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/flywheel_model.1.safetensors
sometimesanotion-lamarck-6304-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sometimesanotion-lamarck-6304-v5/flywheel_model.0.safetensors
sometimesanotion-lamarck-6304-v5-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 0%| | 2/579 [00:07<34:18, 3.57s/it]
Loading 0: 3%|▎ | 16/579 [00:07<03:06, 3.02it/s]
Loading 0: 5%|▌ | 29/579 [00:07<01:25, 6.46it/s]
Loading 0: 7%|▋ | 41/579 [00:07<00:54, 9.83it/s]
Loading 0: 9%|▉ | 54/579 [00:07<00:34, 15.35it/s]
Loading 0: 12%|█▏ | 72/579 [00:07<00:19, 25.50it/s]
Loading 0: 15%|█▌ | 88/579 [00:08<00:13, 36.38it/s]
Loading 0: 17%|█▋ | 101/579 [00:08<00:10, 46.06it/s]
Loading 0: 20%|█▉ | 114/579 [00:08<00:08, 56.59it/s]
Loading 0: 23%|██▎ | 132/579 [00:08<00:05, 75.51it/s]
Loading 0: 26%|██▌ | 148/579 [00:08<00:04, 89.53it/s]
Loading 0: 28%|██▊ | 163/579 [00:08<00:06, 68.47it/s]
Loading 0: 31%|███ | 180/579 [00:08<00:04, 84.32it/s]
Loading 0: 34%|███▍ | 196/579 [00:08<00:03, 96.38it/s]
Loading 0: 36%|███▋ | 210/579 [00:09<00:03, 99.18it/s]
Loading 0: 39%|███▉ | 226/579 [00:09<00:03, 111.92it/s]
Loading 0: 42%|████▏ | 241/579 [00:09<00:02, 120.87it/s]
Loading 0: 44%|████▍ | 256/579 [00:09<00:02, 124.04it/s]
Loading 0: 47%|████▋ | 270/579 [00:09<00:03, 78.26it/s]
Loading 0: 49%|████▉ | 286/579 [00:09<00:03, 93.30it/s]
Loading 0: 52%|█████▏ | 302/579 [00:09<00:02, 107.11it/s]
Loading 0: 55%|█████▍ | 316/579 [00:10<00:02, 110.90it/s]
Loading 0: 57%|█████▋ | 330/579 [00:10<00:02, 109.77it/s]
Loading 0: 60%|██████ | 348/579 [00:10<00:01, 126.30it/s]
Loading 0: 63%|██████▎ | 364/579 [00:10<00:01, 131.23it/s]
Loading 0: 65%|██████▌ | 379/579 [00:10<00:02, 85.57it/s]
Loading 0: 68%|██████▊ | 396/579 [00:10<00:01, 101.15it/s]
Loading 0: 71%|███████ | 412/579 [00:10<00:01, 112.44it/s]
Loading 0: 74%|███████▎ | 426/579 [00:11<00:01, 112.70it/s]
Loading 0: 77%|███████▋ | 444/579 [00:11<00:01, 127.63it/s]
Loading 0: 79%|███████▉ | 460/579 [00:11<00:00, 132.13it/s]
Loading 0: 82%|████████▏ | 475/579 [00:11<00:01, 86.42it/s]
Loading 0: 84%|████████▍ | 487/579 [00:26<00:29, 3.14it/s]
Loading 0: 87%|████████▋ | 501/579 [00:26<00:17, 4.39it/s]
Loading 0: 89%|████████▉ | 516/579 [00:26<00:10, 6.26it/s]
Loading 0: 92%|█████████▏| 530/579 [00:27<00:05, 8.67it/s]
Loading 0: 94%|█████████▍| 544/579 [00:27<00:02, 11.93it/s]
Loading 0: 96%|█████████▌| 557/579 [00:27<00:01, 15.92it/s]
Loading 0: 98%|█████████▊| 570/579 [00:27<00:00, 21.06it/s]
Job sometimesanotion-lamarck-6304-v5-mkmlizer completed after 104.44s with status: succeeded
Stopping job with name sometimesanotion-lamarck-6304-v5-mkmlizer
Pipeline stage MKMLizer completed in 104.91s
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 sometimesanotion-lamarck-6304-v5
Waiting for inference service sometimesanotion-lamarck-6304-v5 to be ready
Inference service sometimesanotion-lamarck-6304-v5 ready after 220.72445964813232s
Pipeline stage MKMLDeployer completed in 221.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6889142990112305s
Received healthy response to inference request in 2.1757559776306152s
Received healthy response to inference request in 1.9456782341003418s
Received healthy response to inference request in 2.0469772815704346s
Received healthy response to inference request in 2.179800271987915s
5 requests
0 failed requests
5th percentile: 1.9659380435943603
10th percentile: 1.9861978530883788
20th percentile: 2.026717472076416
30th percentile: 2.072733020782471
40th percentile: 2.124244499206543
50th percentile: 2.1757559776306152
60th percentile: 2.177373695373535
70th percentile: 2.178991413116455
80th percentile: 2.2816230773925783
90th percentile: 2.4852686882019044
95th percentile: 2.587091493606567
99th percentile: 2.668549737930298
mean time: 2.2074252128601075
Pipeline stage StressChecker completed in 12.27s
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 0.61s
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 0.67s
Shutdown handler de-registered
sometimesanotion-lamarck_6304_v5 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sometimesanotion-lamarck-6304-v5-profiler
Waiting for inference service sometimesanotion-lamarck-6304-v5-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...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sometimesanotion-lamarck-6304-v5-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.17s
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 sometimesanotion-lamarck-6304-v5-profiler
Waiting for inference service sometimesanotion-lamarck-6304-v5-profiler to be ready
Inference service sometimesanotion-lamarck-6304-v5-profiler ready after 50.2872633934021s
Pipeline stage MKMLProfilerDeployer completed in 50.61s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x:/code/chaiverse_profiler_1739875367 --namespace tenant-chaiml-guanaco
kubectl exec -it sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739875367 && 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_1739875367/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x:/code/chaiverse_profiler_1739875680 --namespace tenant-chaiml-guanaco
kubectl exec -it sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739875680 && 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_1739875680/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x:/code/chaiverse_profiler_1739875993 --namespace tenant-chaiml-guanaco
kubectl exec -it sometimesanotion-lam8065aeadea90c72512819cbf82cbc0ab-deplortz2x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739875993 && 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_1739875993/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1739875993/profiles.py", line 602, in <module>\n cli()\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n return self.main(*args, **kwargs)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n rv = self.invoke(ctx)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n return _process_result(sub_ctx.command.invoke(sub_ctx))\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n return ctx.invoke(self.callback, **ctx.params)\n File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n return __callback(*args, **kwargs)\n File "/code/chaiverse_profiler_1739875993/profiles.py", line 103, in profile_batches\n client.wait_for_server_startup(target, max_wait=300)\n File "/code/inference_analysis/client.py", line 136, in wait_for_server_startup\n raise RuntimeError(msg)\nRuntimeError: Timed out after 300s waiting for startup\ncommand terminated with exit code 1\n, output: waiting for startup of TargetModel(endpoint=\'localhost\', route=\'GPT-J-6B-lit-v2\', namespace=\'tenant-chaiml-guanaco\', max_characters=9999, reward=False, url_format=\'{endpoint}-predictor-default.{namespace}.knative.ord1.coreweave.cloud\')\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sometimesanotion-lamarck-6304-v5-profiler is running
Tearing down inference service sometimesanotion-lamarck-6304-v5-profiler
Service sometimesanotion-lamarck-6304-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.31s
Shutdown handler de-registered
sometimesanotion-lamarck_6304_v5 status is now inactive due to auto deactivation removed underperforming models
sometimesanotion-lamarck_6304_v5 status is now torndown due to DeploymentManager action
sometimesanotion-lamarck_6304_v5 status is now torndown due to DeploymentManager action
sometimesanotion-lamarck_6304_v5 status is now torndown due to DeploymentManager action