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 deeppin-red-paper-v4-v1-mkmlizer
Waiting for job on deeppin-red-paper-v4-v1-mkmlizer to finish
deeppin-red-paper-v4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v4-v1-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ /___/ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v4-v1-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v4-v1-mkmlizer: ║ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v4-v1-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v4-v1-mkmlizer: ║ ║
deeppin-red-paper-v4-v1-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v4-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v4-v1-mkmlizer: ║ ║
deeppin-red-paper-v4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v4-v1-mkmlizer: Downloaded to shared memory in 35.337s
deeppin-red-paper-v4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsp_kk67n, device:0
deeppin-red-paper-v4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
deeppin-red-paper-v4-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
deeppin-red-paper-v4-v1-mkmlizer: quantized model in 25.875s
deeppin-red-paper-v4-v1-mkmlizer: Processed model deeppin/red-paper-v4 in 61.212s
deeppin-red-paper-v4-v1-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deeppin-red-paper-v4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deeppin-red-paper-v4-v1
deeppin-red-paper-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v4-v1/tokenizer.json
deeppin-red-paper-v4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v4-v1/flywheel_model.0.safetensors
deeppin-red-paper-v4-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:08, 35.75it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 61.64it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:03, 70.99it/s]
Loading 0: 12%|█▏ | 35/291 [00:00<00:03, 80.40it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 88.70it/s]
Loading 0: 21%|██ | 60/291 [00:00<00:02, 94.86it/s]
Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 83.74it/s]
Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 88.01it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:08, 23.54it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 31.48it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 37.63it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 47.30it/s]
Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 52.54it/s]
Loading 0: 51%|█████ | 148/291 [00:02<00:02, 65.44it/s]
Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 70.57it/s]
Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 75.80it/s]
Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 81.87it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 26.19it/s]
Loading 0: 70%|███████ | 204/291 [00:04<00:02, 32.77it/s]
Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 38.46it/s]
Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 44.38it/s]
Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 51.45it/s]
Loading 0: 83%|████████▎ | 242/291 [00:04<00:00, 60.30it/s]
Loading 0: 86%|████████▋ | 251/291 [00:04<00:00, 66.43it/s]
Loading 0: 89%|████████▉ | 260/291 [00:05<00:00, 70.91it/s]
Loading 0: 92%|█████████▏| 269/291 [00:05<00:00, 74.62it/s]
Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 82.22it/s]
Job deeppin-red-paper-v4-v1-mkmlizer completed after 83.69s with status: succeeded
Stopping job with name deeppin-red-paper-v4-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.14s
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 deeppin-red-paper-v4-v1
Waiting for inference service deeppin-red-paper-v4-v1 to be ready
Inference service deeppin-red-paper-v4-v1 ready after 130.44528460502625s
Pipeline stage MKMLDeployer completed in 130.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.72074556350708s
Received healthy response to inference request in 1.2213664054870605s
Received healthy response to inference request in 1.2593586444854736s
Received healthy response to inference request in 1.4370090961456299s
Received healthy response to inference request in 1.361832857131958s
5 requests
0 failed requests
5th percentile: 1.2289648532867432
10th percentile: 1.2365633010864259
20th percentile: 1.251760196685791
30th percentile: 1.2798534870147704
40th percentile: 1.3208431720733642
50th percentile: 1.361832857131958
60th percentile: 1.3919033527374267
70th percentile: 1.4219738483428954
80th percentile: 1.49375638961792
90th percentile: 1.6072509765625
95th percentile: 1.66399827003479
99th percentile: 1.709396104812622
mean time: 1.4000625133514404
Pipeline stage StressChecker completed in 8.22s
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 0.67s
Shutdown handler de-registered
deeppin-red-paper-v4_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3490.47s
Shutdown handler de-registered
deeppin-red-paper-v4_v1 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper-v4_v1 status is now torndown due to DeploymentManager action