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 cycy233-nemo-p-v4-c2-v1-mkmlizer
Waiting for job on cycy233-nemo-p-v4-c2-v1-mkmlizer to finish
cycy233-nemo-p-v4-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ Version: 0.11.12 ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ║ ║
cycy233-nemo-p-v4-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-nemo-p-v4-c2-v1-mkmlizer: Downloaded to shared memory in 52.143s
cycy233-nemo-p-v4-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2rp6vws4, device:0
cycy233-nemo-p-v4-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-v4-c2-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.
cycy233-nemo-p-v4-c2-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
cycy233-nemo-p-v4-c2-v1-mkmlizer: quantized model in 35.762s
cycy233-nemo-p-v4-c2-v1-mkmlizer: Processed model cycy233/nemo-p-v4-c2 in 87.905s
cycy233-nemo-p-v4-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v4-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v4-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1
cycy233-nemo-p-v4-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1/config.json
cycy233-nemo-p-v4-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1/special_tokens_map.json
cycy233-nemo-p-v4-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1/tokenizer_config.json
cycy233-nemo-p-v4-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1/tokenizer.json
cycy233-nemo-p-v4-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v4-c2-v1/flywheel_model.0.safetensors
cycy233-nemo-p-v4-c2-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:10, 33.15it/s]
Loading 0: 4%|▍ | 16/363 [00:00<00:05, 65.52it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:04, 81.19it/s]
Loading 0: 11%|█ | 40/363 [00:00<00:04, 80.64it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:03, 82.29it/s]
Loading 0: 16%|█▌ | 58/363 [00:00<00:03, 77.30it/s]
Loading 0: 18%|█▊ | 66/363 [00:01<00:14, 20.59it/s]
Loading 0: 21%|██ | 76/363 [00:01<00:10, 27.24it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 35.67it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 43.71it/s]
Loading 0: 31%|███ | 112/363 [00:02<00:04, 57.35it/s]
Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 63.76it/s]
Loading 0: 38%|███▊ | 139/363 [00:02<00:02, 74.84it/s]
Loading 0: 41%|████ | 149/363 [00:03<00:08, 25.87it/s]
Loading 0: 43%|████▎ | 157/363 [00:03<00:06, 30.41it/s]
Loading 0: 46%|████▌ | 166/363 [00:03<00:05, 36.89it/s]
Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 43.61it/s]
Loading 0: 51%|█████ | 184/363 [00:04<00:03, 50.61it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 58.91it/s]
Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 71.29it/s]
Loading 0: 61%|██████▏ | 223/363 [00:05<00:05, 25.67it/s]
Loading 0: 64%|██████▍ | 233/363 [00:05<00:04, 31.87it/s]
Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 41.72it/s]
Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 49.40it/s]
Loading 0: 74%|███████▍ | 269/363 [00:06<00:01, 56.94it/s]
Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 62.56it/s]
Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 65.07it/s]
Loading 0: 82%|████████▏ | 296/363 [00:06<00:00, 70.33it/s]
Loading 0: 84%|████████▍ | 305/363 [00:07<00:02, 22.44it/s]
Loading 0: 86%|████████▌ | 313/363 [00:07<00:01, 27.64it/s]
Loading 0: 89%|████████▊ | 322/363 [00:07<00:01, 34.31it/s]
Loading 0: 93%|█████████▎| 337/363 [00:07<00:00, 47.72it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 55.82it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00, 5.83it/s]
Job cycy233-nemo-p-v4-c2-v1-mkmlizer completed after 173.84s with status: succeeded
Stopping job with name cycy233-nemo-p-v4-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 174.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v4-c2-v1
Waiting for inference service cycy233-nemo-p-v4-c2-v1 to be ready
Inference service cycy233-nemo-p-v4-c2-v1 ready after 230.58206009864807s
Pipeline stage MKMLDeployer completed in 230.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.170088052749634s
Received healthy response to inference request in 1.657970666885376s
Received healthy response to inference request in 2.07757568359375s
Received healthy response to inference request in 1.6607913970947266s
Received healthy response to inference request in 1.712141513824463s
5 requests
0 failed requests
5th percentile: 1.6585348129272461
10th percentile: 1.6590989589691163
20th percentile: 1.6602272510528564
30th percentile: 1.6710614204406737
40th percentile: 1.6916014671325683
50th percentile: 1.712141513824463
60th percentile: 1.8583151817321777
70th percentile: 2.0044888496398925
80th percentile: 2.0960781574249268
90th percentile: 2.1330831050872803
95th percentile: 2.151585578918457
99th percentile: 2.1663875579833984
mean time: 1.85571346282959
Pipeline stage StressChecker completed in 9.94s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.46s
Shutdown handler de-registered
cycy233-nemo-p-v4-c2_v1 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 0.11s
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 cycy233-nemo-p-v4-c2-v1-profiler
Waiting for inference service cycy233-nemo-p-v4-c2-v1-profiler to be ready
Tearing down inference service cycy233-nemo-p-v4-c2-v1-profiler
%s, retrying in %s seconds...
Creating inference service cycy233-nemo-p-v4-c2-v1-profiler
Waiting for inference service cycy233-nemo-p-v4-c2-v1-profiler to be ready
Tearing down inference service cycy233-nemo-p-v4-c2-v1-profiler
%s, retrying in %s seconds...
Creating inference service cycy233-nemo-p-v4-c2-v1-profiler
Waiting for inference service cycy233-nemo-p-v4-c2-v1-profiler to be ready
Tearing down inference service cycy233-nemo-p-v4-c2-v1-profiler
clean up pipeline due to error=%s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
Shutdown handler de-registered
cycy233-nemo-p-v4-c2_v1 status is now inactive due to auto deactivation removed underperforming models