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-v2-mkmlizer
Waiting for job on deeppin-red-paper-v2-mkmlizer to finish
deeppin-red-paper-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deeppin-red-paper-v2-mkmlizer: ║ _____ __ __ ║
deeppin-red-paper-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deeppin-red-paper-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deeppin-red-paper-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deeppin-red-paper-v2-mkmlizer: ║ /___/ ║
deeppin-red-paper-v2-mkmlizer: ║ ║
deeppin-red-paper-v2-mkmlizer: ║ Version: 0.11.12 ║
deeppin-red-paper-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deeppin-red-paper-v2-mkmlizer: ║ https://mk1.ai ║
deeppin-red-paper-v2-mkmlizer: ║ ║
deeppin-red-paper-v2-mkmlizer: ║ The license key for the current software has been verified as ║
deeppin-red-paper-v2-mkmlizer: ║ belonging to: ║
deeppin-red-paper-v2-mkmlizer: ║ ║
deeppin-red-paper-v2-mkmlizer: ║ Chai Research Corp. ║
deeppin-red-paper-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deeppin-red-paper-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
deeppin-red-paper-v2-mkmlizer: ║ ║
deeppin-red-paper-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deeppin-red-paper-v2-mkmlizer: Downloaded to shared memory in 25.253s
deeppin-red-paper-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6_l5nxep, device:0
deeppin-red-paper-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deeppin-red-paper-v2-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-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Failed to get response for submission chaiml-llama-8b-multihea_7878_v5: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46704->127.0.0.1:8080: read: connection reset by peer\n')
deeppin-red-paper-v2-mkmlizer: quantized model in 26.039s
deeppin-red-paper-v2-mkmlizer: Processed model deeppin/red-paper in 51.292s
deeppin-red-paper-v2-mkmlizer: creating bucket guanaco-mkml-models
deeppin-red-paper-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deeppin-red-paper-v2/config.json
deeppin-red-paper-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deeppin-red-paper-v2/special_tokens_map.json
deeppin-red-paper-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deeppin-red-paper-v2/tokenizer_config.json
deeppin-red-paper-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deeppin-red-paper-v2/tokenizer.json
deeppin-red-paper-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deeppin-red-paper-v2/flywheel_model.0.safetensors
deeppin-red-paper-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/291 [00:00<00:05, 47.72it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:04, 67.53it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:02, 86.82it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 86.01it/s]
Loading 0: 18%|█▊ | 53/291 [00:00<00:02, 89.31it/s]
Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 89.45it/s]
Loading 0: 25%|██▌ | 73/291 [00:00<00:02, 91.73it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:08, 23.78it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:07, 27.47it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 37.76it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 44.67it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 52.08it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 58.44it/s]
Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 67.15it/s]
Loading 0: 52%|█████▏ | 151/291 [00:02<00:01, 70.45it/s]
Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 80.13it/s]
Loading 0: 60%|██████ | 175/291 [00:03<00:01, 81.58it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 25.03it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 30.24it/s]
Loading 0: 70%|███████ | 205/291 [00:04<00:02, 35.94it/s]
Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 42.23it/s]
Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 48.07it/s]
Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 53.07it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 57.99it/s]
Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 63.52it/s]
Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 68.92it/s]
Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 79.09it/s]
Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 77.62it/s]
Job deeppin-red-paper-v2-mkmlizer completed after 73.64s with status: succeeded
Stopping job with name deeppin-red-paper-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service deeppin-red-paper-v2
Waiting for inference service deeppin-red-paper-v2 to be ready
Inference service deeppin-red-paper-v2 ready after 120.42830014228821s
Pipeline stage MKMLDeployer completed in 120.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9691290855407715s
Received healthy response to inference request in 1.2344632148742676s
Received healthy response to inference request in 1.2858715057373047s
Received healthy response to inference request in 1.47393798828125s
Received healthy response to inference request in 1.2278342247009277s
5 requests
0 failed requests
5th percentile: 1.2291600227355957
10th percentile: 1.2304858207702636
20th percentile: 1.2331374168395997
30th percentile: 1.244744873046875
40th percentile: 1.2653081893920899
50th percentile: 1.2858715057373047
60th percentile: 1.3610980987548829
70th percentile: 1.4363246917724608
80th percentile: 1.5729762077331544
90th percentile: 1.771052646636963
95th percentile: 1.870090866088867
99th percentile: 1.9493214416503906
mean time: 1.4382472038269043
Pipeline stage StressChecker completed in 8.75s
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 0.65s
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_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 0.11s
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 deeppin-red-paper-v2-profiler
Waiting for inference service deeppin-red-paper-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2199.13s
Shutdown handler de-registered
deeppin-red-paper_v2 status is now inactive due to auto deactivation removed underperforming models
deeppin-red-paper_v2 status is now torndown due to DeploymentManager action