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 leosheng-no-repeat-write-opus-v2-mkmlizer
Waiting for job on leosheng-no-repeat-write-opus-v2-mkmlizer to finish
leosheng-no-repeat-write-opus-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ _____ __ __ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ /___/ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ Version: 0.11.12 ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ https://mk1.ai ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ The license key for the current software has been verified as ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ belonging to: ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ Chai Research Corp. ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ║ ║
leosheng-no-repeat-write-opus-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
leosheng-no-repeat-write-opus-v2-mkmlizer: Downloaded to shared memory in 22.772s
leosheng-no-repeat-write-opus-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpusde4qj2, device:0
leosheng-no-repeat-write-opus-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-no-repeat-write-opus-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.
leosheng-no-repeat-write-opus-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
leosheng-no-repeat-write-opus-v2-mkmlizer: quantized model in 26.005s
leosheng-no-repeat-write-opus-v2-mkmlizer: Processed model leosheng/no-repeat-write-opus in 48.777s
leosheng-no-repeat-write-opus-v2-mkmlizer: creating bucket guanaco-mkml-models
leosheng-no-repeat-write-opus-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-no-repeat-write-opus-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2
leosheng-no-repeat-write-opus-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2/config.json
leosheng-no-repeat-write-opus-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2/special_tokens_map.json
leosheng-no-repeat-write-opus-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2/tokenizer_config.json
leosheng-no-repeat-write-opus-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2/tokenizer.json
leosheng-no-repeat-write-opus-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-no-repeat-write-opus-v2/flywheel_model.0.safetensors
leosheng-no-repeat-write-opus-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/291 [00:00<00:05, 53.10it/s]
Loading 0: 6%|▌ | 17/291 [00:00<00:03, 77.41it/s]
Loading 0: 9%|▉ | 26/291 [00:00<00:03, 82.63it/s]
Loading 0: 12%|█▏ | 35/291 [00:00<00:03, 84.07it/s]
Loading 0: 15%|█▌ | 44/291 [00:00<00:03, 81.87it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 87.72it/s]
Loading 0: 23%|██▎ | 68/291 [00:00<00:02, 91.11it/s]
Loading 0: 27%|██▋ | 78/291 [00:00<00:02, 93.40it/s]
Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.51it/s]
Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 26.67it/s]
Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 33.08it/s]
Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 39.84it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 47.16it/s]
Loading 0: 46%|████▌ | 134/291 [00:02<00:02, 56.38it/s]
Loading 0: 49%|████▉ | 143/291 [00:02<00:02, 61.59it/s]
Loading 0: 52%|█████▏ | 152/291 [00:02<00:02, 66.94it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 76.15it/s]
Loading 0: 61%|██████ | 177/291 [00:03<00:01, 83.83it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 22.85it/s]
Loading 0: 68%|██████▊ | 197/291 [00:04<00:03, 29.36it/s]
Loading 0: 71%|███████ | 206/291 [00:04<00:02, 35.85it/s]
Loading 0: 74%|███████▍ | 215/291 [00:04<00:01, 42.70it/s]
Loading 0: 77%|███████▋ | 224/291 [00:04<00:01, 48.93it/s]
Loading 0: 80%|████████ | 233/291 [00:04<00:01, 56.08it/s]
Loading 0: 83%|████████▎ | 242/291 [00:05<00:00, 62.70it/s]
Loading 0: 86%|████████▋ | 251/291 [00:05<00:00, 68.46it/s]
Loading 0: 89%|████████▉ | 260/291 [00:05<00:00, 72.36it/s]
Loading 0: 92%|█████████▏| 269/291 [00:05<00:00, 73.75it/s]
Loading 0: 96%|█████████▌| 278/291 [00:05<00:00, 77.63it/s]
Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 42.49it/s]
Job leosheng-no-repeat-write-opus-v2-mkmlizer completed after 73.83s with status: succeeded
Stopping job with name leosheng-no-repeat-write-opus-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.35s
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 leosheng-no-repeat-write-opus-v2
Waiting for inference service leosheng-no-repeat-write-opus-v2 to be ready
Inference service leosheng-no-repeat-write-opus-v2 ready after 170.64855694770813s
Pipeline stage MKMLDeployer completed in 171.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.781531572341919s
Received healthy response to inference request in 1.2158126831054688s
Received healthy response to inference request in 1.4496734142303467s
Received healthy response to inference request in 1.1932566165924072s
Received healthy response to inference request in 1.2069861888885498s
5 requests
0 failed requests
5th percentile: 1.1960025310516358
10th percentile: 1.1987484455108643
20th percentile: 1.2042402744293212
30th percentile: 1.2087514877319336
40th percentile: 1.212282085418701
50th percentile: 1.2158126831054688
60th percentile: 1.30935697555542
70th percentile: 1.402901268005371
80th percentile: 1.516045045852661
90th percentile: 1.6487883090972901
95th percentile: 1.7151599407196045
99th percentile: 1.7682572460174562
mean time: 1.3694520950317384
Pipeline stage StressChecker completed in 8.17s
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
leosheng-no-repeat-write-opus_v2 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 5325.39s
Shutdown handler de-registered
leosheng-no-repeat-write-opus_v2 status is now inactive due to auto deactivation removed underperforming models
leosheng-no-repeat-write-opus_v2 status is now torndown due to DeploymentManager action