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 alexxi19-ft-v1-violet-v16-mkmlizer
Waiting for job on alexxi19-ft-v1-violet-v16-mkmlizer to finish
alexxi19-ft-v1-violet-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-violet-v16-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ Version: 0.11.12 ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-violet-v16-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-violet-v16-mkmlizer: Downloaded to shared memory in 31.410s
alexxi19-ft-v1-violet-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvsborguu, device:0
alexxi19-ft-v1-violet-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-violet-v16-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.
alexxi19-ft-v1-violet-v16-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-violet-v16-mkmlizer: quantized model in 35.778s
alexxi19-ft-v1-violet-v16-mkmlizer: Processed model alexxi19/ft-v1-violet in 67.188s
alexxi19-ft-v1-violet-v16-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-violet-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-violet-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16
alexxi19-ft-v1-violet-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16/config.json
alexxi19-ft-v1-violet-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16/special_tokens_map.json
alexxi19-ft-v1-violet-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16/tokenizer_config.json
alexxi19-ft-v1-violet-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16/tokenizer.json
alexxi19-ft-v1-violet-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v16/flywheel_model.0.safetensors
alexxi19-ft-v1-violet-v16-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:06, 56.38it/s]
Loading 0: 6%|▌ | 22/363 [00:00<00:03, 86.34it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:03, 86.75it/s]
Loading 0: 11%|█ | 40/363 [00:00<00:03, 82.05it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:03, 83.28it/s]
Loading 0: 16%|█▌ | 58/363 [00:00<00:03, 84.17it/s]
Loading 0: 18%|█▊ | 67/363 [00:01<00:14, 20.78it/s]
Loading 0: 21%|██ | 77/363 [00:01<00:10, 28.28it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 35.60it/s]
Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 41.39it/s]
Loading 0: 28%|██▊ | 103/363 [00:02<00:05, 48.06it/s]
Loading 0: 31%|███ | 112/363 [00:02<00:04, 55.16it/s]
Loading 0: 33%|███▎ | 121/363 [00:02<00:03, 62.42it/s]
Loading 0: 36%|███▌ | 130/363 [00:02<00:03, 68.23it/s]
Loading 0: 38%|███▊ | 139/363 [00:02<00:03, 68.14it/s]
Loading 0: 40%|████ | 147/363 [00:03<00:10, 20.47it/s]
Loading 0: 43%|████▎ | 157/363 [00:03<00:07, 26.67it/s]
Loading 0: 46%|████▌ | 167/363 [00:04<00:05, 34.79it/s]
Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 40.78it/s]
Loading 0: 51%|█████ | 184/363 [00:04<00:03, 46.94it/s]
Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 53.37it/s]
Loading 0: 56%|█████▌ | 202/363 [00:04<00:02, 60.39it/s]
Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 66.81it/s]
Loading 0: 61%|██████ | 220/363 [00:04<00:02, 71.26it/s]
Loading 0: 63%|██████▎ | 229/363 [00:05<00:06, 20.04it/s]
Loading 0: 66%|██████▌ | 238/363 [00:06<00:04, 25.96it/s]
Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 34.05it/s]
Loading 0: 71%|███████ | 258/363 [00:06<00:02, 42.90it/s]
Loading 0: 74%|███████▎ | 267/363 [00:06<00:01, 48.31it/s]
Loading 0: 76%|███████▌ | 275/363 [00:06<00:01, 52.80it/s]
Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 58.06it/s]
Loading 0: 80%|████████ | 292/363 [00:06<00:01, 64.94it/s]
Loading 0: 83%|████████▎ | 301/363 [00:06<00:00, 69.48it/s]
Loading 0: 85%|████████▌ | 310/363 [00:07<00:02, 20.68it/s]
Loading 0: 88%|████████▊ | 319/363 [00:08<00:01, 26.47it/s]
Loading 0: 90%|█████████ | 328/363 [00:08<00:01, 33.39it/s]
Loading 0: 93%|█████████▎| 337/363 [00:08<00:00, 40.58it/s]
Loading 0: 95%|█████████▌| 346/363 [00:08<00:00, 47.38it/s]
Loading 0: 98%|█████████▊| 355/363 [00:08<00:00, 52.44it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00, 4.29it/s]
Job alexxi19-ft-v1-violet-v16-mkmlizer completed after 93.87s with status: succeeded
Stopping job with name alexxi19-ft-v1-violet-v16-mkmlizer
Pipeline stage MKMLizer completed in 94.35s
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 alexxi19-ft-v1-violet-v16
Waiting for inference service alexxi19-ft-v1-violet-v16 to be ready
Inference service alexxi19-ft-v1-violet-v16 ready after 210.73032569885254s
Pipeline stage MKMLDeployer completed in 211.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7655982971191406s
Received healthy response to inference request in 1.3375475406646729s
Received healthy response to inference request in 0.9283108711242676s
Received healthy response to inference request in 1.0704052448272705s
Received healthy response to inference request in 0.8920531272888184s
5 requests
0 failed requests
5th percentile: 0.8993046760559082
10th percentile: 0.906556224822998
20th percentile: 0.9210593223571777
30th percentile: 0.9567297458648681
40th percentile: 1.0135674953460694
50th percentile: 1.0704052448272705
60th percentile: 1.1772621631622315
70th percentile: 1.2841190814971923
80th percentile: 1.4231576919555664
90th percentile: 1.5943779945373535
95th percentile: 1.679988145828247
99th percentile: 1.748476266860962
mean time: 1.198783016204834
Pipeline stage StressChecker completed in 7.34s
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
alexxi19-ft-v1-violet_v16 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2290.46s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v16 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-violet_v16 status is now torndown due to DeploymentManager action
alexxi19-ft-v1-violet_v16 status is now torndown due to DeploymentManager action
admin requested tearing down of alexxi19-ft-v1-violet_v16
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
admin requested tearing down of alexxi19-ft-v1-violet_v6
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 0.49s
run pipeline %s
Shutdown handler de-registered
run pipeline stage %s
run pipeline stage %s
alexxi19-ft-v1-violet_v16 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter