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 pocketdoc-dans-creepings-2540-v1-mkmlizer
Waiting for job on pocketdoc-dans-creepings-2540-v1-mkmlizer to finish
pocketdoc-dans-creepings-2540-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ _____ __ __ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ /___/ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ Version: 0.11.12 ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ https://mk1.ai ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ The license key for the current software has been verified as ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ belonging to: ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ Chai Research Corp. ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ║ ║
pocketdoc-dans-creepings-2540-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission cloudyu-nemo-dpo-v22_v18: HTTPConnectionPool(host='cloudyu-nemo-dpo-v22-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission stark2000s-10-14-dpo-re_40695_v3: ('http://stark2000s-10-14-dpo-re-40695-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39368->127.0.0.1:8080: read: connection reset by peer\n')
pocketdoc-dans-creepings-2540-v1-mkmlizer: Downloaded to shared memory in 43.376s
pocketdoc-dans-creepings-2540-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyy796gph, device:0
pocketdoc-dans-creepings-2540-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pocketdoc-dans-creepings-2540-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.
pocketdoc-dans-creepings-2540-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
pocketdoc-dans-creepings-2540-v1-mkmlizer: quantized model in 30.725s
pocketdoc-dans-creepings-2540-v1-mkmlizer: Processed model PocketDoc/Dans-CreepingSenseOfDoom-13b in 74.101s
pocketdoc-dans-creepings-2540-v1-mkmlizer: creating bucket guanaco-mkml-models
pocketdoc-dans-creepings-2540-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pocketdoc-dans-creepings-2540-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/config.json
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/added_tokens.json
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/special_tokens_map.json
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/tokenizer_config.json
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/tokenizer.model
pocketdoc-dans-creepings-2540-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pocketdoc-dans-creepings-2540-v1/flywheel_model.0.safetensors
pocketdoc-dans-creepings-2540-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:10, 32.99it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:06, 51.31it/s]
Loading 0: 6%|▌ | 22/363 [00:00<00:06, 56.56it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:05, 57.98it/s]
Loading 0: 11%|█ | 40/363 [00:00<00:05, 60.96it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 62.37it/s]
Loading 0: 16%|█▌ | 58/363 [00:00<00:04, 62.61it/s]
Loading 0: 18%|█▊ | 67/363 [00:01<00:04, 61.47it/s]
Loading 0: 21%|██ | 76/363 [00:01<00:04, 58.91it/s]
Loading 0: 23%|██▎ | 85/363 [00:01<00:04, 60.44it/s]
Loading 0: 26%|██▌ | 94/363 [00:01<00:04, 65.73it/s]
Loading 0: 28%|██▊ | 103/363 [00:01<00:03, 66.75it/s]
Loading 0: 31%|███ | 112/363 [00:01<00:03, 71.11it/s]
Loading 0: 33%|███▎ | 121/363 [00:01<00:03, 66.03it/s]
Loading 0: 36%|███▌ | 130/363 [00:02<00:03, 65.31it/s]
Loading 0: 38%|███▊ | 139/363 [00:04<00:19, 11.76it/s]
Loading 0: 41%|████ | 148/363 [00:04<00:13, 15.71it/s]
Loading 0: 43%|████▎ | 157/363 [00:04<00:09, 20.63it/s]
Loading 0: 46%|████▌ | 166/363 [00:04<00:07, 26.39it/s]
Loading 0: 48%|████▊ | 175/363 [00:04<00:05, 32.61it/s]
Loading 0: 51%|█████ | 184/363 [00:04<00:04, 39.79it/s]
Loading 0: 53%|█████▎ | 193/363 [00:05<00:03, 47.17it/s]
Loading 0: 56%|█████▌ | 202/363 [00:05<00:02, 53.87it/s]
Loading 0: 58%|█████▊ | 211/363 [00:05<00:02, 60.15it/s]
Loading 0: 61%|██████ | 220/363 [00:05<00:02, 65.91it/s]
Loading 0: 63%|██████▎ | 229/363 [00:05<00:01, 70.57it/s]
Loading 0: 66%|██████▌ | 238/363 [00:05<00:01, 73.13it/s]
Loading 0: 68%|██████▊ | 247/363 [00:05<00:01, 74.22it/s]
Loading 0: 71%|███████ | 256/363 [00:05<00:01, 74.01it/s]
Loading 0: 73%|███████▎ | 265/363 [00:05<00:01, 68.73it/s]
Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 67.86it/s]
Loading 0: 78%|███████▊ | 282/363 [00:07<00:05, 15.25it/s]
Loading 0: 79%|███████▉ | 288/363 [00:07<00:04, 17.66it/s]
Loading 0: 81%|████████▏ | 295/363 [00:07<00:03, 21.41it/s]
Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 28.03it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 35.25it/s]
Loading 0: 89%|████████▊ | 322/363 [00:08<00:00, 41.40it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 47.79it/s]
Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 53.20it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 58.28it/s]
Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 61.82it/s]
Job pocketdoc-dans-creepings-2540-v1-mkmlizer completed after 115.44s with status: succeeded
Stopping job with name pocketdoc-dans-creepings-2540-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.88s
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 pocketdoc-dans-creepings-2540-v1
Waiting for inference service pocketdoc-dans-creepings-2540-v1 to be ready
Inference service pocketdoc-dans-creepings-2540-v1 ready after 351.3616940975189s
Pipeline stage MKMLDeployer completed in 351.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8998022079467773s
Received healthy response to inference request in 0.7302255630493164s
Received healthy response to inference request in 0.5703234672546387s
Received healthy response to inference request in 0.9221987724304199s
Received healthy response to inference request in 0.7137489318847656s
5 requests
0 failed requests
5th percentile: 0.5990085601806641
10th percentile: 0.6276936531066895
20th percentile: 0.6850638389587402
30th percentile: 0.7170442581176758
40th percentile: 0.723634910583496
50th percentile: 0.7302255630493164
60th percentile: 0.8070148468017578
70th percentile: 0.8838041305541992
80th percentile: 1.1177194595336917
90th percentile: 1.5087608337402345
95th percentile: 1.7042815208435056
99th percentile: 1.860698070526123
mean time: 0.9672597885131836
Pipeline stage StressChecker completed in 6.16s
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 0.91s
Shutdown handler de-registered
pocketdoc-dans-creepings_2540_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2691.80s
Shutdown handler de-registered
pocketdoc-dans-creepings_2540_v1 status is now inactive due to auto deactivation removed underperforming models
pocketdoc-dans-creepings_2540_v1 status is now torndown due to DeploymentManager action