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-v15-mkmlizer
Waiting for job on alexxi19-ft-v1-violet-v15-mkmlizer to finish
alexxi19-ft-v1-violet-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-violet-v15-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ Version: 0.11.12 ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-violet-v15-mkmlizer: ║ ║
alexxi19-ft-v1-violet-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-violet-v15-mkmlizer: Downloaded to shared memory in 30.305s
alexxi19-ft-v1-violet-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp20ee8eo2, device:0
alexxi19-ft-v1-violet-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-violet-v15-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-v15-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Failed to get response for submission alexdaoud-trainer-humof_91326_v2: ('http://zonemercy-lexical-viral-7348-v17-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34030->127.0.0.1:8080: read: connection reset by peer\n')
alexxi19-ft-v1-violet-v15-mkmlizer: quantized model in 35.957s
alexxi19-ft-v1-violet-v15-mkmlizer: Processed model alexxi19/ft-v1-violet in 66.262s
alexxi19-ft-v1-violet-v15-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-violet-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-violet-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15
alexxi19-ft-v1-violet-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15/config.json
alexxi19-ft-v1-violet-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15/special_tokens_map.json
alexxi19-ft-v1-violet-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15/tokenizer_config.json
alexxi19-ft-v1-violet-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15/tokenizer.json
alexxi19-ft-v1-violet-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v15/flywheel_model.0.safetensors
alexxi19-ft-v1-violet-v15-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:06, 54.14it/s]
Loading 0: 5%|▍ | 17/363 [00:00<00:04, 78.12it/s]
Loading 0: 7%|▋ | 26/363 [00:00<00:04, 82.81it/s]
Loading 0: 10%|▉ | 35/363 [00:00<00:04, 78.30it/s]
Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 76.18it/s]
Loading 0: 14%|█▍ | 52/363 [00:00<00:03, 79.86it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:16, 18.63it/s]
Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 24.43it/s]
Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.98it/s]
Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 38.60it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 46.49it/s]
Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 53.84it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 58.61it/s]
Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 62.52it/s]
Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 68.21it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.43it/s]
Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 25.74it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.92it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 39.35it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:03, 46.98it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 54.12it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 58.19it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 63.34it/s]
Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 68.82it/s]
Loading 0: 61%|██████▏ | 223/363 [00:06<00:06, 20.36it/s]
Loading 0: 64%|██████▍ | 232/363 [00:06<00:04, 26.44it/s]
Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.35it/s]
Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 39.44it/s]
Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 46.80it/s]
Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 54.32it/s]
Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 61.22it/s]
Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 65.17it/s]
Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 67.79it/s]
Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.89it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 27.04it/s]
Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 33.95it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 40.44it/s]
Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 46.76it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 54.26it/s]
Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 61.16it/s]
Job alexxi19-ft-v1-violet-v15-mkmlizer completed after 93.87s with status: succeeded
Stopping job with name alexxi19-ft-v1-violet-v15-mkmlizer
Pipeline stage MKMLizer completed in 94.33s
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 alexxi19-ft-v1-violet-v15
Waiting for inference service alexxi19-ft-v1-violet-v15 to be ready
Inference service alexxi19-ft-v1-violet-v15 ready after 210.67914509773254s
Pipeline stage MKMLDeployer completed in 211.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6986918449401855s
Received healthy response to inference request in 1.1846373081207275s
Received healthy response to inference request in 1.5925452709197998s
Received healthy response to inference request in 1.120821475982666s
Received healthy response to inference request in 1.8062372207641602s
5 requests
0 failed requests
5th percentile: 1.1335846424102782
10th percentile: 1.1463478088378907
20th percentile: 1.1718741416931153
30th percentile: 1.266218900680542
40th percentile: 1.429382085800171
50th percentile: 1.5925452709197998
60th percentile: 1.6350039005279542
70th percentile: 1.6774625301361084
80th percentile: 1.7202009201049804
90th percentile: 1.7632190704345703
95th percentile: 1.7847281455993653
99th percentile: 1.8019354057312011
mean time: 1.480586624145508
Pipeline stage StressChecker completed in 8.62s
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 0.66s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v15 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 0.10s
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 alexxi19-ft-v1-violet-v15-profiler
Waiting for inference service alexxi19-ft-v1-violet-v15-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 2303.19s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v15 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-violet_v15 status is now torndown due to DeploymentManager action
alexxi19-ft-v1-violet_v15 status is now torndown due to DeploymentManager action
alexxi19-ft-v1-violet_v15 status is now torndown due to DeploymentManager action