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 rinen0721-mistral-dpo-0213-m2-v1-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0213-m2-v1-mkmlizer to finish
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Version: 0.12.8 ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Traceback (most recent call last):
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: response.raise_for_status()
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: raise HTTPError(http_error_msg, response=self)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: requests.exceptions.HTTPError: 504 Server Error: Gateway Time-out for url: https://huggingface.co/api/models/rinen0721/Mistral-dpo-0213-m2/paths-info/main
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: The above exception was the direct cause of the following exception:
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Traceback (most recent call last):
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 193, in <module>
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cli()
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: return self.main(*args, **kwargs)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: rv = self.invoke(ctx)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: return __callback(*args, **kwargs)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 39, in quantize
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 81, in download_to_shared_memory
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: if repo_has_model_safetensors(repo_id, revision, token):
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 104, in repo_has_model_safetensors
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: files = [f.path for f in get_paths_info(repo_id, revision=revision, paths=["/"], token=token)]
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: return fn(*args, **kwargs)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/hf_api.py", line 3259, in get_paths_info
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: hf_raise_for_status(response)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 477, in hf_raise_for_status
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: raise _format(HfHubHTTPError, str(e), response) from e
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: huggingface_hub.errors.HfHubHTTPError: 504 Server Error: Gateway Time-out for url: https://huggingface.co/api/models/rinen0721/Mistral-dpo-0213-m2/paths-info/main
Job rinen0721-mistral-dpo-0213-m2-v1-mkmlizer completed after 33.44s with status: failed
Stopping job with name rinen0721-mistral-dpo-0213-m2-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name rinen0721-mistral-dpo-0213-m2-v1-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0213-m2-v1-mkmlizer to finish
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Version: 0.12.8 ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Downloaded to shared memory in 50.543s
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsdihmfym, device:0
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0213-m2-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.
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: quantized model in 35.894s
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Processed model rinen0721/Mistral-dpo-0213-m2 in 86.438s
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1/config.json
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1/special_tokens_map.json
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1/tokenizer_config.json
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1/tokenizer.json
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m2-v1/flywheel_model.0.safetensors
rinen0721-mistral-dpo-0213-m2-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:07, 46.13it/s]
Loading 0: 4%|▍ | 16/363 [00:00<00:05, 62.59it/s]
Loading 0: 7%|▋ | 25/363 [00:00<00:04, 69.21it/s]
Loading 0: 9%|▉ | 34/363 [00:00<00:04, 73.53it/s]
Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 76.08it/s]
Loading 0: 14%|█▍ | 52/363 [00:00<00:04, 73.04it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.19it/s]
Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 25.50it/s]
Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.74it/s]
Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 39.52it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 45.81it/s]
Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 53.35it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 60.26it/s]
Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 65.68it/s]
Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 64.83it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.48it/s]
Loading 0: 42%|████▏ | 151/363 [00:04<00:07, 26.58it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 33.57it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.27it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 46.18it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 53.55it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 59.95it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 64.07it/s]
Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 66.69it/s]
Loading 0: 61%|██████▏ | 223/363 [00:06<00:06, 20.32it/s]
Loading 0: 64%|██████▍ | 232/363 [00:06<00:04, 26.31it/s]
Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.18it/s]
Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 39.66it/s]
Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 44.87it/s]
Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 51.56it/s]
Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 58.91it/s]
Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 64.97it/s]
Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 63.11it/s]
Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.63it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 26.56it/s]
Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 33.23it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 39.38it/s]
Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 44.73it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 49.55it/s]
Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 55.68it/s]
Job rinen0721-mistral-dpo-0213-m2-v1-mkmlizer completed after 145.57s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0213-m2-v1-mkmlizer
Pipeline stage MKMLizer completed in 179.94s
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 rinen0721-mistral-dpo-0213-m2-v1
Waiting for inference service rinen0721-mistral-dpo-0213-m2-v1 to be ready
Failed to get response for submission dtnewman-20250212-c-4ep_25732_v1: HTTPConnectionPool(host='dtnewman-20250212-c-4ep-25732-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rinen0721-mistral-dpo-0213-m2-v1 ready after 170.5976161956787s
Pipeline stage MKMLDeployer completed in 171.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8062334060668945s
Received healthy response to inference request in 1.4513428211212158s
Received healthy response to inference request in 0.7900164127349854s
Received healthy response to inference request in 1.6643829345703125s
Received healthy response to inference request in 1.4657070636749268s
5 requests
0 failed requests
5th percentile: 0.9222816944122314
10th percentile: 1.0545469760894775
20th percentile: 1.3190775394439698
30th percentile: 1.454215669631958
40th percentile: 1.4599613666534423
50th percentile: 1.4657070636749268
60th percentile: 1.545177412033081
70th percentile: 1.6246477603912353
80th percentile: 1.6927530288696289
90th percentile: 1.7494932174682618
95th percentile: 1.7778633117675782
99th percentile: 1.8005593872070313
mean time: 1.435536527633667
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 0.67s
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 0.70s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213-m2_v1 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-mistral-dpo-0213-m2-v1-profiler
Waiting for inference service rinen0721-mistral-dpo-0213-m2-v1-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 2598.06s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213-m2_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0213-m2_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m2_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m2_v1 status is now torndown due to DeploymentManager action