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 riverise-0910-2005-sft-v5-mkmlizer
Waiting for job on riverise-0910-2005-sft-v5-mkmlizer to finish
riverise-0910-2005-sft-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-0910-2005-sft-v5-mkmlizer: ║ _____ __ __ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
riverise-0910-2005-sft-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
riverise-0910-2005-sft-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ /___/ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Version: 0.12.8 ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
riverise-0910-2005-sft-v5-mkmlizer: ║ https://mk1.ai ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ The license key for the current software has been verified as ║
riverise-0910-2005-sft-v5-mkmlizer: ║ belonging to: ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Chai Research Corp. ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-0910-2005-sft-v5-mkmlizer: Traceback (most recent call last):
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 536, in _make_request
riverise-0910-2005-sft-v5-mkmlizer: response = conn.getresponse()
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 461, in getresponse
riverise-0910-2005-sft-v5-mkmlizer: httplib_response = super().getresponse()
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 1375, in getresponse
riverise-0910-2005-sft-v5-mkmlizer: response.begin()
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 318, in begin
riverise-0910-2005-sft-v5-mkmlizer: version, status, reason = self._read_status()
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 279, in _read_status
riverise-0910-2005-sft-v5-mkmlizer: line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 705, in readinto
riverise-0910-2005-sft-v5-mkmlizer: return self._sock.recv_into(b)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1307, in recv_into
riverise-0910-2005-sft-v5-mkmlizer: return self.read(nbytes, buffer)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1163, in read
riverise-0910-2005-sft-v5-mkmlizer: return self._sslobj.read(len, buffer)
riverise-0910-2005-sft-v5-mkmlizer: TimeoutError: The read operation timed out
riverise-0910-2005-sft-v5-mkmlizer: The above exception was the direct cause of the following exception:
riverise-0910-2005-sft-v5-mkmlizer: Traceback (most recent call last):
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
riverise-0910-2005-sft-v5-mkmlizer: resp = conn.urlopen(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 844, in urlopen
riverise-0910-2005-sft-v5-mkmlizer: retries = retries.increment(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 470, in increment
riverise-0910-2005-sft-v5-mkmlizer: raise reraise(type(error), error, _stacktrace)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/util.py", line 39, in reraise
riverise-0910-2005-sft-v5-mkmlizer: raise value
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 790, in urlopen
riverise-0910-2005-sft-v5-mkmlizer: response = self._make_request(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 538, in _make_request
riverise-0910-2005-sft-v5-mkmlizer: self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 370, in _raise_timeout
riverise-0910-2005-sft-v5-mkmlizer: raise ReadTimeoutError(
riverise-0910-2005-sft-v5-mkmlizer: urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)
riverise-0910-2005-sft-v5-mkmlizer: During handling of the above exception, another exception occurred:
riverise-0910-2005-sft-v5-mkmlizer: Traceback (most recent call last):
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error
riverise-0910-2005-sft-v5-mkmlizer: metadata = get_hf_file_metadata(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
riverise-0910-2005-sft-v5-mkmlizer: return fn(*args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata
riverise-0910-2005-sft-v5-mkmlizer: r = _request_wrapper(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper
riverise-0910-2005-sft-v5-mkmlizer: response = _request_wrapper(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 301, in _request_wrapper
riverise-0910-2005-sft-v5-mkmlizer: response = get_session().request(method=method, url=url, **params)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
riverise-0910-2005-sft-v5-mkmlizer: resp = self.send(prep, **send_kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
riverise-0910-2005-sft-v5-mkmlizer: r = adapter.send(request, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 93, in send
riverise-0910-2005-sft-v5-mkmlizer: return super().send(request, *args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 713, in send
riverise-0910-2005-sft-v5-mkmlizer: raise ReadTimeout(e, request=request)
riverise-0910-2005-sft-v5-mkmlizer: requests.exceptions.ReadTimeout: (ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: f51f3019-3729-431f-b0c6-bbd910297bdf)')
riverise-0910-2005-sft-v5-mkmlizer: The above exception was the direct cause of the following exception:
riverise-0910-2005-sft-v5-mkmlizer: Traceback (most recent call last):
riverise-0910-2005-sft-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 193, in <module>
riverise-0910-2005-sft-v5-mkmlizer: cli()
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
riverise-0910-2005-sft-v5-mkmlizer: return self.main(*args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
riverise-0910-2005-sft-v5-mkmlizer: rv = self.invoke(ctx)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
riverise-0910-2005-sft-v5-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
riverise-0910-2005-sft-v5-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
riverise-0910-2005-sft-v5-mkmlizer: return __callback(*args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 39, in quantize
riverise-0910-2005-sft-v5-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
riverise-0910-2005-sft-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 86, in download_to_shared_memory
riverise-0910-2005-sft-v5-mkmlizer: snapshot_download(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
riverise-0910-2005-sft-v5-mkmlizer: return fn(*args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 294, in snapshot_download
riverise-0910-2005-sft-v5-mkmlizer: _inner_hf_hub_download(file)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 270, in _inner_hf_hub_download
riverise-0910-2005-sft-v5-mkmlizer: return hf_hub_download(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
riverise-0910-2005-sft-v5-mkmlizer: return fn(*args, **kwargs)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 840, in hf_hub_download
riverise-0910-2005-sft-v5-mkmlizer: return _hf_hub_download_to_local_dir(
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1089, in _hf_hub_download_to_local_dir
riverise-0910-2005-sft-v5-mkmlizer: _raise_on_head_call_error(head_call_error, force_download, local_files_only)
riverise-0910-2005-sft-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1485, in _raise_on_head_call_error
riverise-0910-2005-sft-v5-mkmlizer: raise LocalEntryNotFoundError(
riverise-0910-2005-sft-v5-mkmlizer: huggingface_hub.errors.LocalEntryNotFoundError: An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.
Job riverise-0910-2005-sft-v5-mkmlizer completed after 47.52s with status: failed
Stopping job with name riverise-0910-2005-sft-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-0910-2005-sft-v5-mkmlizer
Waiting for job on riverise-0910-2005-sft-v5-mkmlizer to finish
riverise-0910-2005-sft-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-0910-2005-sft-v5-mkmlizer: ║ _____ __ __ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
riverise-0910-2005-sft-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
riverise-0910-2005-sft-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ /___/ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Version: 0.12.8 ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
riverise-0910-2005-sft-v5-mkmlizer: ║ https://mk1.ai ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ The license key for the current software has been verified as ║
riverise-0910-2005-sft-v5-mkmlizer: ║ belonging to: ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Chai Research Corp. ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
riverise-0910-2005-sft-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
riverise-0910-2005-sft-v5-mkmlizer: ║ ║
riverise-0910-2005-sft-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-0910-2005-sft-v5-mkmlizer: Downloaded to shared memory in 23.975s
riverise-0910-2005-sft-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy71rxxqv, device:0
riverise-0910-2005-sft-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-0910-2005-sft-v5-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.
riverise-0910-2005-sft-v5-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
riverise-0910-2005-sft-v5-mkmlizer: quantized model in 26.043s
riverise-0910-2005-sft-v5-mkmlizer: Processed model Riverise/0910_2005_sft in 50.019s
riverise-0910-2005-sft-v5-mkmlizer: creating bucket guanaco-mkml-models
riverise-0910-2005-sft-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-0910-2005-sft-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-0910-2005-sft-v5
riverise-0910-2005-sft-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-0910-2005-sft-v5/config.json
riverise-0910-2005-sft-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-0910-2005-sft-v5/special_tokens_map.json
riverise-0910-2005-sft-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-0910-2005-sft-v5/tokenizer_config.json
riverise-0910-2005-sft-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-0910-2005-sft-v5/tokenizer.json
riverise-0910-2005-sft-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-0910-2005-sft-v5/flywheel_model.0.safetensors
riverise-0910-2005-sft-v5-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.55it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 63.74it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:03, 73.85it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:03, 77.57it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 88.63it/s]
Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 81.23it/s]
Loading 0: 21%|██▏ | 62/291 [00:00<00:02, 86.68it/s]
Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 81.84it/s]
Loading 0: 27%|██▋ | 80/291 [00:01<00:02, 82.63it/s]
Loading 0: 31%|███ | 89/291 [00:02<00:09, 21.26it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:06, 30.79it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 36.22it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 43.01it/s]
Loading 0: 45%|████▌ | 131/291 [00:02<00:03, 52.09it/s]
Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 59.08it/s]
Loading 0: 51%|█████ | 149/291 [00:02<00:02, 64.37it/s]
Loading 0: 54%|█████▍ | 158/291 [00:02<00:01, 68.29it/s]
Loading 0: 57%|█████▋ | 167/291 [00:03<00:01, 72.09it/s]
Loading 0: 60%|██████ | 176/291 [00:03<00:01, 76.37it/s]
Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 78.04it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:04, 21.24it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 26.48it/s]
Loading 0: 73%|███████▎ | 213/291 [00:04<00:02, 36.00it/s]
Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 42.51it/s]
Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 49.44it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 55.84it/s]
Loading 0: 86%|████████▋ | 251/291 [00:05<00:00, 64.77it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 74.83it/s]
Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 78.10it/s]
Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 74.46it/s]
Job riverise-0910-2005-sft-v5-mkmlizer completed after 110.69s with status: succeeded
Stopping job with name riverise-0910-2005-sft-v5-mkmlizer
Pipeline stage MKMLizer completed in 159.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-0910-2005-sft-v5
Waiting for inference service riverise-0910-2005-sft-v5 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service riverise-0910-2005-sft-v5 ready after 100.44060802459717s
Pipeline stage MKMLDeployer completed in 101.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8671884536743164s
Received healthy response to inference request in 1.5656630992889404s
Received healthy response to inference request in 1.3982808589935303s
Received healthy response to inference request in 1.5103199481964111s
Received healthy response to inference request in 1.348454236984253s
5 requests
0 failed requests
5th percentile: 1.3584195613861083
10th percentile: 1.368384885787964
20th percentile: 1.388315534591675
30th percentile: 1.4206886768341065
40th percentile: 1.4655043125152587
50th percentile: 1.5103199481964111
60th percentile: 1.532457208633423
70th percentile: 1.5545944690704345
80th percentile: 1.6259681701660156
90th percentile: 1.746578311920166
95th percentile: 1.8068833827972413
99th percentile: 1.8551274394989015
mean time: 1.5379813194274903
Pipeline stage StressChecker completed in 9.54s
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 0.82s
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 0.74s
Shutdown handler de-registered
riverise-0910-2005-sft_v5 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 2515.78s
Shutdown handler de-registered
riverise-0910-2005-sft_v5 status is now inactive due to auto deactivation removed underperforming models
riverise-0910-2005-sft_v5 status is now torndown due to DeploymentManager action