Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer to finish
Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Traceback (most recent call last):
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 509, in http_get
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: hf_transfer.download(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Exception: Failed too many failures in parallel (3): PyErr { type: <class 'Exception'>, value: Exception('Error while downloading: reqwest::Error { kind: Status(503), url: Url { scheme: "https", cannot_be_a_base: false, username: "", password: None, host: Some(Domain("cdn-lfs-us-1.huggingface.co")), port: None, path: "/repos/07/99/57133d260de79bffe4a48/76a5659c9633f89855fa17c2b9363d4ee08100820fa83dcb4439a6b7519ca214", query: Some("response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00003-of-00004.safetensors%3B+filename%3D%22model-00003-of-00004.safetensors%22%3B&Expires=1720096286&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcyMDA5NjI4Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzA3Lzk5LzA3OTlhNTdmOGQ0Njk0MzA1Yzk2YWNiZjgwNTE3ZDdjMzUyZDY5ODdhNzk1NzEzM2QyNjBkZTc5YmZmZTRhNDgvNzZhNTY1OWM5NjMzZjg5ODU1ZmExN2MyYjkzNjNkNGVlMDgxMDA4MjBmYTgzZGNiNDQzOWE2Yjc1MTljYTIxND9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=hOJfGRdcR3kEAVViaBUaEmLm52OjHcnPK4MvTKzHMcKgDTn7DjghvOxwB0l8kbQNsDY4EqdoqzvIZGlcc0lMWU2HuLg8MepqiN48MiVDvaTNHSCosf0J6RVmrnhKSvBVZYT%7EFOzJjtrGI9cQ2kf2MHOJ%7EAvvofjrvpECxOS6KbWb5whHFF2zICg0QoI0cDd8gTHjoe-MBxGOOERI5auY0UKTJTmjnnUpi6YTE02vMEVjzN0l-zH0SuDqMmLHeIS1ldMZXpC5isR5J%7ED9addAZ4W2o0TdTh0F8HLsDdoJwZJPIeJubSR9zsXR8kD4qTj%7Eh0Z5E6Rf8B%7E9j11zWO08xw__&Key-Pair-Id=K24J24Z295AEI9"), fragment: None } }'), traceback: None } (NoPermits)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: The above exception was the direct cause of the following exception:
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Traceback (most recent call last):
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cli()
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return self.main(*args, **kwargs)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: rv = self.invoke(ctx)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return __callback(*args, **kwargs)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: snapshot_download(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return fn(*args, **kwargs)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 314, in snapshot_download
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: _inner_hf_hub_download(file)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 290, in _inner_hf_hub_download
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return hf_hub_download(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return fn(*args, **kwargs)
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: http_get(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 520, in http_get
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: raise RuntimeError(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: RuntimeError: An error occurred while downloading using `hf_transfer`. Consider disabling HF_HUB_ENABLE_HF_TRANSFER for better error handling.
Job bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer completed after 146.53s with status: failed
Stopping job with name bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Downloaded to shared memory in 37.456s
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: unable to retrieve container logs for containerd://7b7302dc4686722ecc0cf
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 110.16it/s]
Loading 0: 9%|▉ | 27/291 [00:00<00:02, 123.12it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 122.24it/s]
Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 123.19it/s]
Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 124.12it/s]
Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 124.90it/s]
Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 70.61it/s]
Loading 0: 36%|███▌ | 104/291 [00:01<00:02, 77.17it/s]
Loading 0: 41%|████ | 120/291 [00:01<00:01, 94.48it/s]
Loading 0: 45%|████▌ | 132/291 [00:01<00:01, 98.46it/s]
Loading 0: 51%|█████ | 147/291 [00:01<00:01, 110.42it/s]
Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 112.26it/s]
Loading 0: 59%|█████▉ | 173/291 [00:01<00:01, 116.61it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 76.81it/s]
Loading 0: 68%|██████▊ | 197/291 [00:02<00:01, 79.87it/s]
Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 89.79it/s]
Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 91.44it/s]
Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 106.03it/s]
Loading 0: 86%|████████▌ | 249/291 [00:02<00:00, 105.18it/s]
Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 114.08it/s]
Loading 0: 95%|█████████▍| 276/291 [00:02<00:00, 110.31it/s]
Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 6.66it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: quantized model in 26.117s
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3.1_e1.5 in 66.202s
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1/config.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-8449-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Saving duration: 0.430s
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.481s
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-8449-v1_reward/reward.tensors
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Downloaded to shared memory in 42.192s
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Job bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer completed after 239.88s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-8449-v1-mkmlizer
Pipeline stage MKMLizer completed in 240.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-8449-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-3-8449-v1 to be ready
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 9/291 [00:00<00:03, 87.06it/s]
Loading 0: 6%|▌ | 18/291 [00:00<00:03, 87.67it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:02, 98.35it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 91.17it/s]
Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 92.59it/s]
Loading 0: 21%|██ | 61/291 [00:00<00:02, 93.17it/s]
Loading 0: 24%|██▍ | 71/291 [00:00<00:02, 92.25it/s]
Loading 0: 28%|██▊ | 81/291 [00:00<00:02, 90.87it/s]
Loading 0: 31%|███▏ | 91/291 [00:01<00:04, 47.63it/s]
Loading 0: 35%|███▌ | 102/291 [00:01<00:03, 57.92it/s]
Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 64.10it/s]
Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 70.00it/s]
Loading 0: 45%|████▌ | 131/291 [00:01<00:02, 74.31it/s]
Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 77.45it/s]
Loading 0: 53%|█████▎ | 153/291 [00:01<00:01, 90.14it/s]
Loading 0: 57%|█████▋ | 165/291 [00:02<00:01, 92.95it/s]
Loading 0: 60%|██████ | 175/291 [00:02<00:01, 90.98it/s]
Loading 0: 64%|██████▎ | 185/291 [00:02<00:01, 90.46it/s]
Loading 0: 67%|██████▋ | 195/291 [00:02<00:01, 48.71it/s]
Loading 0: 70%|██████▉ | 203/291 [00:03<00:02, 34.47it/s]
Loading 0: 72%|███████▏ | 210/291 [00:03<00:02, 36.52it/s]
Loading 0: 75%|███████▌ | 219/291 [00:03<00:01, 43.12it/s]
Loading 0: 78%|███████▊ | 228/291 [00:03<00:01, 49.37it/s]
Loading 0: 81%|████████▏ | 237/291 [00:03<00:00, 55.15it/s]
Loading 0: 85%|████████▍ | 246/291 [00:03<00:00, 60.08it/s]
Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 64.59it/s]
Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 69.53it/s]
Loading 0: 94%|█████████▍| 274/291 [00:04<00:00, 73.33it/s]
Loading 0: 97%|█████████▋| 282/291 [00:04<00:00, 72.75it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 4.47it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: quantized model in 27.678s
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.3.1_e2 in 73.217s
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1/config.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Saving duration: 0.528s
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.470s
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/config.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-3-1-e2-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer completed after 117.94s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-3-1-e2-v1-mkmlizer
Pipeline stage MKMLizer completed in 265.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.23s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-3-1-e2-v1
Inference service bbchicago-brt-8b-l3-v1-3-8449-v1 ready after 50.23304748535156s
Pipeline stage ISVCDeployer completed in 57.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1898059844970703s
Received healthy response to inference request in 1.3152961730957031s
Waiting for inference service bbchicago-brt-8b-l3-v1-3-1-e2-v1 to be ready
Received healthy response to inference request in 1.4820775985717773s
Received healthy response to inference request in 1.2697205543518066s
Received healthy response to inference request in 1.3284626007080078s
5 requests
0 failed requests
5th percentile: 1.2788356781005858
10th percentile: 1.2879508018493653
20th percentile: 1.306181049346924
30th percentile: 1.317929458618164
40th percentile: 1.323196029663086
50th percentile: 1.3284626007080078
60th percentile: 1.3899085998535157
70th percentile: 1.4513545989990233
80th percentile: 1.623623275756836
90th percentile: 1.9067146301269533
95th percentile: 2.0482603073120114
99th percentile: 2.1614968490600583
mean time: 1.517072582244873
Pipeline stage StressChecker completed in 10.24s
bbchicago-brt-8b-l3-v1-3_8449_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-3_8449_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-3_8449_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-3-8449-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.28s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-3-8449-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.56s
bbchicago-brt-8b-l3-v1-3_8449_v1 status is now torndown due to DeploymentManager action