submission_id: steelskull-l3-ms-astoria-70b_v2
developer_uid: windyheath
status: inactive
model_repo: Steelskull/L3-MS-Astoria-70b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-07T21:05:10+00:00
model_name: steelskull-l3-ms-astoria-70b_v2
model_eval_status: success
model_group: Steelskull/L3-MS-Astoria
num_battles: 14145
num_wins: 7478
celo_rating: 1196.52
safety_score: 0.94
propriety_score: 0.7099236641221374
propriety_total_count: 1048.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 70553706496.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: steelskull-l3-ms-astoria-70b_v2
ineligible_reason: propriety_total_count < 5000
language_model: Steelskull/L3-MS-Astoria-70b
model_size: 71B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-07
win_ratio: 0.5286673736302581
Resubmit model
Running pipeline stage MKMLizer
Starting job with name steelskull-l3-ms-astoria-70b-v2-mkmlizer
Waiting for job on steelskull-l3-ms-astoria-70b-v2-mkmlizer to finish
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ _____ __ __ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ /___/ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Version: 0.8.14 ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ https://mk1.ai ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ belonging to: ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Chai Research Corp. ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
steelskull-l3-ms-astoria-70b-v2-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.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Traceback (most recent call last):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
steelskull-l3-ms-astoria-70b-v2-mkmlizer: conn = connection.create_connection(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/connection.py", line 72, in create_connection
steelskull-l3-ms-astoria-70b-v2-mkmlizer: for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 955, in getaddrinfo
steelskull-l3-ms-astoria-70b-v2-mkmlizer: for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: socket.gaierror: [Errno -3] Temporary failure in name resolution
steelskull-l3-ms-astoria-70b-v2-mkmlizer: During handling of the above exception, another exception occurred:
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Traceback (most recent call last):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 714, in urlopen
steelskull-l3-ms-astoria-70b-v2-mkmlizer: httplib_response = self._make_request(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 403, in _make_request
steelskull-l3-ms-astoria-70b-v2-mkmlizer: self._validate_conn(conn)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1053, in _validate_conn
steelskull-l3-ms-astoria-70b-v2-mkmlizer: conn.connect()
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
steelskull-l3-ms-astoria-70b-v2-mkmlizer: self.sock = conn = self._new_conn()
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
steelskull-l3-ms-astoria-70b-v2-mkmlizer: raise NewConnectionError(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x7fc7aeed2560>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution
steelskull-l3-ms-astoria-70b-v2-mkmlizer: During handling of the above exception, another exception occurred:
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Traceback (most recent call last):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
steelskull-l3-ms-astoria-70b-v2-mkmlizer: resp = conn.urlopen(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 798, in urlopen
steelskull-l3-ms-astoria-70b-v2-mkmlizer: retries = retries.increment(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
steelskull-l3-ms-astoria-70b-v2-mkmlizer: raise MaxRetryError(_pool, url, error or ResponseError(cause))
steelskull-l3-ms-astoria-70b-v2-mkmlizer: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/56/fd/b62873c43f7fc51fa0c4b/91492861539c6eed6c878a93b03b0281314bfc9a9e67c61c3db41831cd067dda?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00013-of-00015.safetensors%3B+filename%3D%22model-00013-of-00015.safetensors%22%3B&Expires=1718053766&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODA1Mzc2Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzU2L2ZkLzU2ZmQ0OGFlZjRhZmI0ODU1MWVhMjE3MDM1OWRjOTI5NDAzZTRmNWY3NGRiNjI4NzNjNDNmN2ZjNTFmYTBjNGIvOTE0OTI4NjE1MzljNmVlZDZjODc4YTkzYjAzYjAyODEzMTRiZmM5YTllNjdjNjFjM2RiNDE4MzFjZDA2N2RkYT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=bQoct~YN9BqQRkq5PBkKvYJ17YEL2xYrRSuuHoGUwN9BDNGWlEHyICV4yBloRmuSkwj9qE3YdBH3Hu~6pASn6thKqqWiSP6aCIEQLiD~Wc0CjCF7vBy5Si-ULULQXRcQg-9Zs6XaWC0DuGfWZt1boOZG9jxJF3OeXLKjsstdQbuUwLLVT5gGbNxlDXZQd5Ijz-BJlWa0jcuJBuSjwA8Jsw8JGEZjLEx~kPK2L8VG4u7SlJiMC8ncFB5TAM5dP76wAc1FHdWbW6yNs7KBKRqTr83wVazgwTXH0pHbk7e5xSSNZnHjrceJKdMEbHCxdKdYveE~iBChnl4KWTyGCRaDvg__&Key-Pair-Id=KCD77M1F0VK2B (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7fc7aeed2560>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
steelskull-l3-ms-astoria-70b-v2-mkmlizer: During handling of the above exception, another exception occurred:
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Traceback (most recent call last):
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cli()
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return self.main(*args, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
steelskull-l3-ms-astoria-70b-v2-mkmlizer: rv = self.invoke(ctx)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return __callback(*args, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
steelskull-l3-ms-astoria-70b-v2-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
steelskull-l3-ms-astoria-70b-v2-mkmlizer: snapshot_download(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return fn(*args, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 314, in snapshot_download
steelskull-l3-ms-astoria-70b-v2-mkmlizer: _inner_hf_hub_download(file)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 290, in _inner_hf_hub_download
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return hf_hub_download(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return fn(*args, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
steelskull-l3-ms-astoria-70b-v2-mkmlizer: http_get(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 456, in http_get
steelskull-l3-ms-astoria-70b-v2-mkmlizer: r = _request_wrapper(
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 392, in _request_wrapper
steelskull-l3-ms-astoria-70b-v2-mkmlizer: response = get_session().request(method=method, url=url, **params)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
steelskull-l3-ms-astoria-70b-v2-mkmlizer: resp = self.send(prep, **send_kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
steelskull-l3-ms-astoria-70b-v2-mkmlizer: r = adapter.send(request, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 68, in send
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return super().send(request, *args, **kwargs)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 519, in send
steelskull-l3-ms-astoria-70b-v2-mkmlizer: raise ConnectionError(e, request=request)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/56/fd/b62873c43f7fc51fa0c4b/91492861539c6eed6c878a93b03b0281314bfc9a9e67c61c3db41831cd067dda?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00013-of-00015.safetensors%3B+filename%3D%22model-00013-of-00015.safetensors%22%3B&Expires=1718053766&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODA1Mzc2Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzU2L2ZkLzU2ZmQ0OGFlZjRhZmI0ODU1MWVhMjE3MDM1OWRjOTI5NDAzZTRmNWY3NGRiNjI4NzNjNDNmN2ZjNTFmYTBjNGIvOTE0OTI4NjE1MzljNmVlZDZjODc4YTkzYjAzYjAyODEzMTRiZmM5YTllNjdjNjFjM2RiNDE4MzFjZDA2N2RkYT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=bQoct~YN9BqQRkq5PBkKvYJ17YEL2xYrRSuuHoGUwN9BDNGWlEHyICV4yBloRmuSkwj9qE3YdBH3Hu~6pASn6thKqqWiSP6aCIEQLiD~Wc0CjCF7vBy5Si-ULULQXRcQg-9Zs6XaWC0DuGfWZt1boOZG9jxJF3OeXLKjsstdQbuUwLLVT5gGbNxlDXZQd5Ijz-BJlWa0jcuJBuSjwA8Jsw8JGEZjLEx~kPK2L8VG4u7SlJiMC8ncFB5TAM5dP76wAc1FHdWbW6yNs7KBKRqTr83wVazgwTXH0pHbk7e5xSSNZnHjrceJKdMEbHCxdKdYveE~iBChnl4KWTyGCRaDvg__&Key-Pair-Id=KCD77M1F0VK2B (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7fc7aeed2560>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"), '(Request ID: 26f6b0db-3fe4-4546-915b-bc6c6bbdeb74)')
Job steelskull-l3-ms-astoria-70b-v2-mkmlizer completed after 278.64s with status: failed
Stopping job with name steelskull-l3-ms-astoria-70b-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name steelskull-l3-ms-astoria-70b-v2-mkmlizer
Waiting for job on steelskull-l3-ms-astoria-70b-v2-mkmlizer to finish
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ _____ __ __ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ /___/ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Version: 0.8.14 ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ https://mk1.ai ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ belonging to: ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Chai Research Corp. ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ║ ║
steelskull-l3-ms-astoria-70b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
steelskull-l3-ms-astoria-70b-v2-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.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Downloaded to shared memory in 141.152s
steelskull-l3-ms-astoria-70b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 0%| | 2/723 [00:09<54:38, 4.55s/it] Loading 0: 1%| | 6/723 [00:09<14:25, 1.21s/it] Loading 0: 2%|▏ | 14/723 [00:09<04:43, 2.50it/s] Loading 0: 3%|▎ | 22/723 [00:09<02:27, 4.74it/s] Loading 0: 4%|▎ | 27/723 [00:09<01:47, 6.50it/s] Loading 0: 4%|▍ | 32/723 [00:10<01:39, 6.95it/s] Loading 0: 6%|▌ | 40/723 [00:10<01:02, 10.87it/s] Loading 0: 6%|▌ | 45/723 [00:10<00:49, 13.57it/s] Loading 0: 7%|▋ | 50/723 [00:10<00:40, 16.81it/s] Loading 0: 8%|▊ | 58/723 [00:10<00:28, 23.20it/s] Loading 0: 9%|▊ | 63/723 [00:10<00:25, 26.06it/s] Loading 0: 9%|▉ | 68/723 [00:10<00:22, 29.28it/s] Loading 0: 11%|█ | 76/723 [00:11<00:17, 36.14it/s] Loading 0: 11%|█ | 81/723 [00:11<00:17, 36.96it/s] Loading 0: 12%|█▏ | 86/723 [00:11<00:33, 19.26it/s] Loading 0: 13%|█▎ | 94/723 [00:11<00:24, 25.87it/s] Loading 0: 14%|█▎ | 99/723 [00:12<00:21, 28.67it/s] Loading 0: 14%|█▍ | 104/723 [00:12<00:19, 31.21it/s] Loading 0: 15%|█▌ | 112/723 [00:25<06:20, 1.61it/s] Loading 0: 16%|█▌ | 116/723 [00:25<05:00, 2.02it/s] Loading 0: 17%|█▋ | 122/723 [00:25<03:28, 2.88it/s] Loading 0: 18%|█▊ | 130/723 [00:25<02:13, 4.46it/s] Loading 0: 19%|█▊ | 135/723 [00:26<01:57, 4.99it/s] Loading 0: 19%|█▉ | 140/723 [00:26<01:29, 6.49it/s] Loading 0: 20%|██ | 148/723 [00:26<00:58, 9.77it/s] Loading 0: 21%|██ | 153/723 [00:26<00:47, 12.11it/s] Loading 0: 22%|██▏ | 158/723 [00:26<00:37, 15.05it/s] Loading 0: 23%|██▎ | 166/723 [00:26<00:26, 20.95it/s] Loading 0: 24%|██▎ | 171/723 [00:26<00:23, 23.93it/s] Loading 0: 24%|██▍ | 176/723 [00:26<00:20, 27.26it/s] Loading 0: 25%|██▌ | 184/723 [00:26<00:15, 34.38it/s] Loading 0: 26%|██▋ | 190/723 [00:27<00:26, 20.25it/s] Loading 0: 27%|██▋ | 194/723 [00:27<00:23, 22.62it/s] Loading 0: 28%|██▊ | 202/723 [00:27<00:17, 29.65it/s] Loading 0: 29%|██▊ | 207/723 [00:27<00:16, 31.84it/s] Loading 0: 29%|██▉ | 212/723 [00:28<00:14, 34.34it/s] Loading 0: 30%|███ | 220/723 [00:28<00:12, 40.95it/s] Loading 0: 31%|███ | 225/723 [00:28<00:12, 41.03it/s] Loading 0: 32%|███▏ | 230/723 [00:28<00:11, 41.32it/s] Loading 0: 33%|███▎ | 238/723 [00:28<00:10, 46.76it/s] Loading 0: 34%|███▎ | 243/723 [00:29<00:21, 21.99it/s] Loading 0: 34%|███▍ | 247/723 [00:41<00:21, 21.99it/s] Loading 0: 34%|███▍ | 248/723 [00:41<05:31, 1.43it/s] Loading 0: 35%|███▍ | 253/723 [00:41<04:01, 1.95it/s] Loading 0: 36%|███▌ | 257/723 [00:41<03:06, 2.50it/s] Loading 0: 36%|███▌ | 261/723 [00:42<02:20, 3.28it/s] Loading 0: 37%|███▋ | 266/723 [00:42<01:40, 4.53it/s] Loading 0: 37%|███▋ | 270/723 [00:42<01:16, 5.90it/s] Loading 0: 38%|███▊ | 274/723 [00:42<00:58, 7.68it/s] Loading 0: 38%|███▊ | 278/723 [00:42<00:46, 9.51it/s] Loading 0: 39%|███▉ | 283/723 [00:42<00:34, 12.78it/s] Loading 0: 40%|███▉ | 287/723 [00:42<00:29, 14.73it/s] Loading 0: 40%|████ | 292/723 [00:43<00:38, 11.12it/s] Loading 0: 41%|████ | 295/723 [00:43<00:34, 12.32it/s] Loading 0: 42%|████▏ | 301/723 [00:43<00:24, 17.42it/s] Loading 0: 42%|████▏ | 305/723 [00:44<00:21, 19.00it/s] Loading 0: 43%|████▎ | 310/723 [00:44<00:17, 23.21it/s] Loading 0: 43%|████▎ | 314/723 [00:44<00:17, 23.71it/s] Loading 0: 44%|████▍ | 319/723 [00:44<00:14, 27.48it/s] Loading 0: 45%|████▍ | 323/723 [00:44<00:15, 26.46it/s] Loading 0: 45%|████▌ | 328/723 [00:44<00:13, 29.88it/s] Loading 0: 46%|████▌ | 332/723 [00:44<00:13, 27.96it/s] Loading 0: 47%|████▋ | 337/723 [00:45<00:12, 31.15it/s] Loading 0: 47%|████▋ | 341/723 [00:45<00:13, 28.81it/s] Loading 0: 48%|████▊ | 345/723 [00:45<00:24, 15.30it/s] Loading 0: 48%|████▊ | 348/723 [00:45<00:25, 14.74it/s] Loading 0: 49%|████▉ | 355/723 [00:46<00:17, 21.51it/s] Loading 0: 50%|████▉ | 359/723 [00:46<00:16, 22.19it/s] Loading 0: 50%|█████ | 364/723 [00:46<00:13, 25.97it/s] Loading 0: 51%|█████ | 368/723 [00:46<00:13, 25.53it/s] Loading 0: 52%|█████▏ | 373/723 [00:46<00:12, 29.05it/s] Loading 0: 52%|█████▏ | 377/723 [00:46<00:12, 27.48it/s] Loading 0: 53%|█████▎ | 382/723 [00:46<00:11, 30.73it/s] Loading 0: 53%|█████▎ | 386/723 [01:00<05:15, 1.07it/s] Loading 0: 54%|█████▍ | 391/723 [01:00<03:32, 1.56it/s] Loading 0: 55%|█████▍ | 395/723 [01:01<02:52, 1.91it/s] Loading 0: 55%|█████▌ | 400/723 [01:01<01:56, 2.77it/s] Loading 0: 56%|█████▌ | 404/723 [01:01<01:27, 3.65it/s] Loading 0: 57%|█████▋ | 409/723 [01:01<01:00, 5.19it/s] Loading 0: 57%|█████▋ | 413/723 [01:02<00:46, 6.61it/s] Loading 0: 58%|█████▊ | 418/723 [01:02<00:33, 9.11it/s] Loading 0: 58%|█████▊ | 422/723 [01:02<00:27, 10.96it/s] Loading 0: 59%|█████▉ | 427/723 [01:02<00:20, 14.34it/s] Loading 0: 60%|█████▉ | 431/723 [01:02<00:18, 15.98it/s] Loading 0: 60%|██████ | 436/723 [01:02<00:14, 19.90it/s] Loading 0: 61%|██████ | 440/723 [01:02<00:14, 20.06it/s] Loading 0: 62%|██████▏ | 445/723 [01:03<00:12, 23.10it/s] Loading 0: 62%|██████▏ | 449/723 [01:03<00:22, 12.40it/s] Loading 0: 63%|██████▎ | 454/723 [01:03<00:16, 16.07it/s] Loading 0: 63%|██████▎ | 457/723 [01:04<00:16, 16.52it/s] Loading 0: 64%|██████▍ | 463/723 [01:04<00:11, 22.17it/s] Loading 0: 65%|██████▍ | 467/723 [01:04<00:11, 22.70it/s] Loading 0: 65%|██████▌ | 472/723 [01:04<00:09, 26.45it/s] Loading 0: 66%|██████▌ | 476/723 [01:04<00:09, 25.81it/s] Loading 0: 67%|██████▋ | 481/723 [01:04<00:08, 29.52it/s] Loading 0: 67%|██████▋ | 485/723 [01:04<00:08, 27.66it/s] Loading 0: 68%|██████▊ | 490/723 [01:05<00:07, 30.88it/s] Loading 0: 68%|██████▊ | 494/723 [01:05<00:08, 28.39it/s] Loading 0: 69%|██████▉ | 499/723 [01:05<00:15, 14.43it/s] Loading 0: 69%|██████▉ | 502/723 [01:06<00:14, 15.18it/s] Loading 0: 70%|███████ | 508/723 [01:06<00:10, 20.92it/s] Loading 0: 71%|███████ | 512/723 [01:06<00:09, 22.01it/s] Loading 0: 72%|███████▏ | 517/723 [01:06<00:07, 26.17it/s] Loading 0: 72%|███████▏ | 521/723 [01:06<00:07, 25.40it/s] Loading 0: 73%|███████▎ | 525/723 [01:19<03:02, 1.09it/s] Loading 0: 73%|███████▎ | 527/723 [01:19<02:32, 1.28it/s] Loading 0: 73%|███████▎ | 531/723 [01:19<01:43, 1.86it/s] Loading 0: 74%|███████▍ | 535/723 [01:19<01:11, 2.65it/s] Loading 0: 75%|███████▍ | 539/723 [01:20<00:50, 3.64it/s] Loading 0: 75%|███████▌ | 544/723 [01:20<00:33, 5.37it/s] Loading 0: 76%|███████▌ | 548/723 [01:20<00:25, 6.89it/s] Loading 0: 76%|███████▌ | 551/723 [01:21<00:29, 5.85it/s] Loading 0: 77%|███████▋ | 554/723 [01:21<00:23, 7.09it/s] Loading 0: 77%|███████▋ | 558/723 [01:21<00:17, 9.58it/s] Loading 0: 78%|███████▊ | 562/723 [01:21<00:12, 12.62it/s] Loading 0: 78%|███████▊ | 565/723 [01:21<00:11, 13.72it/s] Loading 0: 79%|███████▉ | 571/723 [01:21<00:07, 19.59it/s] Loading 0: 80%|███████▉ | 575/723 [01:21<00:07, 20.80it/s] Loading 0: 80%|████████ | 580/723 [01:22<00:05, 24.72it/s] Loading 0: 81%|████████ | 584/723 [01:22<00:05, 24.59it/s] Loading 0: 81%|████████▏ | 589/723 [01:22<00:04, 28.19it/s] Loading 0: 82%|████████▏ | 593/723 [01:22<00:04, 26.76it/s] Loading 0: 83%|████████▎ | 598/723 [01:22<00:04, 30.12it/s] Loading 0: 83%|████████▎ | 602/723 [01:23<00:09, 13.29it/s] Loading 0: 84%|████████▍ | 607/723 [01:23<00:06, 17.06it/s] Loading 0: 84%|████████▍ | 610/723 [01:23<00:06, 17.33it/s] Loading 0: 85%|████████▌ | 616/723 [01:23<00:04, 22.91it/s] Loading 0: 86%|████████▌ | 620/723 [01:23<00:04, 23.17it/s] Loading 0: 86%|████████▋ | 625/723 [01:24<00:03, 27.04it/s] Loading 0: 87%|████████▋ | 629/723 [01:24<00:03, 26.42it/s] Loading 0: 88%|████████▊ | 634/723 [01:24<00:02, 30.15it/s] Loading 0: 88%|████████▊ | 638/723 [01:24<00:02, 28.46it/s] Loading 0: 89%|████████▉ | 643/723 [01:24<00:02, 31.73it/s] Loading 0: 89%|████████▉ | 647/723 [01:24<00:02, 29.42it/s] Loading 0: 90%|█████████ | 652/723 [01:24<00:02, 32.34it/s] Loading 0: 91%|█████████ | 656/723 [01:25<00:04, 14.29it/s] Loading 0: 91%|█████████▏| 661/723 [01:25<00:03, 18.20it/s] Loading 0: 92%|█████████▏| 665/723 [01:38<00:53, 1.09it/s] Loading 0: 93%|█████████▎| 670/723 [01:38<00:33, 1.59it/s] Loading 0: 93%|█████████▎| 674/723 [01:38<00:22, 2.13it/s] Loading 0: 94%|█████████▍| 679/723 [01:39<00:14, 3.09it/s] Loading 0: 94%|█████████▍| 683/723 [01:39<00:09, 4.06it/s] Loading 0: 95%|█████████▌| 688/723 [01:39<00:06, 5.73it/s] Loading 0: 96%|█████████▌| 692/723 [01:39<00:04, 7.19it/s] Loading 0: 96%|█████████▋| 697/723 [01:39<00:02, 9.76it/s] Loading 0: 97%|█████████▋| 701/723 [01:39<00:01, 11.49it/s] Loading 0: 98%|█████████▊| 706/723 [01:40<00:01, 9.10it/s] Loading 0: 98%|█████████▊| 709/723 [01:40<00:01, 10.13it/s] Loading 0: 99%|█████████▉| 715/723 [01:40<00:00, 14.43it/s] Loading 0: 99%|█████████▉| 718/723 [01:41<00:00, 14.90it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: quantized model in 117.914s
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Processed model Steelskull/L3-MS-Astoria-70b in 269.521s
steelskull-l3-ms-astoria-70b-v2-mkmlizer: creating bucket guanaco-mkml-models
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
steelskull-l3-ms-astoria-70b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/config.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/special_tokens_map.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/tokenizer_config.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/tokenizer.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.5.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.0.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.1.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.4.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.2.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/steelskull-l3-ms-astoria-70b-v2/flywheel_model.3.safetensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
steelskull-l3-ms-astoria-70b-v2-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.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: warnings.warn(
steelskull-l3-ms-astoria-70b-v2-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.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: warnings.warn(
steelskull-l3-ms-astoria-70b-v2-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.
steelskull-l3-ms-astoria-70b-v2-mkmlizer: warnings.warn(
steelskull-l3-ms-astoria-70b-v2-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()
steelskull-l3-ms-astoria-70b-v2-mkmlizer: return self.fget.__get__(instance, owner)()
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Saving duration: 0.245s
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.570s
steelskull-l3-ms-astoria-70b-v2-mkmlizer: creating bucket guanaco-reward-models
steelskull-l3-ms-astoria-70b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
steelskull-l3-ms-astoria-70b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/config.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/special_tokens_map.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/tokenizer_config.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/merges.txt
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/vocab.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/tokenizer.json
steelskull-l3-ms-astoria-70b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/steelskull-l3-ms-astoria-70b-v2_reward/reward.tensors
Job steelskull-l3-ms-astoria-70b-v2-mkmlizer completed after 392.34s with status: succeeded
Stopping job with name steelskull-l3-ms-astoria-70b-v2-mkmlizer
Pipeline stage MKMLizer completed in 671.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service steelskull-l3-ms-astoria-70b-v2
Waiting for inference service steelskull-l3-ms-astoria-70b-v2 to be ready
Inference service steelskull-l3-ms-astoria-70b-v2 ready after 90.47402358055115s
Pipeline stage ISVCDeployer completed in 96.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.07284140586853s
Received healthy response to inference request in 4.2175421714782715s
Received healthy response to inference request in 4.1860551834106445s
Received healthy response to inference request in 4.187040090560913s
Received healthy response to inference request in 4.190171718597412s
5 requests
0 failed requests
5th percentile: 4.186252164840698
10th percentile: 4.186449146270752
20th percentile: 4.1868431091308596
30th percentile: 4.187666416168213
40th percentile: 4.1889190673828125
50th percentile: 4.190171718597412
60th percentile: 4.201119899749756
70th percentile: 4.2120680809021
80th percentile: 4.388602018356323
90th percentile: 4.730721712112427
95th percentile: 4.9017815589904785
99th percentile: 5.03862943649292
mean time: 4.3707301139831545
Pipeline stage StressChecker completed in 22.92s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
steelskull-l3-ms-astoria-70b_v2 status is now deployed due to DeploymentManager action
steelskull-l3-ms-astoria-70b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics