submission_id: alkahestry-stheno-l3-8b_v5
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Stheno-L3-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.72, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 1000, 'presence_penalty': 0.82, 'frequency_penalty': 0.2, 'stopping_words': ['</s>', '<|im_end|>', '\n{{User}}', '<|eot_id|>', '<|end_of_text|>', '\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: 2024-06-16T01:22:20+00:00
model_name: alkahestry-stheno-l3-8b_v5
model_eval_status: success
model_group: alkahestry/Stheno-L3-8B
num_battles: 11363
num_wins: 5433
celo_rating: 1158.65
propriety_score: 0.6973073351903436
propriety_total_count: 5385.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: alkahestry-stheno-l3-8b_v5
ineligible_reason: None
language_model: alkahestry/Stheno-L3-8B
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-15
win_ratio: 0.47813077532341813
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-stheno-l3-8b-v5-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v5-mkmlizer to finish
Stopping job with name alkahestry-stheno-l3-8b-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name alkahestry-stheno-l3-8b-v5-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v5-mkmlizer to finish
alkahestry-stheno-l3-8b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-v5-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.
alkahestry-stheno-l3-8b-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-stheno-l3-8b-v5-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
alkahestry-stheno-l3-8b-v5-mkmlizer: conn = connection.create_connection(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/connection.py", line 72, in create_connection
alkahestry-stheno-l3-8b-v5-mkmlizer: for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 955, in getaddrinfo
alkahestry-stheno-l3-8b-v5-mkmlizer: for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
alkahestry-stheno-l3-8b-v5-mkmlizer: socket.gaierror: [Errno -3] Temporary failure in name resolution
alkahestry-stheno-l3-8b-v5-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v5-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 714, in urlopen
alkahestry-stheno-l3-8b-v5-mkmlizer: httplib_response = self._make_request(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 403, in _make_request
alkahestry-stheno-l3-8b-v5-mkmlizer: self._validate_conn(conn)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1053, in _validate_conn
alkahestry-stheno-l3-8b-v5-mkmlizer: conn.connect()
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
alkahestry-stheno-l3-8b-v5-mkmlizer: self.sock = conn = self._new_conn()
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
alkahestry-stheno-l3-8b-v5-mkmlizer: raise NewConnectionError(
alkahestry-stheno-l3-8b-v5-mkmlizer: urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x7f6d04f8bbb0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution
alkahestry-stheno-l3-8b-v5-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v5-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
alkahestry-stheno-l3-8b-v5-mkmlizer: resp = conn.urlopen(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 798, in urlopen
alkahestry-stheno-l3-8b-v5-mkmlizer: retries = retries.increment(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
alkahestry-stheno-l3-8b-v5-mkmlizer: raise MaxRetryError(_pool, url, error or ResponseError(cause))
alkahestry-stheno-l3-8b-v5-mkmlizer: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/9f/2c/eb91fbec5a4afbdc0f991/472f041b925c3cdc90ba71c62d4bbdb91af00ff92dbb7f714f0b253093bdc2f3?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=1718760174&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODc2MDE3NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzlmLzJjLzlmMmNhOTc2MGM4YmRiZWZkZDVhZTczNzA0MTM5Y2NjNTQxYWJhODI1ZGJlYjkxZmJlYzVhNGFmYmRjMGY5OTEvNDcyZjA0MWI5MjVjM2NkYzkwYmE3MWM2MmQ0YmJkYjkxYWYwMGZmOTJkYmI3ZjcxNGYwYjI1MzA5M2JkYzJmMz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=Ef6k~DKNFmxPTFJ7fkU3GcshPZ8yfc4b~inLR3AnPvP0Q0C~toSbwItvnVFLlfOycpEwVaXH0UT98b~BGkRTIJytqo79SyksH6NOPCneBkJw5ZnMeSg1-C-8peN0G4c0RLZr5hIJCxchghN-kUBDagwFBL9SkjvZgtqANjNdbCAfgtLskcyp0JzcvP6-~RYlf58ZEz0GdyeOSOLtHQvrZbBufKitDrMq4SJ8nlhOhi8IevPMaZj6196F7aA0B9wVzvDQTKl6NF9TJkYw6DIa~41CQ21bJgiGFe-8WGzCNe~j~N6HI4rCx0F-SJxo9sKUiTc1I8GVCA6go74vYoSjAA__&Key-Pair-Id=K2FPYV99P2N66Q (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f6d04f8bbb0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
alkahestry-stheno-l3-8b-v5-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v5-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
alkahestry-stheno-l3-8b-v5-mkmlizer: cli()
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
alkahestry-stheno-l3-8b-v5-mkmlizer: return self.main(*args, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
alkahestry-stheno-l3-8b-v5-mkmlizer: rv = self.invoke(ctx)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
alkahestry-stheno-l3-8b-v5-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
alkahestry-stheno-l3-8b-v5-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
alkahestry-stheno-l3-8b-v5-mkmlizer: return __callback(*args, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
alkahestry-stheno-l3-8b-v5-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
alkahestry-stheno-l3-8b-v5-mkmlizer: snapshot_download(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
alkahestry-stheno-l3-8b-v5-mkmlizer: return fn(*args, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 314, in snapshot_download
alkahestry-stheno-l3-8b-v5-mkmlizer: _inner_hf_hub_download(file)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 290, in _inner_hf_hub_download
alkahestry-stheno-l3-8b-v5-mkmlizer: return hf_hub_download(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
alkahestry-stheno-l3-8b-v5-mkmlizer: return fn(*args, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
alkahestry-stheno-l3-8b-v5-mkmlizer: http_get(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 456, in http_get
alkahestry-stheno-l3-8b-v5-mkmlizer: r = _request_wrapper(
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 392, in _request_wrapper
alkahestry-stheno-l3-8b-v5-mkmlizer: response = get_session().request(method=method, url=url, **params)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
alkahestry-stheno-l3-8b-v5-mkmlizer: resp = self.send(prep, **send_kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
alkahestry-stheno-l3-8b-v5-mkmlizer: r = adapter.send(request, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 68, in send
alkahestry-stheno-l3-8b-v5-mkmlizer: return super().send(request, *args, **kwargs)
alkahestry-stheno-l3-8b-v5-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 519, in send
alkahestry-stheno-l3-8b-v5-mkmlizer: raise ConnectionError(e, request=request)
alkahestry-stheno-l3-8b-v5-mkmlizer: requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/9f/2c/eb91fbec5a4afbdc0f991/472f041b925c3cdc90ba71c62d4bbdb91af00ff92dbb7f714f0b253093bdc2f3?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=1718760174&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODc2MDE3NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzlmLzJjLzlmMmNhOTc2MGM4YmRiZWZkZDVhZTczNzA0MTM5Y2NjNTQxYWJhODI1ZGJlYjkxZmJlYzVhNGFmYmRjMGY5OTEvNDcyZjA0MWI5MjVjM2NkYzkwYmE3MWM2MmQ0YmJkYjkxYWYwMGZmOTJkYmI3ZjcxNGYwYjI1MzA5M2JkYzJmMz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=Ef6k~DKNFmxPTFJ7fkU3GcshPZ8yfc4b~inLR3AnPvP0Q0C~toSbwItvnVFLlfOycpEwVaXH0UT98b~BGkRTIJytqo79SyksH6NOPCneBkJw5ZnMeSg1-C-8peN0G4c0RLZr5hIJCxchghN-kUBDagwFBL9SkjvZgtqANjNdbCAfgtLskcyp0JzcvP6-~RYlf58ZEz0GdyeOSOLtHQvrZbBufKitDrMq4SJ8nlhOhi8IevPMaZj6196F7aA0B9wVzvDQTKl6NF9TJkYw6DIa~41CQ21bJgiGFe-8WGzCNe~j~N6HI4rCx0F-SJxo9sKUiTc1I8GVCA6go74vYoSjAA__&Key-Pair-Id=K2FPYV99P2N66Q (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f6d04f8bbb0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"), '(Request ID: 84613203-7ece-4726-97fb-73136b915db4)')
Job alkahestry-stheno-l3-8b-v5-mkmlizer completed after 44.54s with status: failed
Stopping job with name alkahestry-stheno-l3-8b-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name alkahestry-stheno-l3-8b-v5-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v5-mkmlizer to finish
alkahestry-stheno-l3-8b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-v5-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.
alkahestry-stheno-l3-8b-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-stheno-l3-8b-v5-mkmlizer: Downloaded to shared memory in 42.285s
alkahestry-stheno-l3-8b-v5-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-stheno-l3-8b-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-stheno-l3-8b-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:44, 2.44s/it] Loading 0: 4%|▍ | 11/291 [00:04<01:34, 2.96it/s] Loading 0: 8%|▊ | 22/291 [00:05<00:37, 7.09it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:20, 12.37it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:10, 22.37it/s] Loading 0: 21%|██ | 60/291 [00:05<00:09, 23.74it/s] Loading 0: 24%|██▍ | 71/291 [00:05<00:06, 31.57it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:04, 42.77it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 48.47it/s] Loading 0: 36%|███▌ | 104/291 [00:06<00:03, 54.55it/s] Loading 0: 39%|███▉ | 113/291 [00:06<00:02, 60.50it/s] Loading 0: 42%|████▏ | 122/291 [00:06<00:02, 65.76it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 72.18it/s] Loading 0: 48%|████▊ | 141/291 [00:06<00:01, 75.94it/s] Loading 0: 52%|█████▏ | 150/291 [00:06<00:01, 78.06it/s] Loading 0: 55%|█████▍ | 159/291 [00:06<00:01, 80.72it/s] Loading 0: 58%|█████▊ | 168/291 [00:07<00:02, 48.43it/s] Loading 0: 61%|██████ | 177/291 [00:07<00:02, 55.57it/s] Loading 0: 64%|██████▍ | 186/291 [00:07<00:01, 62.21it/s] Loading 0: 69%|██████▉ | 202/291 [00:07<00:01, 80.64it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:00, 79.86it/s] Loading 0: 76%|███████▌ | 221/291 [00:07<00:00, 81.55it/s] Loading 0: 79%|███████▉ | 230/291 [00:07<00:00, 82.68it/s] Loading 0: 82%|████████▏ | 240/291 [00:07<00:00, 86.36it/s] Loading 0: 88%|████████▊ | 256/291 [00:08<00:00, 101.54it/s] Loading 0: 92%|█████████▏| 267/291 [00:08<00:00, 58.13it/s] Loading 0: 95%|█████████▍| 276/291 [00:08<00:00, 63.01it/s] Loading 0: 98%|█████████▊| 285/291 [00:08<00:00, 67.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-stheno-l3-8b-v5-mkmlizer: quantized model in 24.862s
alkahestry-stheno-l3-8b-v5-mkmlizer: Processed model alkahestry/Stheno-L3-8B in 69.795s
alkahestry-stheno-l3-8b-v5-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-stheno-l3-8b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-stheno-l3-8b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5/config.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5/special_tokens_map.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5/tokenizer_config.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5/tokenizer.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v5/flywheel_model.0.safetensors
alkahestry-stheno-l3-8b-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alkahestry-stheno-l3-8b-v5-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.
alkahestry-stheno-l3-8b-v5-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v5-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.
alkahestry-stheno-l3-8b-v5-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v5-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.
alkahestry-stheno-l3-8b-v5-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v5-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()
alkahestry-stheno-l3-8b-v5-mkmlizer: return self.fget.__get__(instance, owner)()
alkahestry-stheno-l3-8b-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-stheno-l3-8b-v5-mkmlizer: Saving duration: 0.419s
alkahestry-stheno-l3-8b-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.345s
alkahestry-stheno-l3-8b-v5-mkmlizer: creating bucket guanaco-reward-models
alkahestry-stheno-l3-8b-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-stheno-l3-8b-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/config.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/special_tokens_map.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/tokenizer_config.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/merges.txt
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/vocab.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/tokenizer.json
alkahestry-stheno-l3-8b-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v5_reward/reward.tensors
Job alkahestry-stheno-l3-8b-v5-mkmlizer completed after 116.7s with status: succeeded
Stopping job with name alkahestry-stheno-l3-8b-v5-mkmlizer
Pipeline stage MKMLizer completed in 169.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-stheno-l3-8b-v5
Waiting for inference service alkahestry-stheno-l3-8b-v5 to be ready
Inference service alkahestry-stheno-l3-8b-v5 ready after 40.57050585746765s
Pipeline stage ISVCDeployer completed in 48.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.94647216796875s
Received healthy response to inference request in 1.1654112339019775s
Received healthy response to inference request in 8.10921025276184s
Received healthy response to inference request in 1.1535792350769043s
Received healthy response to inference request in 1.1559405326843262s
5 requests
0 failed requests
5th percentile: 1.1540514945983886
10th percentile: 1.154523754119873
20th percentile: 1.1554682731628418
30th percentile: 1.1578346729278564
40th percentile: 1.161622953414917
50th percentile: 1.1654112339019775
60th percentile: 1.4778356075286865
70th percentile: 1.7902599811553954
80th percentile: 3.1790197849273696
90th percentile: 5.644115018844605
95th percentile: 6.876662635803221
99th percentile: 7.8627007293701165
mean time: 2.7061226844787596
Pipeline stage StressChecker completed in 14.50s
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 0.06s
M-Eval Dataset for topic stay_in_character is loaded
alkahestry-stheno-l3-8b_v5 status is now deployed due to DeploymentManager action
alkahestry-stheno-l3-8b_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics