submission_id: alkahestry-stheno-l3-8b_v6
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Stheno-L3-8B
reward_repo: Jellywibble/CHAI_alignment_reward_model
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': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system\nYou are now in roleplay chat mode. Engage in an endless chat with {user_name}. Always wait {user_name} turn, next actions and responses. You will fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}<|end_header_id|>", 'prompt_template': '{prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>', 'bot_template': '{bot_name}: {message}<|eot_id|>', 'user_template': '{user_name}: {message}<|eot_id|>', '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: 2024-06-16T01:29:42+00:00
model_name: alkahestry-stheno-l3-8b_v5
model_eval_status: success
model_group: alkahestry/Stheno-L3-8B
num_battles: 11293
num_wins: 4761
celo_rating: 1119.58
propriety_score: 0.7348670563831793
propriety_total_count: 5303.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1024
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: Jellywibble/CHAI_alignment_reward_model
us_pacific_date: 2024-06-15
win_ratio: 0.4215885947046843
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-stheno-l3-8b-v6-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v6-mkmlizer to finish
alkahestry-stheno-l3-8b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-stheno-l3-8b-v6-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
alkahestry-stheno-l3-8b-v6-mkmlizer: conn = connection.create_connection(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/connection.py", line 72, in create_connection
alkahestry-stheno-l3-8b-v6-mkmlizer: for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 955, in getaddrinfo
alkahestry-stheno-l3-8b-v6-mkmlizer: for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
alkahestry-stheno-l3-8b-v6-mkmlizer: socket.gaierror: [Errno -3] Temporary failure in name resolution
alkahestry-stheno-l3-8b-v6-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v6-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 714, in urlopen
alkahestry-stheno-l3-8b-v6-mkmlizer: httplib_response = self._make_request(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 403, in _make_request
alkahestry-stheno-l3-8b-v6-mkmlizer: self._validate_conn(conn)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1053, in _validate_conn
alkahestry-stheno-l3-8b-v6-mkmlizer: conn.connect()
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
alkahestry-stheno-l3-8b-v6-mkmlizer: self.sock = conn = self._new_conn()
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
alkahestry-stheno-l3-8b-v6-mkmlizer: raise NewConnectionError(
alkahestry-stheno-l3-8b-v6-mkmlizer: urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x7fe7e25f7280>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution
alkahestry-stheno-l3-8b-v6-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v6-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
alkahestry-stheno-l3-8b-v6-mkmlizer: resp = conn.urlopen(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 798, in urlopen
alkahestry-stheno-l3-8b-v6-mkmlizer: retries = retries.increment(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
alkahestry-stheno-l3-8b-v6-mkmlizer: raise MaxRetryError(_pool, url, error or ResponseError(cause))
alkahestry-stheno-l3-8b-v6-mkmlizer: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/9f/2c/eb91fbec5a4afbdc0f991/d20d257871c35d777096acf1ffac2438bbae1f09c0bfb3190663e5caba759081?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00004.safetensors%3B+filename%3D%22model-00001-of-00004.safetensors%22%3B&Expires=1718760591&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODc2MDU5MX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzlmLzJjLzlmMmNhOTc2MGM4YmRiZWZkZDVhZTczNzA0MTM5Y2NjNTQxYWJhODI1ZGJlYjkxZmJlYzVhNGFmYmRjMGY5OTEvZDIwZDI1Nzg3MWMzNWQ3NzcwOTZhY2YxZmZhYzI0MzhiYmFlMWYwOWMwYmZiMzE5MDY2M2U1Y2FiYTc1OTA4MT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=rGg0nifC~J4vY97pmN2KA68RIBh9Znw2H8rNYSZw3I3yxgYC1rSs3k99jloTRx8RDkgDmdZpCdAXPY4XPND4HDY3p-b9LjThT4NP-5YxlUqi2WQa3ofXLXLREizVnpTguB7hZB62lnwrsqvIxpYHnEUjuNVo3ASorGwsAcnNjzVYm0KWc3O3HVlShvNdKtuaCHmZJI7taqpRiyBVPzT0GHN4qzxc3RD5pWPdUpOjKklUUnTNPkIg3hDRZw1ti5PaCoQnbfWkYb~pYE-PurMGonzvad59MxPv2ANWUlfpZvuLV-OR9KvfGdO31Rp5h~dJcVdi7ulpGZW5LaQfHYe1Lw__&Key-Pair-Id=K2FPYV99P2N66Q (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7fe7e25f7280>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
alkahestry-stheno-l3-8b-v6-mkmlizer: During handling of the above exception, another exception occurred:
alkahestry-stheno-l3-8b-v6-mkmlizer: Traceback (most recent call last):
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
alkahestry-stheno-l3-8b-v6-mkmlizer: cli()
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
alkahestry-stheno-l3-8b-v6-mkmlizer: return self.main(*args, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
alkahestry-stheno-l3-8b-v6-mkmlizer: rv = self.invoke(ctx)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
alkahestry-stheno-l3-8b-v6-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
alkahestry-stheno-l3-8b-v6-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
alkahestry-stheno-l3-8b-v6-mkmlizer: return __callback(*args, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
alkahestry-stheno-l3-8b-v6-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
alkahestry-stheno-l3-8b-v6-mkmlizer: snapshot_download(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
alkahestry-stheno-l3-8b-v6-mkmlizer: return fn(*args, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 314, in snapshot_download
alkahestry-stheno-l3-8b-v6-mkmlizer: _inner_hf_hub_download(file)
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: return hf_hub_download(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
alkahestry-stheno-l3-8b-v6-mkmlizer: return fn(*args, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
alkahestry-stheno-l3-8b-v6-mkmlizer: http_get(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 456, in http_get
alkahestry-stheno-l3-8b-v6-mkmlizer: r = _request_wrapper(
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 392, in _request_wrapper
alkahestry-stheno-l3-8b-v6-mkmlizer: response = get_session().request(method=method, url=url, **params)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
alkahestry-stheno-l3-8b-v6-mkmlizer: resp = self.send(prep, **send_kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
alkahestry-stheno-l3-8b-v6-mkmlizer: r = adapter.send(request, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 68, in send
alkahestry-stheno-l3-8b-v6-mkmlizer: return super().send(request, *args, **kwargs)
alkahestry-stheno-l3-8b-v6-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 519, in send
alkahestry-stheno-l3-8b-v6-mkmlizer: raise ConnectionError(e, request=request)
alkahestry-stheno-l3-8b-v6-mkmlizer: requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/9f/2c/eb91fbec5a4afbdc0f991/d20d257871c35d777096acf1ffac2438bbae1f09c0bfb3190663e5caba759081?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00004.safetensors%3B+filename%3D%22model-00001-of-00004.safetensors%22%3B&Expires=1718760591&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODc2MDU5MX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzlmLzJjLzlmMmNhOTc2MGM4YmRiZWZkZDVhZTczNzA0MTM5Y2NjNTQxYWJhODI1ZGJlYjkxZmJlYzVhNGFmYmRjMGY5OTEvZDIwZDI1Nzg3MWMzNWQ3NzcwOTZhY2YxZmZhYzI0MzhiYmFlMWYwOWMwYmZiMzE5MDY2M2U1Y2FiYTc1OTA4MT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=rGg0nifC~J4vY97pmN2KA68RIBh9Znw2H8rNYSZw3I3yxgYC1rSs3k99jloTRx8RDkgDmdZpCdAXPY4XPND4HDY3p-b9LjThT4NP-5YxlUqi2WQa3ofXLXLREizVnpTguB7hZB62lnwrsqvIxpYHnEUjuNVo3ASorGwsAcnNjzVYm0KWc3O3HVlShvNdKtuaCHmZJI7taqpRiyBVPzT0GHN4qzxc3RD5pWPdUpOjKklUUnTNPkIg3hDRZw1ti5PaCoQnbfWkYb~pYE-PurMGonzvad59MxPv2ANWUlfpZvuLV-OR9KvfGdO31Rp5h~dJcVdi7ulpGZW5LaQfHYe1Lw__&Key-Pair-Id=K2FPYV99P2N66Q (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7fe7e25f7280>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"), '(Request ID: fc70d5dc-75d7-41d3-b572-33e3ec34d095)')
Job alkahestry-stheno-l3-8b-v6-mkmlizer completed after 22.86s with status: failed
Stopping job with name alkahestry-stheno-l3-8b-v6-mkmlizer
%s, retrying in %s seconds...
Starting job with name alkahestry-stheno-l3-8b-v6-mkmlizer
Waiting for job on alkahestry-stheno-l3-8b-v6-mkmlizer to finish
alkahestry-stheno-l3-8b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ _____ __ __ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ /___/ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ https://mk1.ai ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ belonging to: ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Chai Research Corp. ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ║ ║
alkahestry-stheno-l3-8b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-stheno-l3-8b-v6-mkmlizer: unable to retrieve container logs for containerd://3e813f6b354cde71ed28c
alkahestry-stheno-l3-8b-v6-mkmlizer: Downloaded to shared memory in 47.013s
alkahestry-stheno-l3-8b-v6-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-stheno-l3-8b-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-stheno-l3-8b-v6-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%|▍ | 13/291 [00:04<01:19, 3.51it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:37, 7.23it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:21, 11.98it/s] Loading 0: 15%|█▌ | 45/291 [00:05<00:12, 19.40it/s] Loading 0: 20%|█▉ | 58/291 [00:05<00:08, 28.79it/s] Loading 0: 23%|██▎ | 68/291 [00:05<00:08, 27.32it/s] Loading 0: 27%|██▋ | 80/291 [00:05<00:05, 37.13it/s] Loading 0: 32%|███▏ | 94/291 [00:06<00:03, 49.88it/s] Loading 0: 36%|███▌ | 105/291 [00:06<00:03, 57.44it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 73.42it/s] Loading 0: 45%|████▌ | 132/291 [00:06<00:02, 77.06it/s] Loading 0: 51%|█████ | 148/291 [00:06<00:01, 90.90it/s] Loading 0: 55%|█████▍ | 160/291 [00:06<00:01, 85.42it/s] Loading 0: 59%|█████▉ | 171/291 [00:07<00:02, 56.64it/s] Loading 0: 63%|██████▎ | 184/291 [00:07<00:01, 67.75it/s] Loading 0: 67%|██████▋ | 194/291 [00:07<00:01, 73.72it/s] Loading 0: 70%|███████ | 204/291 [00:07<00:01, 77.98it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 93.17it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:00, 92.35it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:00, 103.93it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 101.59it/s] Loading 0: 93%|█████████▎| 270/291 [00:08<00:00, 62.94it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 66.91it/s] Loading 0: 99%|█████████▉| 288/291 [00:08<00:00, 70.35it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-stheno-l3-8b-v6-mkmlizer: quantized model in 24.432s
alkahestry-stheno-l3-8b-v6-mkmlizer: Processed model alkahestry/Stheno-L3-8B in 74.059s
alkahestry-stheno-l3-8b-v6-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-stheno-l3-8b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-stheno-l3-8b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6/special_tokens_map.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6/config.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6/tokenizer_config.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6/tokenizer.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-stheno-l3-8b-v6/flywheel_model.0.safetensors
alkahestry-stheno-l3-8b-v6-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v6-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-v6-mkmlizer: warnings.warn(
alkahestry-stheno-l3-8b-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-stheno-l3-8b-v6-mkmlizer: Saving duration: 0.153s
alkahestry-stheno-l3-8b-v6-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 2.453s
alkahestry-stheno-l3-8b-v6-mkmlizer: creating bucket guanaco-reward-models
alkahestry-stheno-l3-8b-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-stheno-l3-8b-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/special_tokens_map.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/config.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/tokenizer_config.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/merges.txt
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/vocab.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/tokenizer.json
alkahestry-stheno-l3-8b-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-stheno-l3-8b-v6_reward/reward.tensors
Job alkahestry-stheno-l3-8b-v6-mkmlizer completed after 114.7s with status: succeeded
Stopping job with name alkahestry-stheno-l3-8b-v6-mkmlizer
Pipeline stage MKMLizer completed in 141.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-stheno-l3-8b-v6
Waiting for inference service alkahestry-stheno-l3-8b-v6 to be ready
Inference service alkahestry-stheno-l3-8b-v6 ready after 40.27350449562073s
Pipeline stage ISVCDeployer completed in 47.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0572750568389893s
Received healthy response to inference request in 1.1885278224945068s
Received healthy response to inference request in 1.1982858180999756s
Received healthy response to inference request in 1.2031946182250977s
Received healthy response to inference request in 6.178509950637817s
5 requests
0 failed requests
5th percentile: 1.1904794216156005
10th percentile: 1.1924310207366944
20th percentile: 1.196334218978882
30th percentile: 1.199267578125
40th percentile: 1.201231098175049
50th percentile: 1.2031946182250977
60th percentile: 1.5448267936706541
70th percentile: 1.8864589691162108
80th percentile: 2.8815220355987554
90th percentile: 4.530015993118287
95th percentile: 5.354262971878051
99th percentile: 6.013660554885864
mean time: 2.3651586532592774
Pipeline stage StressChecker completed in 12.80s
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
alkahestry-stheno-l3-8b_v6 status is now deployed due to DeploymentManager action
alkahestry-stheno-l3-8b_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics