developer_uid: Trace2333
submission_id: trace2333-duduk-llama2-v0_v2
model_name: trace2333-duduk-llama2-v0_v2
model_group: Trace2333/duduk_llama2_v
status: torndown
timestamp: 2024-07-03T05:15:52+00:00
num_battles: 12207
num_wins: 4974
celo_rating: 1114.32
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/duduk_llama2_v0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-duduk-llama2-v0_v2
is_internal_developer: False
language_model: Trace2333/duduk_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-07-02
win_ratio: 0.4074711231260752
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.2, 'frequency_penalty': 0.3, 'stopping_words': ['</s>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona####: {memory}", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-duduk-llama2-v0-v2-mkmlizer
Waiting for job on trace2333-duduk-llama2-v0-v2-mkmlizer to finish
trace2333-duduk-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /___/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Version: 0.8.14 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama2-v0-v2-mkmlizer: Traceback (most recent call last):
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
trace2333-duduk-llama2-v0-v2-mkmlizer: conn = connection.create_connection(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/connection.py", line 72, in create_connection
trace2333-duduk-llama2-v0-v2-mkmlizer: for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 955, in getaddrinfo
trace2333-duduk-llama2-v0-v2-mkmlizer: for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
trace2333-duduk-llama2-v0-v2-mkmlizer: socket.gaierror: [Errno -3] Temporary failure in name resolution
trace2333-duduk-llama2-v0-v2-mkmlizer: During handling of the above exception, another exception occurred:
trace2333-duduk-llama2-v0-v2-mkmlizer: Traceback (most recent call last):
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 714, in urlopen
trace2333-duduk-llama2-v0-v2-mkmlizer: httplib_response = self._make_request(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 403, in _make_request
trace2333-duduk-llama2-v0-v2-mkmlizer: self._validate_conn(conn)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1053, in _validate_conn
trace2333-duduk-llama2-v0-v2-mkmlizer: conn.connect()
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
trace2333-duduk-llama2-v0-v2-mkmlizer: self.sock = conn = self._new_conn()
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
trace2333-duduk-llama2-v0-v2-mkmlizer: raise NewConnectionError(
trace2333-duduk-llama2-v0-v2-mkmlizer: urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x7f801ad84c10>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution
trace2333-duduk-llama2-v0-v2-mkmlizer: During handling of the above exception, another exception occurred:
trace2333-duduk-llama2-v0-v2-mkmlizer: Traceback (most recent call last):
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
trace2333-duduk-llama2-v0-v2-mkmlizer: resp = conn.urlopen(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 798, in urlopen
trace2333-duduk-llama2-v0-v2-mkmlizer: retries = retries.increment(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
trace2333-duduk-llama2-v0-v2-mkmlizer: raise MaxRetryError(_pool, url, error or ResponseError(cause))
trace2333-duduk-llama2-v0-v2-mkmlizer: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/27/5f/9f1e5fe714d2d1baf781e/6cfc4aadea20c8fd1abb86638b2e3e3081bd9d7de670ae2ca57ca9354afec1cd?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00006.safetensors%3B+filename%3D%22model-00001-of-00006.safetensors%22%3B&Expires=1720242964&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcyMDI0Mjk2NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzI3LzVmLzI3NWY4NWU3NWI4YWE0YWIxOTRmOTUwZGNlZGJmNmZmY2ZiNzU4Zjk0ZGQ5ZjFlNWZlNzE0ZDJkMWJhZjc4MWUvNmNmYzRhYWRlYTIwYzhmZDFhYmI4NjYzOGIyZTNlMzA4MWJkOWQ3ZGU2NzBhZTJjYTU3Y2E5MzU0YWZlYzFjZD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=Y2TVxMg~XSSU~L1S1AqCGHiUMcu3cc-obuNYLkRudHw1wSVIOW-owKIjiGdtoiTJVy1xJEeE-JUylLqtuu5GcfjqfgOylK9WzIgFHAMIY~eidVuLSYc8T4GTOemHjuqHzFjzpvD2HA0j4oSlEkX55UZPrgawqyT3w~4uit6gltiKjKf~EfumbEGnLKv3gFYyyOBsRyrDGDHDWFycSbiyEWjDLwIOFptRyOsNa1EfKfch9pmNppTexKfQWEneppLwMNRNy3JkWE5aTzxKHq7-SCPLnBoXgB6qAS0P8l5fPzhO2pO05Z~kGv2jy1vPxtRxN6n2YDEiVA0ul7q2sTow6w__&Key-Pair-Id=K24J24Z295AEI9 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f801ad84c10>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
trace2333-duduk-llama2-v0-v2-mkmlizer: During handling of the above exception, another exception occurred:
trace2333-duduk-llama2-v0-v2-mkmlizer: Traceback (most recent call last):
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
trace2333-duduk-llama2-v0-v2-mkmlizer: cli()
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
trace2333-duduk-llama2-v0-v2-mkmlizer: return self.main(*args, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
trace2333-duduk-llama2-v0-v2-mkmlizer: rv = self.invoke(ctx)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
trace2333-duduk-llama2-v0-v2-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
trace2333-duduk-llama2-v0-v2-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
trace2333-duduk-llama2-v0-v2-mkmlizer: return __callback(*args, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
trace2333-duduk-llama2-v0-v2-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
trace2333-duduk-llama2-v0-v2-mkmlizer: snapshot_download(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
trace2333-duduk-llama2-v0-v2-mkmlizer: return fn(*args, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 292, in snapshot_download
trace2333-duduk-llama2-v0-v2-mkmlizer: _inner_hf_hub_download(file)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 268, in _inner_hf_hub_download
trace2333-duduk-llama2-v0-v2-mkmlizer: return hf_hub_download(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
trace2333-duduk-llama2-v0-v2-mkmlizer: return fn(*args, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1202, in hf_hub_download
trace2333-duduk-llama2-v0-v2-mkmlizer: return _hf_hub_download_to_local_dir(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1487, in _hf_hub_download_to_local_dir
trace2333-duduk-llama2-v0-v2-mkmlizer: _download_to_tmp_and_move(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1884, in _download_to_tmp_and_move
trace2333-duduk-llama2-v0-v2-mkmlizer: http_get(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 459, in http_get
trace2333-duduk-llama2-v0-v2-mkmlizer: r = _request_wrapper(
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 395, in _request_wrapper
trace2333-duduk-llama2-v0-v2-mkmlizer: response = get_session().request(method=method, url=url, **params)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
trace2333-duduk-llama2-v0-v2-mkmlizer: resp = self.send(prep, **send_kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
trace2333-duduk-llama2-v0-v2-mkmlizer: r = adapter.send(request, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 66, in send
trace2333-duduk-llama2-v0-v2-mkmlizer: return super().send(request, *args, **kwargs)
trace2333-duduk-llama2-v0-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 519, in send
trace2333-duduk-llama2-v0-v2-mkmlizer: raise ConnectionError(e, request=request)
trace2333-duduk-llama2-v0-v2-mkmlizer: requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/27/5f/9f1e5fe714d2d1baf781e/6cfc4aadea20c8fd1abb86638b2e3e3081bd9d7de670ae2ca57ca9354afec1cd?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00006.safetensors%3B+filename%3D%22model-00001-of-00006.safetensors%22%3B&Expires=1720242964&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcyMDI0Mjk2NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzI3LzVmLzI3NWY4NWU3NWI4YWE0YWIxOTRmOTUwZGNlZGJmNmZmY2ZiNzU4Zjk0ZGQ5ZjFlNWZlNzE0ZDJkMWJhZjc4MWUvNmNmYzRhYWRlYTIwYzhmZDFhYmI4NjYzOGIyZTNlMzA4MWJkOWQ3ZGU2NzBhZTJjYTU3Y2E5MzU0YWZlYzFjZD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=Y2TVxMg~XSSU~L1S1AqCGHiUMcu3cc-obuNYLkRudHw1wSVIOW-owKIjiGdtoiTJVy1xJEeE-JUylLqtuu5GcfjqfgOylK9WzIgFHAMIY~eidVuLSYc8T4GTOemHjuqHzFjzpvD2HA0j4oSlEkX55UZPrgawqyT3w~4uit6gltiKjKf~EfumbEGnLKv3gFYyyOBsRyrDGDHDWFycSbiyEWjDLwIOFptRyOsNa1EfKfch9pmNppTexKfQWEneppLwMNRNy3JkWE5aTzxKHq7-SCPLnBoXgB6qAS0P8l5fPzhO2pO05Z~kGv2jy1vPxtRxN6n2YDEiVA0ul7q2sTow6w__&Key-Pair-Id=K24J24Z295AEI9 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f801ad84c10>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"), '(Request ID: 1791ed1e-47f4-44e1-b381-98e01d89ceed)')
trace2333-duduk-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /___/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Version: 0.8.14 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Job trace2333-duduk-llama2-v0-v2-mkmlizer completed after 34.12s with status: failed
Stopping job with name trace2333-duduk-llama2-v0-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-duduk-llama2-v0-v2-mkmlizer
Waiting for job on trace2333-duduk-llama2-v0-v2-mkmlizer to finish
trace2333-duduk-llama2-v0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ /___/ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Version: 0.8.14 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ║ ║
trace2333-duduk-llama2-v0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama2-v0-v2-mkmlizer: Downloaded to shared memory in 36.450s
trace2333-duduk-llama2-v0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-duduk-llama2-v0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
trace2333-duduk-llama2-v0-v2-mkmlizer: quantized model in 15.824s
trace2333-duduk-llama2-v0-v2-mkmlizer: Processed model Trace2333/duduk_llama2_v0 in 52.275s
trace2333-duduk-llama2-v0-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama2-v0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2/config.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2/special_tokens_map.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2/tokenizer_config.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2/tokenizer.model
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama2-v0-v2/tokenizer.json
trace2333-duduk-llama2-v0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-duduk-llama2-v0-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 89.02it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:03, 86.52it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:03, 85.01it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:03, 84.10it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:02, 83.16it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:05, 41.04it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 53.31it/s] Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 58.09it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 64.15it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:02, 69.34it/s] Loading 0: 35%|███▍ | 101/291 [00:01<00:02, 73.40it/s] Loading 0: 38%|███▊ | 110/291 [00:01<00:03, 46.37it/s] Loading 0: 41%|████ | 118/291 [00:01<00:03, 51.94it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:02, 58.99it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:02, 65.44it/s] Loading 0: 50%|████▉ | 145/291 [00:02<00:02, 70.63it/s] Loading 0: 53%|█████▎ | 154/291 [00:02<00:01, 74.45it/s] Loading 0: 56%|█████▌ | 163/291 [00:02<00:02, 46.55it/s] Loading 0: 59%|█████▉ | 172/291 [00:02<00:02, 53.82it/s] Loading 0: 62%|██████▏ | 181/291 [00:02<00:01, 60.52it/s] Loading 0: 65%|██████▌ | 190/291 [00:03<00:01, 66.25it/s] Loading 0: 68%|██████▊ | 199/291 [00:03<00:01, 71.06it/s] Loading 0: 71%|███████▏ | 208/291 [00:03<00:01, 75.02it/s] Loading 0: 75%|███████▍ | 217/291 [00:03<00:01, 46.24it/s] Loading 0: 78%|███████▊ | 226/291 [00:03<00:01, 53.72it/s] Loading 0: 81%|████████ | 235/291 [00:03<00:00, 60.51it/s] Loading 0: 84%|████████▍ | 244/291 [00:03<00:00, 66.40it/s] Loading 0: 87%|████████▋ | 253/291 [00:04<00:00, 70.91it/s] Loading 0: 90%|█████████ | 262/291 [00:04<00:00, 74.98it/s] Loading 0: 93%|█████████▎| 271/291 [00:05<00:01, 14.86it/s] Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 20.41it/s] Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 26.33it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama2-v0-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama2-v0-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
trace2333-duduk-llama2-v0-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama2-v0-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama2-v0-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama2-v0-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.
trace2333-duduk-llama2-v0-v2-mkmlizer: warnings.warn(
trace2333-duduk-llama2-v0-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()
trace2333-duduk-llama2-v0-v2-mkmlizer: return self.fget.__get__(instance, owner)()
trace2333-duduk-llama2-v0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama2-v0-v2-mkmlizer: Saving duration: 0.559s
trace2333-duduk-llama2-v0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.336s
trace2333-duduk-llama2-v0-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama2-v0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama2-v0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/config.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/special_tokens_map.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/tokenizer_config.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/merges.txt
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/vocab.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/tokenizer.json
trace2333-duduk-llama2-v0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama2-v0-v2_reward/reward.tensors
Job trace2333-duduk-llama2-v0-v2-mkmlizer completed after 84.91s with status: succeeded
Stopping job with name trace2333-duduk-llama2-v0-v2-mkmlizer
Pipeline stage MKMLizer completed in 120.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama2-v0-v2
Waiting for inference service trace2333-duduk-llama2-v0-v2 to be ready
Inference service trace2333-duduk-llama2-v0-v2 ready after 40.18633222579956s
Pipeline stage ISVCDeployer completed in 47.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4603917598724365s
Received healthy response to inference request in 1.0117473602294922s
Received healthy response to inference request in 0.6052331924438477s
Received healthy response to inference request in 0.6515634059906006s
Received healthy response to inference request in 0.9247260093688965s
5 requests
0 failed requests
5th percentile: 0.6144992351531983
10th percentile: 0.6237652778625489
20th percentile: 0.64229736328125
30th percentile: 0.7061959266662597
40th percentile: 0.8154609680175782
50th percentile: 0.9247260093688965
60th percentile: 0.9595345497131348
70th percentile: 0.994343090057373
80th percentile: 1.101476240158081
90th percentile: 1.280934000015259
95th percentile: 1.3706628799438476
99th percentile: 1.4424459838867187
mean time: 0.9307323455810547
Pipeline stage StressChecker completed in 5.77s
trace2333-duduk-llama2-v0_v2 status is now deployed due to DeploymentManager action
trace2333-duduk-llama2-v0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama2-v0_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama2-v0-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama2-v0-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama2-v0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama2-v0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama2-v0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.49s
trace2333-duduk-llama2-v0_v2 status is now torndown due to DeploymentManager action