chaiml-ca18-v2-1-dpo-lr_51001

developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v2-1-dpo-lr_51001_v1
model_name: training123
model_group: ChaiML/ca18-v2-1-dpo_lr1
status: torndown
timestamp: 2025-11-19T22:36:16+00:00
num_battles: 5320
num_wins: 2844
celo_rating: 1304.29
family_friendly_score: 0.5164
family_friendly_standard_error: 0.007067263119482675
submission_type: basic
model_repo: ChaiML/ca18-v2-1-dpo_lr15-b025
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6870123518930878, 'latency_mean': 1.4554560005664825, 'latency_p50': 1.4555014371871948, 'latency_p90': 1.6008892059326172}, {'batch_size': 3, 'throughput': 1.264198830210145, 'latency_mean': 2.3639317417144774, 'latency_p50': 2.3701947927474976, 'latency_p90': 2.6047439575195312}, {'batch_size': 5, 'throughput': 1.5417834391535274, 'latency_mean': 3.2242222249507906, 'latency_p50': 3.220232605934143, 'latency_p90': 3.6463780164718624}, {'batch_size': 6, 'throughput': 1.6197810502454053, 'latency_mean': 3.683007798194885, 'latency_p50': 3.680646300315857, 'latency_p90': 4.174464631080627}, {'batch_size': 8, 'throughput': 1.7450179774893977, 'latency_mean': 4.566554490327835, 'latency_p50': 4.5680763721466064, 'latency_p90': 5.2070074558258055}, {'batch_size': 10, 'throughput': 1.801780609288481, 'latency_mean': 5.513124693632125, 'latency_p50': 5.569371700286865, 'latency_p90': 6.151676750183105}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v2-1-dpo_lr15-b025
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2025-11-16
win_ratio: 0.5345864661654135
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'User:', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, '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': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer to finish
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Traceback (most recent call last):
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 536, in _make_request
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response = conn.getresponse()
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 461, in getresponse
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     httplib_response = super().getresponse()
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 1375, in getresponse
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response.begin()
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 318, in begin
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     version, status, reason = self._read_status()
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 279, in _read_status
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/socket.py", line 705, in readinto
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return self._sock.recv_into(b)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/ssl.py", line 1307, in recv_into
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return self.read(nbytes, buffer)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/ssl.py", line 1163, in read
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return self._sslobj.read(len, buffer)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: TimeoutError: The read operation timed out
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: The above exception was the direct cause of the following exception:
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Traceback (most recent call last):
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     resp = conn.urlopen(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 844, in urlopen
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     retries = retries.increment(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 470, in increment
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     raise reraise(type(error), error, _stacktrace)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/util/util.py", line 39, in reraise
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     raise value
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 790, in urlopen
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response = self._make_request(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 538, in _make_request
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 370, in _raise_timeout
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     raise ReadTimeoutError(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: During handling of the above exception, another exception occurred:
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Traceback (most recent call last):
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1546, in _get_metadata_or_catch_error
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     metadata = get_hf_file_metadata(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return fn(*args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1463, in get_hf_file_metadata
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     r = _request_wrapper(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response = _request_wrapper(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,))
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     response = session.request(method=method, url=url, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     resp = self.send(prep, **send_kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     r = adapter.send(request, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 96, in send
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return super().send(request, *args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 713, in send
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     raise ReadTimeout(e, request=request)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: requests.exceptions.ReadTimeout: (ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: 114b3d6e-9814-41f1-9b42-f3b0e84069a9)')
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: The above exception was the direct cause of the following exception:
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Traceback (most recent call last):
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/code/uploading/mkmlize.py", line 225, in <module>
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     cli()
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return self.main(*args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     rv = self.invoke(ctx)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return _process_result(sub_ctx.command.invoke(sub_ctx))
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return ctx.invoke(self.callback, **ctx.params)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return __callback(*args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/code/uploading/mkmlize.py", line 41, in quantize
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/code/uploading/mkmlize.py", line 91, in download_to_shared_memory
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     snapshot_download(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return fn(*args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 330, in snapshot_download
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     _inner_hf_hub_download(file)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 306, in _inner_hf_hub_download
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return hf_hub_download(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return fn(*args, **kwargs)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 990, in hf_hub_download
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     return _hf_hub_download_to_local_dir(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1253, in _hf_hub_download_to_local_dir
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     _raise_on_head_call_error(head_call_error, force_download, local_files_only)
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1661, in _raise_on_head_call_error
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer:     raise LocalEntryNotFoundError(
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: huggingface_hub.errors.LocalEntryNotFoundError: An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.
Job chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer completed after 47.84s with status: failed
Stopping job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer to finish
Stopping job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer to finish
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Downloaded to shared memory in 38.497s
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Checking if ChaiML/ca18-v2-1-dpo_lr15-b025 already exists in ChaiML
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi914aedj, device:0
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: quantized model in 25.916s
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Processed model ChaiML/ca18-v2-1-dpo_lr15-b025 in 64.414s
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia/config.json
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia/tokenizer.json
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-lr-51001-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.92it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 52.35it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 54.46it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 55.84it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.84it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 62.31it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 47.49it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 45.42it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 52.63it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 51.28it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 52.49it/s]
Loading 0:  28%|██▊       | 100/363 [00:01<00:05, 49.54it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 56.44it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 56.28it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 56.55it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:04, 50.76it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 53.83it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 51.85it/s]
Loading 0:  40%|████      | 147/363 [00:02<00:05, 39.46it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 41.39it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 40.12it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 48.71it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 48.46it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 50.63it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 48.56it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 56.09it/s]
Loading 0:  55%|█████▍    | 199/363 [00:03<00:03, 53.26it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 53.88it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 55.49it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 52.51it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 42.28it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.20it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 46.20it/s]
Loading 0:  66%|██████▌   | 239/363 [00:04<00:02, 41.56it/s]
Loading 0:  68%|██████▊   | 247/363 [00:04<00:02, 50.51it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 49.19it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 51.09it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:01, 48.97it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 56.31it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 53.04it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.43it/s]
Loading 0:  80%|████████  | 292/363 [00:05<00:01, 54.89it/s]
Loading 0:  82%|████████▏ | 298/363 [00:05<00:01, 48.80it/s]
Loading 0:  84%|████████▎ | 304/363 [00:06<00:01, 30.09it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.43it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.87it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.78it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 42.58it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.44it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 48.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 50.74it/s]
                                                            
Job chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer completed after 114.9s with status: succeeded
Stopping job with name chaiml-ca18-v2-1-dpo-lr-51001-v1-mkmlizer
Pipeline stage MKMLizer completed in 174.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v2-1-dpo-lr-51001-v1
Waiting for inference service chaiml-ca18-v2-1-dpo-lr-51001-v1 to be ready
Inference service chaiml-ca18-v2-1-dpo-lr-51001-v1 ready after 332.2383840084076s
Pipeline stage MKMLDeployer completed in 332.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6728522777557373s
Received healthy response to inference request in 1.3391706943511963s
Received healthy response to inference request in 1.7757456302642822s
Received healthy response to inference request in 1.6742725372314453s
Received healthy response to inference request in 1.534090280532837s
5 requests
0 failed requests
5th percentile: 1.3781546115875245
10th percentile: 1.4171385288238525
20th percentile: 1.4951063632965087
30th percentile: 1.561842679977417
40th percentile: 1.6173474788665771
50th percentile: 1.6728522777557373
60th percentile: 1.6734203815460205
70th percentile: 1.6739884853363036
80th percentile: 1.6945671558380127
90th percentile: 1.7351563930511475
95th percentile: 1.7554510116577149
99th percentile: 1.7716867065429687
mean time: 1.5992262840270997
Pipeline stage StressChecker completed in 9.95s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.75s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.68s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo-lr_51001_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2539.96s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo-lr_51001_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-1-dpo-lr_51001_v1 status is now torndown due to DeploymentManager action