developer_uid: rirv938
submission_id: rirv938-grpo-20250711-c_20147_v1
model_name: rirv938-grpo-20250711-c_20147_v1
model_group: rirv938/grpo_20250711_cp
status: torndown
timestamp: 2025-07-11T23:36:39+00:00
num_battles: 9484
num_wins: 4039
celo_rating: 1233.39
family_friendly_score: 0.4898
family_friendly_standard_error: 0.007069596310964298
submission_type: basic
model_repo: rirv938/grpo_20250711_cp624_sid_mistral_24b_dpo_40k__merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 102
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.618841547256487, 'latency_mean': 1.6158201587200165, 'latency_p50': 1.6297425031661987, 'latency_p90': 1.8181989192962646}, {'batch_size': 5, 'throughput': 2.0510258640359367, 'latency_mean': 2.4162495839595795, 'latency_p50': 2.414845108985901, 'latency_p90': 2.7131263256072997}, {'batch_size': 10, 'throughput': 2.965282438729432, 'latency_mean': 3.3268670058250427, 'latency_p50': 3.3279848098754883, 'latency_p90': 3.7251304626464843}, {'batch_size': 15, 'throughput': 3.3175113852432236, 'latency_mean': 4.433933091163635, 'latency_p50': 4.473875284194946, 'latency_p90': 5.002084994316101}, {'batch_size': 20, 'throughput': 3.5031388551069433, 'latency_mean': 5.56158280968666, 'latency_p50': 5.4859418869018555, 'latency_p90': 6.785385775566101}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-grpo-20250711-c_20147_v1
is_internal_developer: True
language_model: rirv938/grpo_20250711_cp624_sid_mistral_24b_dpo_40k__merged
model_size: 24B
ranking_group: single
throughput_3p7s: 3.16
us_pacific_date: 2025-07-11
win_ratio: 0.42587515816111343
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 102, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{bot_name}:', 'truncate_by_message': False}
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 rirv938-grpo-20250711-c-20147-v1-mkmlizer
Waiting for job on rirv938-grpo-20250711-c-20147-v1-mkmlizer to finish
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Version: 0.29.15 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ belonging to: ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Traceback (most recent call last):
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 536, in _make_request
rirv938-grpo-20250711-c-20147-v1-mkmlizer: response = conn.getresponse()
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 461, in getresponse
rirv938-grpo-20250711-c-20147-v1-mkmlizer: httplib_response = super().getresponse()
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 1375, in getresponse
rirv938-grpo-20250711-c-20147-v1-mkmlizer: response.begin()
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 318, in begin
rirv938-grpo-20250711-c-20147-v1-mkmlizer: version, status, reason = self._read_status()
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 279, in _read_status
rirv938-grpo-20250711-c-20147-v1-mkmlizer: line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 705, in readinto
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return self._sock.recv_into(b)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1307, in recv_into
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return self.read(nbytes, buffer)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1163, in read
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return self._sslobj.read(len, buffer)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: TimeoutError: The read operation timed out
rirv938-grpo-20250711-c-20147-v1-mkmlizer: The above exception was the direct cause of the following exception:
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Traceback (most recent call last):
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
rirv938-grpo-20250711-c-20147-v1-mkmlizer: resp = conn.urlopen(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 844, in urlopen
rirv938-grpo-20250711-c-20147-v1-mkmlizer: retries = retries.increment(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 470, in increment
rirv938-grpo-20250711-c-20147-v1-mkmlizer: raise reraise(type(error), error, _stacktrace)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/util.py", line 39, in reraise
rirv938-grpo-20250711-c-20147-v1-mkmlizer: raise value
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 790, in urlopen
rirv938-grpo-20250711-c-20147-v1-mkmlizer: response = self._make_request(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 538, in _make_request
rirv938-grpo-20250711-c-20147-v1-mkmlizer: self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 370, in _raise_timeout
rirv938-grpo-20250711-c-20147-v1-mkmlizer: raise ReadTimeoutError(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: During handling of the above exception, another exception occurred:
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Traceback (most recent call last):
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1484, in _get_metadata_or_catch_error
rirv938-grpo-20250711-c-20147-v1-mkmlizer: metadata = get_hf_file_metadata(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return fn(*args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1401, in get_hf_file_metadata
rirv938-grpo-20250711-c-20147-v1-mkmlizer: r = _request_wrapper(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 285, in _request_wrapper
rirv938-grpo-20250711-c-20147-v1-mkmlizer: response = _request_wrapper(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 308, in _request_wrapper
rirv938-grpo-20250711-c-20147-v1-mkmlizer: response = get_session().request(method=method, url=url, **params)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
rirv938-grpo-20250711-c-20147-v1-mkmlizer: resp = self.send(prep, **send_kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
rirv938-grpo-20250711-c-20147-v1-mkmlizer: r = adapter.send(request, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 96, in send
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return super().send(request, *args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 713, in send
rirv938-grpo-20250711-c-20147-v1-mkmlizer: raise ReadTimeout(e, request=request)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: requests.exceptions.ReadTimeout: (ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: 7255e950-1d8a-41cb-8f07-69ad59940e1e)')
rirv938-grpo-20250711-c-20147-v1-mkmlizer: The above exception was the direct cause of the following exception:
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Traceback (most recent call last):
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 225, in <module>
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cli()
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return self.main(*args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
rirv938-grpo-20250711-c-20147-v1-mkmlizer: rv = self.invoke(ctx)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return __callback(*args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 41, in quantize
rirv938-grpo-20250711-c-20147-v1-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/code/uploading/mkmlize.py", line 91, in download_to_shared_memory
rirv938-grpo-20250711-c-20147-v1-mkmlizer: snapshot_download(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return fn(*args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 294, in snapshot_download
rirv938-grpo-20250711-c-20147-v1-mkmlizer: _inner_hf_hub_download(file)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 270, in _inner_hf_hub_download
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return hf_hub_download(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return fn(*args, **kwargs)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 941, in hf_hub_download
rirv938-grpo-20250711-c-20147-v1-mkmlizer: return _hf_hub_download_to_local_dir(
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1194, in _hf_hub_download_to_local_dir
rirv938-grpo-20250711-c-20147-v1-mkmlizer: _raise_on_head_call_error(head_call_error, force_download, local_files_only)
rirv938-grpo-20250711-c-20147-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1599, in _raise_on_head_call_error
rirv938-grpo-20250711-c-20147-v1-mkmlizer: raise LocalEntryNotFoundError(
rirv938-grpo-20250711-c-20147-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.
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Version: 0.29.15 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ belonging to: ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Job rirv938-grpo-20250711-c-20147-v1-mkmlizer completed after 120.76s with status: failed
Stopping job with name rirv938-grpo-20250711-c-20147-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name rirv938-grpo-20250711-c-20147-v1-mkmlizer
Waiting for job on rirv938-grpo-20250711-c-20147-v1-mkmlizer to finish
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Version: 0.29.15 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ belonging to: ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ║ ║
rirv938-grpo-20250711-c-20147-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Downloaded to shared memory in 167.899s
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Checking if rirv938/grpo_20250711_cp624_sid_mistral_24b_dpo_40k__merged already exists in ChaiML
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Creating repo ChaiML/grpo_20250711_cp624_sid_mistral_24b_dpo_40k__merged and uploading /tmp/tmp26cka8vz to it
rirv938-grpo-20250711-c-20147-v1-mkmlizer: 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:06<02:12, 6.30s/it] 9%|▉ | 2/22 [00:13<02:18, 6.93s/it] 14%|█▎ | 3/22 [00:21<02:15, 7.15s/it] 18%|█▊ | 4/22 [00:25<01:50, 6.11s/it] 23%|██▎ | 5/22 [00:31<01:44, 6.12s/it] 27%|██▋ | 6/22 [00:36<01:29, 5.59s/it] 32%|███▏ | 7/22 [00:45<01:41, 6.76s/it] 36%|███▋ | 8/22 [00:52<01:36, 6.87s/it] 41%|████ | 9/22 [01:02<01:39, 7.68s/it] 45%|████▌ | 10/22 [01:07<01:22, 6.86s/it] 50%|█████ | 11/22 [01:14<01:17, 7.03s/it] 55%|█████▍ | 12/22 [01:23<01:16, 7.69s/it] 59%|█████▉ | 13/22 [01:28<01:01, 6.78s/it] 64%|██████▎ | 14/22 [01:32<00:48, 6.07s/it] 68%|██████▊ | 15/22 [01:38<00:40, 5.81s/it] 73%|███████▎ | 16/22 [01:45<00:37, 6.25s/it] 77%|███████▋ | 17/22 [01:49<00:28, 5.69s/it] 82%|████████▏ | 18/22 [01:54<00:22, 5.55s/it] 86%|████████▋ | 19/22 [01:59<00:15, 5.26s/it] 91%|█████████ | 20/22 [02:03<00:10, 5.03s/it] 95%|█████████▌| 21/22 [02:08<00:05, 5.00s/it] 100%|██████████| 22/22 [02:10<00:00, 3.87s/it] 100%|██████████| 22/22 [02:10<00:00, 5.92s/it]
rirv938-grpo-20250711-c-20147-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp26cka8vz, device:0
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-20250711-c-20147-v1-mkmlizer: quantized model in 72.754s
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Processed model rirv938/grpo_20250711_cp624_sid_mistral_24b_dpo_40k__merged in 490.300s
rirv938-grpo-20250711-c-20147-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-20250711-c-20147-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/config.json
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/special_tokens_map.json
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/tokenizer_config.json
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/tokenizer.json
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/flywheel_model.1.safetensors
rirv938-grpo-20250711-c-20147-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-20250711-c-20147-v1/nvidia/flywheel_model.0.safetensors
rirv938-grpo-20250711-c-20147-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:15, 23.10it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:31, 11.38it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:20, 17.16it/s] Loading 0: 4%|▎ | 13/363 [00:01<00:29, 11.76it/s] Loading 0: 4%|▍ | 15/363 [00:01<00:36, 9.65it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:24, 14.05it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:25, 13.26it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:27, 12.22it/s] Loading 0: 8%|▊ | 28/363 [00:02<00:20, 16.05it/s] Loading 0: 9%|▉ | 32/363 [00:02<00:17, 19.21it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:25, 12.87it/s] Loading 0: 10%|█ | 37/363 [00:02<00:27, 11.99it/s] Loading 0: 11%|█ | 39/363 [00:02<00:25, 12.63it/s] Loading 0: 11%|█▏ | 41/363 [00:03<00:32, 9.97it/s] Loading 0: 13%|█▎ | 46/363 [00:03<00:21, 14.89it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:17, 17.59it/s] Loading 0: 15%|█▍ | 53/363 [00:04<00:25, 12.04it/s] Loading 0: 15%|█▌ | 55/363 [00:04<00:27, 11.35it/s] Loading 0: 16%|█▌ | 57/363 [00:04<00:25, 12.04it/s] Loading 0: 16%|█▋ | 59/363 [00:04<00:32, 9.22it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:21, 14.16it/s] Loading 0: 19%|█▊ | 68/363 [00:05<00:17, 17.00it/s] Loading 0: 20%|█▉ | 71/363 [00:05<00:26, 11.14it/s] Loading 0: 20%|██ | 73/363 [00:05<00:27, 10.69it/s] Loading 0: 21%|██ | 75/363 [00:05<00:25, 11.41it/s] Loading 0: 21%|██ | 77/363 [00:06<00:31, 9.09it/s] Loading 0: 23%|██▎ | 82/363 [00:06<00:20, 13.98it/s] Loading 0: 24%|██▎ | 86/363 [00:06<00:16, 17.05it/s] Loading 0: 25%|██▍ | 89/363 [00:07<00:23, 11.44it/s] Loading 0: 25%|██▌ | 91/363 [00:07<00:24, 10.95it/s] Loading 0: 26%|██▌ | 95/363 [00:07<00:18, 14.32it/s] Loading 0: 27%|██▋ | 99/363 [00:07<00:15, 17.13it/s] Loading 0: 28%|██▊ | 102/363 [00:07<00:16, 15.59it/s] Loading 0: 29%|██▊ | 104/363 [00:07<00:18, 14.10it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:23, 10.77it/s] Loading 0: 30%|██▉ | 108/363 [00:08<00:27, 9.15it/s] Loading 0: 31%|███ | 111/363 [00:08<00:22, 11.43it/s] Loading 0: 31%|███ | 113/363 [00:09<00:26, 9.48it/s] Loading 0: 33%|███▎ | 118/363 [00:09<00:17, 14.18it/s] Loading 0: 34%|███▎ | 122/363 [00:09<00:14, 17.21it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:19, 12.09it/s] Loading 0: 35%|███▍ | 127/363 [00:10<00:20, 11.50it/s] Loading 0: 36%|███▌ | 129/363 [00:10<00:19, 12.02it/s] Loading 0: 36%|███▌ | 131/363 [00:10<00:23, 9.90it/s] Loading 0: 37%|███▋ | 136/363 [00:10<00:15, 14.84it/s] Loading 0: 39%|███▊ | 140/363 [00:10<00:12, 17.85it/s] Loading 0: 39%|███▉ | 143/363 [00:11<00:17, 12.40it/s] Loading 0: 40%|███▉ | 145/363 [00:11<00:18, 11.83it/s] Loading 0: 40%|████ | 147/363 [00:11<00:17, 12.61it/s] Loading 0: 41%|████ | 149/363 [00:11<00:20, 10.38it/s] Loading 0: 42%|████▏ | 154/363 [00:11<00:13, 15.67it/s] Loading 0: 44%|████▎ | 158/363 [00:12<00:11, 18.60it/s] Loading 0: 44%|████▍ | 161/363 [00:12<00:15, 12.75it/s] Loading 0: 45%|████▍ | 163/363 [00:12<00:16, 12.06it/s] Loading 0: 45%|████▌ | 165/363 [00:12<00:15, 12.50it/s] Loading 0: 46%|████▌ | 167/363 [00:13<00:19, 10.00it/s] Loading 0: 47%|████▋ | 172/363 [00:13<00:12, 15.23it/s] Loading 0: 48%|████▊ | 176/363 [00:13<00:10, 18.17it/s] Loading 0: 49%|████▉ | 179/363 [00:13<00:14, 12.42it/s] Loading 0: 50%|████▉ | 181/363 [00:14<00:15, 11.73it/s] Loading 0: 50%|█████ | 183/363 [00:14<00:14, 12.33it/s] Loading 0: 51%|█████ | 185/363 [00:14<00:18, 9.66it/s] Loading 0: 52%|█████▏ | 190/363 [00:14<00:11, 14.60it/s] Loading 0: 53%|█████▎ | 194/363 [00:14<00:09, 17.60it/s] Loading 0: 54%|█████▍ | 197/363 [00:15<00:13, 12.05it/s] Loading 0: 55%|█████▍ | 199/363 [00:15<00:14, 11.51it/s] Loading 0: 55%|█████▌ | 200/363 [00:34<00:14, 11.51it/s] Loading 0: 55%|█████▌ | 201/363 [00:34<05:52, 2.17s/it] Loading 0: 56%|█████▌ | 202/363 [00:34<05:03, 1.89s/it] Loading 0: 56%|█████▌ | 204/363 [00:34<03:39, 1.38s/it] Loading 0: 57%|█████▋ | 207/363 [00:34<02:16, 1.15it/s] Loading 0: 58%|█████▊ | 209/363 [00:34<01:41, 1.52it/s] Loading 0: 58%|█████▊ | 212/363 [00:34<01:06, 2.27it/s] Loading 0: 59%|█████▉ | 214/363 [00:35<00:54, 2.71it/s] Loading 0: 60%|█████▉ | 216/363 [00:35<00:45, 3.20it/s] Loading 0: 60%|██████ | 219/363 [00:35<00:31, 4.62it/s] Loading 0: 61%|██████ | 221/363 [00:35<00:28, 4.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:36<00:16, 8.56it/s] Loading 0: 63%|██████▎ | 230/363 [00:36<00:11, 11.46it/s] Loading 0: 64%|██████▍ | 233/363 [00:36<00:13, 9.79it/s] Loading 0: 65%|██████▍ | 235/363 [00:36<00:13, 9.82it/s] Loading 0: 65%|██████▌ | 237/363 [00:36<00:11, 10.73it/s] Loading 0: 66%|██████▌ | 239/363 [00:37<00:13, 9.14it/s] Loading 0: 67%|██████▋ | 244/363 [00:37<00:08, 14.10it/s] Loading 0: 68%|██████▊ | 248/363 [00:37<00:06, 17.20it/s] Loading 0: 69%|██████▉ | 251/363 [00:37<00:09, 12.17it/s] Loading 0: 70%|██████▉ | 253/363 [00:38<00:09, 11.41it/s] Loading 0: 70%|███████ | 255/363 [00:38<00:08, 12.26it/s] Loading 0: 71%|███████ | 257/363 [00:38<00:10, 10.00it/s] Loading 0: 72%|███████▏ | 262/363 [00:38<00:06, 15.17it/s] Loading 0: 73%|███████▎ | 266/363 [00:38<00:05, 18.09it/s] Loading 0: 74%|███████▍ | 269/363 [00:39<00:07, 12.75it/s] Loading 0: 75%|███████▍ | 271/363 [00:39<00:07, 12.07it/s] Loading 0: 75%|███████▌ | 273/363 [00:39<00:07, 12.76it/s] Loading 0: 76%|███████▌ | 275/363 [00:39<00:08, 10.35it/s] Loading 0: 77%|███████▋ | 280/363 [00:40<00:05, 15.64it/s] Loading 0: 78%|███████▊ | 284/363 [00:40<00:04, 18.76it/s] Loading 0: 79%|███████▉ | 287/363 [00:40<00:05, 13.18it/s] Loading 0: 80%|███████▉ | 289/363 [00:40<00:05, 12.58it/s] Loading 0: 80%|████████ | 291/363 [00:40<00:05, 13.20it/s] Loading 0: 81%|████████ | 293/363 [00:41<00:06, 10.67it/s] Loading 0: 82%|████████▏ | 298/363 [00:41<00:04, 15.97it/s] Loading 0: 83%|████████▎ | 302/363 [00:41<00:03, 18.89it/s] Loading 0: 84%|████████▍ | 305/363 [00:41<00:04, 13.02it/s] Loading 0: 85%|████████▍ | 307/363 [00:42<00:04, 12.05it/s] Loading 0: 85%|████████▌ | 309/363 [00:42<00:04, 12.76it/s] Loading 0: 86%|████████▌ | 311/363 [00:42<00:05, 9.80it/s] Loading 0: 87%|████████▋ | 316/363 [00:42<00:03, 14.95it/s] Loading 0: 88%|████████▊ | 320/363 [00:42<00:02, 18.30it/s] Loading 0: 89%|████████▉ | 323/363 [00:43<00:03, 12.72it/s] Loading 0: 90%|████████▉ | 325/363 [00:43<00:03, 11.89it/s] Loading 0: 90%|█████████ | 327/363 [00:43<00:02, 12.52it/s] Loading 0: 91%|█████████ | 329/363 [00:43<00:03, 10.19it/s] Loading 0: 92%|█████████▏| 334/363 [00:44<00:01, 15.48it/s] Loading 0: 93%|█████████▎| 338/363 [00:44<00:01, 18.89it/s] Loading 0: 94%|█████████▍| 341/363 [00:44<00:01, 13.19it/s] Loading 0: 94%|█████████▍| 343/363 [00:44<00:01, 12.46it/s] Loading 0: 95%|█████████▌| 345/363 [00:44<00:01, 12.95it/s] Loading 0: 96%|█████████▌| 347/363 [00:45<00:01, 10.07it/s] Loading 0: 97%|█████████▋| 352/363 [00:45<00:00, 15.38it/s] Loading 0: 98%|█████████▊| 356/363 [00:45<00:00, 18.66it/s] Loading 0: 99%|█████████▉| 359/363 [00:46<00:00, 9.37it/s] Loading 0: 99%|█████████▉| 361/363 [00:46<00:00, 8.50it/s]
Job rirv938-grpo-20250711-c-20147-v1-mkmlizer completed after 527.52s with status: succeeded
Stopping job with name rirv938-grpo-20250711-c-20147-v1-mkmlizer
Pipeline stage MKMLizer completed in 649.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-20250711-c-20147-v1
Waiting for inference service rirv938-grpo-20250711-c-20147-v1 to be ready
Inference service rirv938-grpo-20250711-c-20147-v1 ready after 271.0951554775238s
Pipeline stage MKMLDeployer completed in 271.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6021523475646973s
Received healthy response to inference request in 2.079559087753296s
Received healthy response to inference request in 2.1147654056549072s
Received healthy response to inference request in 1.8744380474090576s
Received healthy response to inference request in 1.8381328582763672s
5 requests
0 failed requests
5th percentile: 1.8453938961029053
10th percentile: 1.8526549339294434
20th percentile: 1.8671770095825195
30th percentile: 1.9154622554779053
40th percentile: 1.9975106716156006
50th percentile: 2.079559087753296
60th percentile: 2.0936416149139405
70th percentile: 2.107724142074585
80th percentile: 2.2122427940368654
90th percentile: 2.4071975708007813
95th percentile: 2.504674959182739
99th percentile: 2.5826568698883055
mean time: 2.101809549331665
Pipeline stage StressChecker completed in 12.02s
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 0.74s
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 0.72s
Shutdown handler de-registered
rirv938-grpo-20250711-c_20147_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-grpo-20250711-c-20147-v1-profiler
Waiting for inference service rirv938-grpo-20250711-c-20147-v1-profiler to be ready
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 2930.55s
Shutdown handler de-registered
rirv938-grpo-20250711-c_20147_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-20250711-c_20147_v1 status is now torndown due to DeploymentManager action