developer_uid: NischayDnk
submission_id: intervitensinc-gemma-2-_70884_v2
model_name: intervitensinc-gemma-2-_70884_v2
model_group: IntervitensInc/gemma-2-2
status: torndown
timestamp: 2025-03-30T08:18:11+00:00
num_battles: 10747
num_wins: 4708
celo_rating: 1236.83
family_friendly_score: 0.6046
family_friendly_standard_error: 0.006914605411735365
submission_type: basic
model_repo: IntervitensInc/gemma-2-27b-chatml
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2778581162416476, 'latency_mean': 3.598866649866104, 'latency_p50': 3.565669536590576, 'latency_p90': 4.038410067558289}, {'batch_size': 2, 'throughput': 0.4198753021795036, 'latency_mean': 4.754925827980042, 'latency_p50': 4.747826814651489, 'latency_p90': 5.216635823249817}, {'batch_size': 3, 'throughput': 0.5372013277760336, 'latency_mean': 5.5720581889152525, 'latency_p50': 5.570709586143494, 'latency_p90': 6.2255446195602415}, {'batch_size': 5, 'throughput': 0.6775580307493045, 'latency_mean': 7.328157955408097, 'latency_p50': 7.33204197883606, 'latency_p90': 8.183861660957337}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: intervitensinc-gemma-2-_70884_v2
is_internal_developer: False
language_model: IntervitensInc/gemma-2-27b-chatml
model_size: 29B
ranking_group: single
throughput_3p7s: 0.29
us_pacific_date: 2025-03-30
win_ratio: 0.43807574206755373
generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 intervitensinc-gemma-2-70884-v2-mkmlizer
Waiting for job on intervitensinc-gemma-2-70884-v2-mkmlizer to finish
intervitensinc-gemma-2-70884-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ _____ __ __ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ /___/ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Version: 0.12.8 ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ https://mk1.ai ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ The license key for the current software has been verified as ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ belonging to: ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Chai Research Corp. ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission intervitensinc-gemma-2-_70884_v1: HTTPConnectionPool(host='intervitensinc-gemma-2-70884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
intervitensinc-gemma-2-70884-v2-mkmlizer: Traceback (most recent call last):
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 536, in _make_request
intervitensinc-gemma-2-70884-v2-mkmlizer: response = conn.getresponse()
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 461, in getresponse
intervitensinc-gemma-2-70884-v2-mkmlizer: httplib_response = super().getresponse()
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 1375, in getresponse
intervitensinc-gemma-2-70884-v2-mkmlizer: response.begin()
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 318, in begin
intervitensinc-gemma-2-70884-v2-mkmlizer: version, status, reason = self._read_status()
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/http/client.py", line 279, in _read_status
intervitensinc-gemma-2-70884-v2-mkmlizer: line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 705, in readinto
intervitensinc-gemma-2-70884-v2-mkmlizer: return self._sock.recv_into(b)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1307, in recv_into
intervitensinc-gemma-2-70884-v2-mkmlizer: return self.read(nbytes, buffer)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/ssl.py", line 1163, in read
intervitensinc-gemma-2-70884-v2-mkmlizer: return self._sslobj.read(len, buffer)
intervitensinc-gemma-2-70884-v2-mkmlizer: TimeoutError: The read operation timed out
intervitensinc-gemma-2-70884-v2-mkmlizer: The above exception was the direct cause of the following exception:
intervitensinc-gemma-2-70884-v2-mkmlizer: Traceback (most recent call last):
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
intervitensinc-gemma-2-70884-v2-mkmlizer: resp = conn.urlopen(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 844, in urlopen
intervitensinc-gemma-2-70884-v2-mkmlizer: retries = retries.increment(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 470, in increment
intervitensinc-gemma-2-70884-v2-mkmlizer: raise reraise(type(error), error, _stacktrace)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/util.py", line 39, in reraise
intervitensinc-gemma-2-70884-v2-mkmlizer: raise value
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 790, in urlopen
intervitensinc-gemma-2-70884-v2-mkmlizer: response = self._make_request(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 538, in _make_request
intervitensinc-gemma-2-70884-v2-mkmlizer: self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 370, in _raise_timeout
intervitensinc-gemma-2-70884-v2-mkmlizer: raise ReadTimeoutError(
intervitensinc-gemma-2-70884-v2-mkmlizer: urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)
intervitensinc-gemma-2-70884-v2-mkmlizer: During handling of the above exception, another exception occurred:
intervitensinc-gemma-2-70884-v2-mkmlizer: Traceback (most recent call last):
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error
intervitensinc-gemma-2-70884-v2-mkmlizer: metadata = get_hf_file_metadata(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
intervitensinc-gemma-2-70884-v2-mkmlizer: return fn(*args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata
intervitensinc-gemma-2-70884-v2-mkmlizer: r = _request_wrapper(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper
intervitensinc-gemma-2-70884-v2-mkmlizer: response = _request_wrapper(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 301, in _request_wrapper
intervitensinc-gemma-2-70884-v2-mkmlizer: response = get_session().request(method=method, url=url, **params)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
intervitensinc-gemma-2-70884-v2-mkmlizer: resp = self.send(prep, **send_kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
intervitensinc-gemma-2-70884-v2-mkmlizer: r = adapter.send(request, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 93, in send
intervitensinc-gemma-2-70884-v2-mkmlizer: return super().send(request, *args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 713, in send
intervitensinc-gemma-2-70884-v2-mkmlizer: raise ReadTimeout(e, request=request)
intervitensinc-gemma-2-70884-v2-mkmlizer: requests.exceptions.ReadTimeout: (ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: 98ff7822-69e1-49b4-b3b1-7c8458485862)')
intervitensinc-gemma-2-70884-v2-mkmlizer: The above exception was the direct cause of the following exception:
intervitensinc-gemma-2-70884-v2-mkmlizer: Traceback (most recent call last):
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 193, in <module>
intervitensinc-gemma-2-70884-v2-mkmlizer: cli()
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
intervitensinc-gemma-2-70884-v2-mkmlizer: return self.main(*args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
intervitensinc-gemma-2-70884-v2-mkmlizer: rv = self.invoke(ctx)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
intervitensinc-gemma-2-70884-v2-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
intervitensinc-gemma-2-70884-v2-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
intervitensinc-gemma-2-70884-v2-mkmlizer: return __callback(*args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 39, in quantize
intervitensinc-gemma-2-70884-v2-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/code/uploading/mkmlize.py", line 86, in download_to_shared_memory
intervitensinc-gemma-2-70884-v2-mkmlizer: snapshot_download(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
intervitensinc-gemma-2-70884-v2-mkmlizer: return fn(*args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 294, in snapshot_download
intervitensinc-gemma-2-70884-v2-mkmlizer: _inner_hf_hub_download(file)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 270, in _inner_hf_hub_download
intervitensinc-gemma-2-70884-v2-mkmlizer: return hf_hub_download(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
intervitensinc-gemma-2-70884-v2-mkmlizer: return fn(*args, **kwargs)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 840, in hf_hub_download
intervitensinc-gemma-2-70884-v2-mkmlizer: return _hf_hub_download_to_local_dir(
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1089, in _hf_hub_download_to_local_dir
intervitensinc-gemma-2-70884-v2-mkmlizer: _raise_on_head_call_error(head_call_error, force_download, local_files_only)
intervitensinc-gemma-2-70884-v2-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1485, in _raise_on_head_call_error
intervitensinc-gemma-2-70884-v2-mkmlizer: raise LocalEntryNotFoundError(
intervitensinc-gemma-2-70884-v2-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.
Failed to get response for submission intervitensinc-gemma-2-_70884_v1: HTTPConnectionPool(host='intervitensinc-gemma-2-70884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Job intervitensinc-gemma-2-70884-v2-mkmlizer completed after 140.43s with status: failed
Stopping job with name intervitensinc-gemma-2-70884-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name intervitensinc-gemma-2-70884-v2-mkmlizer
Waiting for job on intervitensinc-gemma-2-70884-v2-mkmlizer to finish
intervitensinc-gemma-2-70884-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ _____ __ __ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ /___/ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Version: 0.12.8 ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ https://mk1.ai ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ The license key for the current software has been verified as ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ belonging to: ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Chai Research Corp. ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ║ ║
intervitensinc-gemma-2-70884-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
intervitensinc-gemma-2-70884-v2-mkmlizer: Downloaded to shared memory in 146.812s
intervitensinc-gemma-2-70884-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv99u6aob, device:0
intervitensinc-gemma-2-70884-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission intervitensinc-gemma-2-_70884_v1: HTTPConnectionPool(host='intervitensinc-gemma-2-70884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
intervitensinc-gemma-2-70884-v2-mkmlizer: quantized model in 77.659s
intervitensinc-gemma-2-70884-v2-mkmlizer: Processed model IntervitensInc/gemma-2-27b-chatml in 224.471s
intervitensinc-gemma-2-70884-v2-mkmlizer: creating bucket guanaco-mkml-models
intervitensinc-gemma-2-70884-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
intervitensinc-gemma-2-70884-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/config.json
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/special_tokens_map.json
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/tokenizer_config.json
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/tokenizer.model
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/tokenizer.json
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/flywheel_model.2.safetensors
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/flywheel_model.0.safetensors
intervitensinc-gemma-2-70884-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/intervitensinc-gemma-2-70884-v2/flywheel_model.1.safetensors
Failed to get response for submission intervitensinc-gemma-2-_70884_v1: HTTPConnectionPool(host='intervitensinc-gemma-2-70884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
intervitensinc-gemma-2-70884-v2-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 5/508 [00:00<00:12, 39.17it/s] Loading 0: 2%|▏ | 9/508 [00:00<00:36, 13.63it/s] Loading 0: 3%|▎ | 15/508 [00:00<00:25, 19.13it/s] Loading 0: 4%|▎ | 18/508 [00:00<00:23, 21.08it/s] Loading 0: 5%|▍ | 23/508 [00:01<00:18, 26.42it/s] Loading 0: 6%|▌ | 28/508 [00:01<00:20, 23.26it/s] Loading 0: 6%|▌ | 31/508 [00:01<00:28, 16.89it/s] Loading 0: 7%|▋ | 36/508 [00:01<00:21, 21.71it/s] Loading 0: 8%|▊ | 39/508 [00:01<00:24, 18.84it/s] Loading 0: 9%|▉ | 45/508 [00:02<00:18, 25.65it/s] Loading 0: 10%|▉ | 49/508 [00:02<00:16, 28.32it/s] Loading 0: 10%|█ | 53/508 [00:02<00:29, 15.67it/s] Loading 0: 11%|█▏ | 58/508 [00:02<00:22, 20.25it/s] Loading 0: 12%|█▏ | 62/508 [00:03<00:22, 19.83it/s] Loading 0: 13%|█▎ | 68/508 [00:03<00:17, 25.58it/s] Loading 0: 14%|█▍ | 72/508 [00:03<00:21, 20.58it/s] Loading 0: 15%|█▍ | 75/508 [00:03<00:26, 16.24it/s] Loading 0: 16%|█▌ | 80/508 [00:03<00:20, 20.97it/s] Loading 0: 17%|█▋ | 84/508 [00:04<00:20, 20.35it/s] Loading 0: 18%|█▊ | 89/508 [00:04<00:16, 24.90it/s] Loading 0: 18%|█▊ | 93/508 [00:04<00:15, 26.55it/s] Loading 0: 19%|█▉ | 97/508 [00:04<00:19, 20.88it/s] Loading 0: 20%|█▉ | 100/508 [00:04<00:21, 18.72it/s] Loading 0: 20%|██ | 103/508 [00:04<00:19, 20.33it/s] Loading 0: 21%|██ | 106/508 [00:05<00:18, 21.95it/s] Loading 0: 21%|██▏ | 109/508 [00:05<00:21, 18.89it/s] Loading 0: 23%|██▎ | 115/508 [00:05<00:14, 26.34it/s] Loading 0: 23%|██▎ | 119/508 [00:05<00:25, 15.09it/s] Loading 0: 24%|██▍ | 124/508 [00:06<00:19, 19.56it/s] Loading 0: 25%|██▌ | 128/508 [00:06<00:19, 19.22it/s] Loading 0: 26%|██▌ | 133/508 [00:06<00:15, 23.94it/s] Loading 0: 27%|██▋ | 137/508 [00:06<00:14, 26.23it/s] Loading 0: 28%|██▊ | 141/508 [00:06<00:23, 15.81it/s] Loading 0: 29%|██▊ | 146/508 [00:07<00:17, 20.48it/s] Loading 0: 30%|██▉ | 150/508 [00:07<00:17, 20.24it/s] Loading 0: 31%|███ | 155/508 [00:07<00:14, 24.47it/s] Loading 0: 31%|███▏ | 159/508 [00:07<00:13, 26.82it/s] Loading 0: 32%|███▏ | 163/508 [00:07<00:20, 16.51it/s] Loading 0: 33%|███▎ | 169/508 [00:08<00:16, 20.09it/s] Loading 0: 34%|███▍ | 174/508 [00:08<00:13, 24.61it/s] Loading 0: 35%|███▌ | 178/508 [00:08<00:12, 26.54it/s] Loading 0: 36%|███▌ | 182/508 [00:08<00:14, 22.24it/s] Loading 0: 36%|███▋ | 185/508 [00:08<00:18, 17.33it/s] Loading 0: 38%|███▊ | 191/508 [00:09<00:15, 20.94it/s] Loading 0: 38%|███▊ | 191/508 [00:23<00:15, 20.94it/s] Loading 0: 38%|███▊ | 192/508 [00:23<06:42, 1.27s/it] Loading 0: 39%|███▉ | 199/508 [00:23<03:34, 1.44it/s] Loading 0: 40%|███▉ | 203/508 [00:23<02:38, 1.93it/s] Loading 0: 41%|████ | 206/508 [00:24<02:09, 2.33it/s] Loading 0: 41%|████ | 209/508 [00:24<01:39, 3.00it/s] Loading 0: 42%|████▏ | 213/508 [00:24<01:11, 4.12it/s] Loading 0: 43%|████▎ | 216/508 [00:24<00:55, 5.28it/s] Loading 0: 44%|████▎ | 222/508 [00:24<00:33, 8.54it/s] Loading 0: 44%|████▍ | 226/508 [00:25<00:28, 9.90it/s] Loading 0: 45%|████▌ | 229/508 [00:25<00:27, 9.97it/s] Loading 0: 46%|████▋ | 235/508 [00:25<00:19, 13.69it/s] Loading 0: 47%|████▋ | 238/508 [00:25<00:17, 15.58it/s] Loading 0: 48%|████▊ | 244/508 [00:25<00:12, 21.79it/s] Loading 0: 49%|████▉ | 248/508 [00:25<00:12, 20.11it/s] Loading 0: 50%|████▉ | 252/508 [00:26<00:14, 17.28it/s] Loading 0: 50%|█████ | 256/508 [00:26<00:12, 20.54it/s] Loading 0: 51%|█████ | 259/508 [00:26<00:13, 18.68it/s] Loading 0: 52%|█████▏ | 265/508 [00:26<00:09, 25.13it/s] Loading 0: 53%|█████▎ | 270/508 [00:26<00:10, 22.80it/s] Loading 0: 54%|█████▎ | 273/508 [00:27<00:13, 17.79it/s] Loading 0: 55%|█████▍ | 279/508 [00:27<00:10, 21.08it/s] Loading 0: 56%|█████▌ | 282/508 [00:27<00:10, 22.36it/s] Loading 0: 56%|█████▋ | 287/508 [00:27<00:08, 27.36it/s] Loading 0: 57%|█████▋ | 291/508 [00:27<00:07, 29.76it/s] Loading 0: 58%|█████▊ | 295/508 [00:28<00:12, 17.69it/s] Loading 0: 59%|█████▉ | 301/508 [00:28<00:09, 21.08it/s] Loading 0: 60%|█████▉ | 304/508 [00:28<00:09, 22.43it/s] Loading 0: 61%|██████ | 309/508 [00:28<00:07, 27.05it/s] Loading 0: 62%|██████▏ | 314/508 [00:28<00:08, 23.90it/s] Loading 0: 62%|██████▏ | 317/508 [00:29<00:10, 18.55it/s] Loading 0: 64%|██████▎ | 323/508 [00:29<00:08, 21.88it/s] Loading 0: 64%|██████▍ | 326/508 [00:29<00:07, 23.11it/s] Loading 0: 65%|██████▌ | 331/508 [00:29<00:06, 28.19it/s] Loading 0: 66%|██████▌ | 335/508 [00:29<00:05, 30.69it/s] Loading 0: 67%|██████▋ | 339/508 [00:30<00:09, 18.02it/s] Loading 0: 68%|██████▊ | 345/508 [00:30<00:07, 21.41it/s] Loading 0: 69%|██████▊ | 348/508 [00:30<00:07, 22.80it/s] Loading 0: 69%|██████▉ | 353/508 [00:30<00:05, 27.66it/s] Loading 0: 70%|███████ | 357/508 [00:30<00:05, 30.05it/s] Loading 0: 71%|███████ | 361/508 [00:31<00:08, 17.87it/s] Loading 0: 72%|███████▏ | 367/508 [00:31<00:06, 21.24it/s] Loading 0: 73%|███████▎ | 370/508 [00:31<00:06, 22.61it/s] Loading 0: 74%|███████▍ | 376/508 [00:31<00:04, 28.50it/s] Loading 0: 75%|███████▍ | 380/508 [00:31<00:05, 23.28it/s] Loading 0: 75%|███████▌ | 383/508 [00:32<00:06, 18.21it/s] Loading 0: 77%|███████▋ | 389/508 [00:32<00:05, 21.53it/s] Loading 0: 77%|███████▋ | 392/508 [00:32<00:05, 22.91it/s] Loading 0: 78%|███████▊ | 398/508 [00:32<00:03, 28.86it/s] Loading 0: 79%|███████▉ | 402/508 [00:32<00:04, 23.87it/s] Loading 0: 80%|███████▉ | 405/508 [00:32<00:05, 18.45it/s] Loading 0: 81%|████████ | 411/508 [00:33<00:04, 21.86it/s] Loading 0: 81%|████████▏ | 414/508 [00:33<00:04, 23.04it/s] Loading 0: 82%|████████▏ | 419/508 [00:33<00:03, 27.51it/s] Loading 0: 83%|████████▎ | 423/508 [00:33<00:02, 29.05it/s] Loading 0: 84%|████████▍ | 427/508 [00:33<00:04, 17.74it/s] Loading 0: 85%|████████▌ | 433/508 [00:34<00:03, 21.19it/s] Loading 0: 86%|████████▌ | 436/508 [00:34<00:03, 22.58it/s] Loading 0: 87%|████████▋ | 442/508 [00:34<00:02, 28.53it/s] Loading 0: 88%|████████▊ | 446/508 [00:34<00:02, 23.68it/s] Loading 0: 88%|████████▊ | 449/508 [00:49<01:05, 1.10s/it] Loading 0: 90%|████████▉ | 455/508 [00:49<00:36, 1.45it/s] Loading 0: 91%|█████████ | 460/508 [00:49<00:22, 2.09it/s] Loading 0: 91%|█████████▏| 464/508 [00:49<00:15, 2.77it/s] Loading 0: 92%|█████████▏| 468/508 [00:49<00:11, 3.54it/s] Loading 0: 93%|█████████▎| 471/508 [00:50<00:08, 4.15it/s] Loading 0: 94%|█████████▍| 477/508 [00:50<00:04, 6.30it/s] Loading 0: 95%|█████████▍| 482/508 [00:50<00:02, 8.72it/s] Loading 0: 96%|█████████▌| 486/508 [00:50<00:02, 10.88it/s] Loading 0: 96%|█████████▋| 490/508 [00:50<00:01, 11.85it/s] Loading 0: 97%|█████████▋| 493/508 [00:51<00:01, 11.45it/s] Loading 0: 98%|█████████▊| 499/508 [00:51<00:00, 15.23it/s] Loading 0: 99%|█████████▉| 504/508 [00:51<00:00, 19.46it/s] Loading 0: 100%|██████████| 508/508 [00:51<00:00, 22.56it/s]
Job intervitensinc-gemma-2-70884-v2-mkmlizer completed after 259.88s with status: succeeded
Stopping job with name intervitensinc-gemma-2-70884-v2-mkmlizer
Pipeline stage MKMLizer completed in 401.45s
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 intervitensinc-gemma-2-70884-v2
Waiting for inference service intervitensinc-gemma-2-70884-v2 to be ready
Inference service intervitensinc-gemma-2-70884-v2 ready after 120.5460090637207s
Pipeline stage MKMLDeployer completed in 121.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.08853816986084s
Failed to get response for submission intervitensinc-gemma-2-_70884_v1: HTTPConnectionPool(host='intervitensinc-gemma-2-70884-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 3.3791563510894775s
Received healthy response to inference request in 2.54782772064209s
Received healthy response to inference request in 3.3558454513549805s
Received healthy response to inference request in 3.3282880783081055s
5 requests
0 failed requests
5th percentile: 2.703919792175293
10th percentile: 2.860011863708496
20th percentile: 3.1721960067749024
30th percentile: 3.3337995529174806
40th percentile: 3.3448225021362306
50th percentile: 3.3558454513549805
60th percentile: 3.365169811248779
70th percentile: 3.374494171142578
80th percentile: 3.5210327148437504
90th percentile: 3.804785442352295
95th percentile: 3.946661806106567
99th percentile: 4.0601628971099855
mean time: 3.3399311542510985
Pipeline stage StressChecker completed in 18.37s
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 0.95s
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 0.77s
Shutdown handler de-registered
intervitensinc-gemma-2-_70884_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5493.14s
Shutdown handler de-registered
intervitensinc-gemma-2-_70884_v2 status is now inactive due to auto deactivation removed underperforming models
intervitensinc-gemma-2-_70884_v2 status is now torndown due to DeploymentManager action