submission_id: meta-llama-meta-llama-3-_5386_v3
developer_uid: c.gato
best_of: 16
celo_rating: 1182.38
display_name: meta-llama-meta-llama-3-_5386_v3
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: meta-llama/Meta-Llama-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: meta-llama/Meta-Llama-3-
model_name: meta-llama-meta-llama-3-_5386_v3
model_num_parameters: 8030261248.0
model_repo: meta-llama/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 24010
num_wins: 12516
ranking_group: single
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-18T14:12:59+00:00
us_pacific_date: 2024-06-18
win_ratio: 0.5212827988338192
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meta-llama-meta-llama-3-5386-v3-mkmlizer
Waiting for job on meta-llama-meta-llama-3-5386-v3-mkmlizer to finish
meta-llama-meta-llama-3-5386-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Version: 0.8.14 ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-5386-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
meta-llama-meta-llama-3-5386-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
meta-llama-meta-llama-3-5386-v3-mkmlizer: Traceback (most recent call last):
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 509, in http_get
meta-llama-meta-llama-3-5386-v3-mkmlizer: hf_transfer.download(
meta-llama-meta-llama-3-5386-v3-mkmlizer: Exception: Error while downloading: reqwest::Error { kind: Request, url: Url { scheme: "https", cannot_be_a_base: false, username: "", password: None, host: Some(Domain("cdn-lfs-us-1.huggingface.co")), port: None, path: "/repos/55/ac/d75fe51bfa8bd7a4e4518/d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c", query: Some("response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model-00001-of-00004.safetensors%3B+filename%3D%22model-00001-of-00004.safetensors%22%3B&Expires=1718979134&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODk3OTEzNH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzU1L2FjLzU1YWNkZGJiNWMyYWMyMDQxYjg5YTg1OGVlYmE4MmU2MTMwYzYxNjAyOTRkNzVmZTUxYmZhOGJkN2E0ZTQ1MTgvZDhjZjljNGQwZGQ5NzJlMWEyMTMxYmZlNjU2MjM1ZWU5ODIyMTY3OTcxMWEzYmVlZjZkNDZkYWRmMGYyMGI1Yz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=SLmRTgOE3NxBmfW5I09KPNlR8pAnvDTxDxgRkzAs0BM1p-xh8TQIROvhX0kvkZrdcGj8jl4f7BCTsjvTiJbwr6IdkeU6-Rsk3oQIQj1%7EulYEH2Y2wtWHkzcbCRk2mIiRy%7Ekh1GjlE35AQLzIj%7EPmViQNTjRGfK1nlt9PA-JZbVQK56iXkMp8965SJwIg2GqzzKFe%7Edp86KIX0WBYOL6hnS9eT7TJFo43bCdWXYi6HhrXxH5SH52ykpdASOq0dBm1F5yHIb5ZXH0bw0QJIKoOEEB2KUCJjiuMVbCGvtxavUM3tuzT268TG%7EUFKXdXYEemEdJv4fEWEAHDa4jz-NukqQ__&Key-Pair-Id=K2FPYV99P2N66Q"), fragment: None }, source: hyper::Error(Connect, ConnectError("dns error", Custom { kind: Uncategorized, error: "failed to lookup address information: Temporary failure in name resolution" })) }
meta-llama-meta-llama-3-5386-v3-mkmlizer: The above exception was the direct cause of the following exception:
meta-llama-meta-llama-3-5386-v3-mkmlizer: Traceback (most recent call last):
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/code/uploading/mkmlize.py", line 151, in <module>
meta-llama-meta-llama-3-5386-v3-mkmlizer: cli()
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
meta-llama-meta-llama-3-5386-v3-mkmlizer: return self.main(*args, **kwargs)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
meta-llama-meta-llama-3-5386-v3-mkmlizer: rv = self.invoke(ctx)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
meta-llama-meta-llama-3-5386-v3-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
meta-llama-meta-llama-3-5386-v3-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
meta-llama-meta-llama-3-5386-v3-mkmlizer: return __callback(*args, **kwargs)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/code/uploading/mkmlize.py", line 38, in quantize
meta-llama-meta-llama-3-5386-v3-mkmlizer: temp_folder = download_to_shared_memory(repo_id, revision, hf_auth_token)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/code/uploading/mkmlize.py", line 65, in download_to_shared_memory
meta-llama-meta-llama-3-5386-v3-mkmlizer: snapshot_download(
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
meta-llama-meta-llama-3-5386-v3-mkmlizer: return fn(*args, **kwargs)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 314, in snapshot_download
meta-llama-meta-llama-3-5386-v3-mkmlizer: _inner_hf_hub_download(file)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/_snapshot_download.py", line 290, in _inner_hf_hub_download
meta-llama-meta-llama-3-5386-v3-mkmlizer: return hf_hub_download(
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
meta-llama-meta-llama-3-5386-v3-mkmlizer: return fn(*args, **kwargs)
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
meta-llama-meta-llama-3-5386-v3-mkmlizer: http_get(
meta-llama-meta-llama-3-5386-v3-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 520, in http_get
meta-llama-meta-llama-3-5386-v3-mkmlizer: raise RuntimeError(
meta-llama-meta-llama-3-5386-v3-mkmlizer: RuntimeError: An error occurred while downloading using `hf_transfer`. Consider disabling HF_HUB_ENABLE_HF_TRANSFER for better error handling.
Job meta-llama-meta-llama-3-5386-v3-mkmlizer completed after 21.91s with status: failed
Stopping job with name meta-llama-meta-llama-3-5386-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name meta-llama-meta-llama-3-5386-v3-mkmlizer
Waiting for job on meta-llama-meta-llama-3-5386-v3-mkmlizer to finish
meta-llama-meta-llama-3-5386-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Version: 0.8.14 ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ║ ║
meta-llama-meta-llama-3-5386-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-5386-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
meta-llama-meta-llama-3-5386-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
meta-llama-meta-llama-3-5386-v3-mkmlizer: Downloaded to shared memory in 56.098s
meta-llama-meta-llama-3-5386-v3-mkmlizer: quantizing model to /dev/shm/model_cache
meta-llama-meta-llama-3-5386-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-5386-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 78.28it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 78.33it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:03, 75.69it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:02, 91.42it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 93.61it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 85.96it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 85.67it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 85.80it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:04, 42.49it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:03, 50.06it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:03, 57.28it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 62.86it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:02, 68.02it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:02, 72.21it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:02, 75.40it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:01, 81.87it/s] Loading 0: 57%|█████▋ | 165/291 [00:02<00:01, 99.04it/s] Loading 0: 62%|██████▏ | 179/291 [00:02<00:01, 105.98it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:01, 57.68it/s] Loading 0: 68%|██████▊ | 199/291 [00:02<00:01, 63.08it/s] Loading 0: 71%|███████▏ | 208/291 [00:02<00:01, 68.15it/s] Loading 0: 75%|███████▍ | 217/291 [00:03<00:01, 72.16it/s] Loading 0: 78%|███████▊ | 226/291 [00:03<00:00, 75.48it/s] Loading 0: 81%|████████ | 235/291 [00:03<00:00, 77.81it/s] Loading 0: 84%|████████▍ | 244/291 [00:03<00:00, 79.67it/s] Loading 0: 87%|████████▋ | 253/291 [00:03<00:00, 81.33it/s] Loading 0: 90%|█████████ | 262/291 [00:03<00:00, 83.46it/s] Loading 0: 94%|█████████▍| 273/291 [00:03<00:00, 85.23it/s] Loading 0: 97%|█████████▋| 282/291 [00:03<00:00, 81.70it/s] Loading 0: 100%|██████████| 291/291 [00:09<00:00, 4.96it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meta-llama-meta-llama-3-5386-v3-mkmlizer: quantized model in 25.702s
meta-llama-meta-llama-3-5386-v3-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B-Instruct in 87.181s
meta-llama-meta-llama-3-5386-v3-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-5386-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-5386-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3/special_tokens_map.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3/config.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3/tokenizer.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3/tokenizer_config.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v3/flywheel_model.0.safetensors
meta-llama-meta-llama-3-5386-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meta-llama-meta-llama-3-5386-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meta-llama-meta-llama-3-5386-v3-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-5386-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meta-llama-meta-llama-3-5386-v3-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-5386-v3-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.
meta-llama-meta-llama-3-5386-v3-mkmlizer: warnings.warn(
meta-llama-meta-llama-3-5386-v3-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()
meta-llama-meta-llama-3-5386-v3-mkmlizer: return self.fget.__get__(instance, owner)()
meta-llama-meta-llama-3-5386-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meta-llama-meta-llama-3-5386-v3-mkmlizer: Saving duration: 0.501s
meta-llama-meta-llama-3-5386-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.755s
meta-llama-meta-llama-3-5386-v3-mkmlizer: creating bucket guanaco-reward-models
meta-llama-meta-llama-3-5386-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meta-llama-meta-llama-3-5386-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/config.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/merges.txt
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/special_tokens_map.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/tokenizer_config.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/vocab.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/tokenizer.json
meta-llama-meta-llama-3-5386-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meta-llama-meta-llama-3-5386-v3_reward/reward.tensors
Job meta-llama-meta-llama-3-5386-v3-mkmlizer completed after 145.15s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-5386-v3-mkmlizer
Pipeline stage MKMLizer completed in 170.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meta-llama-meta-llama-3-5386-v3
Waiting for inference service meta-llama-meta-llama-3-5386-v3 to be ready
Inference service meta-llama-meta-llama-3-5386-v3 ready after 40.245185136795044s
Pipeline stage ISVCDeployer completed in 47.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1935181617736816s
Received healthy response to inference request in 1.3003942966461182s
Received healthy response to inference request in 1.0783042907714844s
Received healthy response to inference request in 1.2373919486999512s
Received healthy response to inference request in 1.289628028869629s
5 requests
0 failed requests
5th percentile: 1.1101218223571778
10th percentile: 1.141939353942871
20th percentile: 1.2055744171142577
30th percentile: 1.2478391647338867
40th percentile: 1.268733596801758
50th percentile: 1.289628028869629
60th percentile: 1.2939345359802246
70th percentile: 1.2982410430908202
80th percentile: 1.479019069671631
90th percentile: 1.8362686157226564
95th percentile: 2.0148933887481686
99th percentile: 2.157793207168579
mean time: 1.419847345352173
Pipeline stage StressChecker completed in 8.31s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
meta-llama-meta-llama-3-_5386_v3 status is now deployed due to DeploymentManager action
meta-llama-meta-llama-3-_5386_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meta-llama-meta-llama-3-_5386_v3
Running pipeline stage ISVCDeleter
Checking if service meta-llama-meta-llama-3-5386-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meta-llama-meta-llama-3-5386-v3/config.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-5386-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-5386-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-5386-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key meta-llama-meta-llama-3-5386-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meta-llama-meta-llama-3-5386-v3_reward/config.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meta-llama-meta-llama-3-5386-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.81s
meta-llama-meta-llama-3-_5386_v3 status is now torndown due to DeploymentManager action