submission_id: hastagaras-kaliurang-8b-l3-h_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1203.4
display_name: 1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|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': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/Kaliurang-8B-L3-H
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Hastagaras/Kaliurang-8B-
model_name: 1
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Kaliurang-8B-L3-H
model_size: 8B
num_battles: 35386
num_wins: 18616
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': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-07-06T08:55:04+00:00
us_pacific_date: 2024-07-06
win_ratio: 0.5260837619397501
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-kaliurang-8b-l3-h-v1-mkmlizer
Waiting for job on hastagaras-kaliurang-8b-l3-h-v1-mkmlizer to finish
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ /___/ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ belonging to: ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Downloaded to shared memory in 47.011s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 111.12it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 133.86it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 131.42it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 133.41it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 139.76it/s] Loading 0: 31%|███ | 89/291 [00:00<00:02, 73.11it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 85.40it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 101.26it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 107.79it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 115.44it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 125.43it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 128.54it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 75.83it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 90.43it/s] Loading 0: 77%|███████▋ | 224/291 [00:02<00:00, 99.73it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 107.52it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 119.82it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 127.85it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 8.48it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: quantized model in 23.891s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Processed model Hastagaras/Kaliurang-8B-L3-H in 70.902s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/tokenizer_config.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/config.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/special_tokens_map.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/tokenizer.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/flywheel_model.0.safetensors
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-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.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Traceback (most recent call last):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: conn = connection.create_connection(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/connection.py", line 72, in create_connection
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/socket.py", line 955, in getaddrinfo
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: socket.gaierror: [Errno -3] Temporary failure in name resolution
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: During handling of the above exception, another exception occurred:
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Traceback (most recent call last):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 714, in urlopen
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: httplib_response = self._make_request(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 403, in _make_request
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: self._validate_conn(conn)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1053, in _validate_conn
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: conn.connect()
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: self.sock = conn = self._new_conn()
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: raise NewConnectionError(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x7f11012c1cc0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: During handling of the above exception, another exception occurred:
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Traceback (most recent call last):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: resp = conn.urlopen(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 798, in urlopen
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: retries = retries.increment(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: raise MaxRetryError(_pool, url, error or ResponseError(cause))
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/dc/b4/49cb0beb9d88e612ee4c9/f485ab2daabd6cfb584d1f5dbe44415c4037052562040fbb665d9d465a3487f2?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27pytorch_model.bin%3B+filename%3D%22pytorch_model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1720515399&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcyMDUxNTM5OX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2RjL2I0L2RjYjQ0YWZmYTFmYTZkOWY2YWZlMGNhZjg2ZDM4ODJlMzljNGMzZTZiOWE0OWNiMGJlYjlkODhlNjEyZWU0YzkvZjQ4NWFiMmRhYWJkNmNmYjU4NGQxZjVkYmU0NDQxNWM0MDM3MDUyNTYyMDQwZmJiNjY1ZDlkNDY1YTM0ODdmMj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=cZtTt0o8C0b06YC1RgUGv0QeikiVTea~MNiZagWFNE8SSraj94EU3MQhaH~6VLU8qwVvSlDF4xPsEDKElDFF8kznCFUIi6IxRmk59r42P06lc40mlQPP~1W7wKGof2~tpeZVN2tXqPmNLhhvZe2C5pbcP0DAt2ldGyar6CrHJAof4BHjbCaWStVJISwdTeJZ8L7j9Q94mLaCzXDD~t1ku9zqD5EthLw9G42cy12HjcGXr1VUOraqtBEQhIm7Swk2oVuu4DKC04ytpGsJBsBQqL0-YJUwD9SWcFRvNw6tNZqalSkzuJDFPfc97~vtUmBBSoS3taT7mbPYkhTCWXQ0CQ__&Key-Pair-Id=K24J24Z295AEI9 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f11012c1cc0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: During handling of the above exception, another exception occurred:
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Traceback (most recent call last):
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/code/uploading/reward.py", line 66, in <module>
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cli()
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return self.main(*args, **kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: rv = self.invoke(ctx)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return _process_result(sub_ctx.command.invoke(sub_ctx))
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return ctx.invoke(self.callback, **ctx.params)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return __callback(*args, **kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/code/uploading/reward.py", line 29, in tensorize_reward_model
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: model, config, tokenizer = download_from_huggingface(repo_id, revision, hf_auth_token)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/code/uploading/reward.py", line 44, in download_from_huggingface
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: model = AutoModelForSequenceClassification.from_pretrained(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 563, in from_pretrained
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return model_class.from_pretrained(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3380, in from_pretrained
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: resolved_archive_file = cached_file(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py", line 399, in cached_file
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: resolved_file = hf_hub_download(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return fn(*args, **kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1221, in hf_hub_download
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return _hf_hub_download_to_cache_dir(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1367, in _hf_hub_download_to_cache_dir
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: _download_to_tmp_and_move(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1884, in _download_to_tmp_and_move
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: http_get(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 459, in http_get
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: r = _request_wrapper(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 395, in _request_wrapper
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: response = get_session().request(method=method, url=url, **params)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: resp = self.send(prep, **send_kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: r = adapter.send(request, **kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 66, in send
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return super().send(request, *args, **kwargs)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 519, in send
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: raise ConnectionError(e, request=request)
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Max retries exceeded with url: /repos/dc/b4/49cb0beb9d88e612ee4c9/f485ab2daabd6cfb584d1f5dbe44415c4037052562040fbb665d9d465a3487f2?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27pytorch_model.bin%3B+filename%3D%22pytorch_model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1720515399&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcyMDUxNTM5OX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2RjL2I0L2RjYjQ0YWZmYTFmYTZkOWY2YWZlMGNhZjg2ZDM4ODJlMzljNGMzZTZiOWE0OWNiMGJlYjlkODhlNjEyZWU0YzkvZjQ4NWFiMmRhYWJkNmNmYjU4NGQxZjVkYmU0NDQxNWM0MDM3MDUyNTYyMDQwZmJiNjY1ZDlkNDY1YTM0ODdmMj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=cZtTt0o8C0b06YC1RgUGv0QeikiVTea~MNiZagWFNE8SSraj94EU3MQhaH~6VLU8qwVvSlDF4xPsEDKElDFF8kznCFUIi6IxRmk59r42P06lc40mlQPP~1W7wKGof2~tpeZVN2tXqPmNLhhvZe2C5pbcP0DAt2ldGyar6CrHJAof4BHjbCaWStVJISwdTeJZ8L7j9Q94mLaCzXDD~t1ku9zqD5EthLw9G42cy12HjcGXr1VUOraqtBEQhIm7Swk2oVuu4DKC04ytpGsJBsBQqL0-YJUwD9SWcFRvNw6tNZqalSkzuJDFPfc97~vtUmBBSoS3taT7mbPYkhTCWXQ0CQ__&Key-Pair-Id=K24J24Z295AEI9 (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f11012c1cc0>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))"), '(Request ID: d51d90e4-600c-4a78-8181-65994d489309)')
Job hastagaras-kaliurang-8b-l3-h-v1-mkmlizer completed after 116.09s with status: failed
Stopping job with name hastagaras-kaliurang-8b-l3-h-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-kaliurang-8b-l3-h-v1-mkmlizer
Waiting for job on hastagaras-kaliurang-8b-l3-h-v1-mkmlizer to finish
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ /___/ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ belonging to: ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ║ ║
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Downloaded to shared memory in 16.140s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 114.31it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 136.00it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 134.06it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 133.83it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 140.70it/s] Loading 0: 31%|███ | 90/291 [00:00<00:02, 85.29it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 94.74it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 109.23it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 113.97it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 116.96it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 119.62it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 127.73it/s] Loading 0: 65%|██████▍ | 189/291 [00:01<00:01, 86.33it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 94.67it/s] Loading 0: 75%|███████▌ | 219/291 [00:01<00:00, 107.89it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 111.89it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 116.73it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 125.38it/s] Loading 0: 96%|█████████▌| 278/291 [00:02<00:00, 125.49it/s] Loading 0: 100%|██████████| 291/291 [00:08<00:00, 7.95it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: quantized model in 19.822s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Processed model Hastagaras/Kaliurang-8B-L3-H in 35.962s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/config.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/special_tokens_map.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/tokenizer_config.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/tokenizer.json
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-kaliurang-8b-l3-h-v1/flywheel_model.0.safetensors
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-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.
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: warnings.warn(
hastagaras-kaliurang-8b-l3-h-v1-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()
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Saving duration: 0.263s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.046s
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-h-v1_reward
hastagaras-kaliurang-8b-l3-h-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-kaliurang-8b-l3-h-v1_reward/config.json
Job hastagaras-kaliurang-8b-l3-h-v1-mkmlizer completed after 78.0s with status: succeeded
Stopping job with name hastagaras-kaliurang-8b-l3-h-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-kaliurang-8b-l3-h-v1
Waiting for inference service hastagaras-kaliurang-8b-l3-h-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service hastagaras-kaliurang-8b-l3-h-v1 ready after 40.24378418922424s
Pipeline stage ISVCDeployer completed in 47.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1109302043914795s
Received healthy response to inference request in 1.3747777938842773s
Received healthy response to inference request in 1.3348617553710938s
Received healthy response to inference request in 1.3114969730377197s
Received healthy response to inference request in 1.358548641204834s
5 requests
0 failed requests
5th percentile: 1.3161699295043945
10th percentile: 1.3208428859710692
20th percentile: 1.330188798904419
30th percentile: 1.3395991325378418
40th percentile: 1.349073886871338
50th percentile: 1.358548641204834
60th percentile: 1.3650403022766113
70th percentile: 1.3715319633483887
80th percentile: 1.5220082759857179
90th percentile: 1.8164692401885987
95th percentile: 1.963699722290039
99th percentile: 2.081484107971191
mean time: 1.4981230735778808
Pipeline stage StressChecker completed in 8.68s
hastagaras-kaliurang-8b-l3-h_v1 status is now deployed due to DeploymentManager action
hastagaras-kaliurang-8b-l3-h_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-kaliurang-8b-l3-h_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-kaliurang-8b-l3-h-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.16s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-kaliurang-8b-l3-h-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-kaliurang-8b-l3-h-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.68s
hastagaras-kaliurang-8b-l3-h_v1 status is now torndown due to DeploymentManager action