submission_id: failspy-llama-3-70b-inst_8684_v1
developer_uid: windyheath
best_of: 4
celo_rating: 1191.79
display_name: failspy-llama-3-70b-inst_8684_v1
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: failspy/llama-3-70B-Instruct-abliterated
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: failspy/llama-3-70B-Inst
model_name: failspy-llama-3-70b-inst_8684_v1
model_num_parameters: 70553706496.0
model_repo: failspy/llama-3-70B-Instruct-abliterated
model_size: 71B
num_battles: 12117
num_wins: 6296
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: 2024-06-07T21:20:59+00:00
us_pacific_date: 2024-06-07
win_ratio: 0.5196005611950153
Resubmit model
Running pipeline stage MKMLizer
Starting job with name failspy-llama-3-70b-inst-8684-v1-mkmlizer
Waiting for job on failspy-llama-3-70b-inst-8684-v1-mkmlizer to finish
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║     _____            __           __                                ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║       /___/                                                         ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║                                                                     ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  https://mk1.ai                                                     ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║                                                                     ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  belonging to:                                                      ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║                                                                     ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  Chai Research Corp.                                                ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ║                                                                     ║
failspy-llama-3-70b-inst-8684-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
failspy-llama-3-70b-inst-8684-v1-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.
failspy-llama-3-70b-inst-8684-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Downloaded to shared memory in 274.907s
failspy-llama-3-70b-inst-8684-v1-mkmlizer: quantizing model to /dev/shm/model_cache
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
failspy-llama-3-70b-inst-8684-v1-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/723 [00:00<00:19, 36.54it/s]
Loading 0:   2%|▏         | 14/723 [00:00<00:11, 61.66it/s]
Loading 0:   3%|▎         | 21/723 [00:00<00:23, 29.65it/s]
Loading 0:   4%|▎         | 26/723 [00:00<00:20, 33.65it/s]
Loading 0:   4%|▍         | 32/723 [00:00<00:19, 36.11it/s]
Loading 0:   6%|▌         | 42/723 [00:01<00:19, 34.79it/s]
Loading 0:   7%|▋         | 47/723 [00:01<00:19, 35.34it/s]
Loading 0:   7%|▋         | 51/723 [00:01<00:19, 34.19it/s]
Loading 0:   8%|▊         | 58/723 [00:01<00:16, 40.77it/s]
Loading 0:   9%|▉         | 68/723 [00:01<00:18, 34.94it/s]
Loading 0:  10%|▉         | 72/723 [00:02<00:19, 33.73it/s]
Loading 0:  11%|█         | 77/723 [00:02<00:18, 34.28it/s]
Loading 0:  12%|█▏        | 85/723 [00:02<00:15, 42.06it/s]
Loading 0:  13%|█▎        | 92/723 [00:02<00:19, 32.45it/s]
Loading 0:  13%|█▎        | 96/723 [00:02<00:19, 31.64it/s]
Loading 0:  14%|█▍        | 103/723 [00:02<00:16, 38.10it/s]
Loading 0:  15%|█▌        | 110/723 [00:02<00:14, 42.77it/s]
Loading 0:  16%|█▌        | 116/723 [00:03<00:19, 31.68it/s]
Loading 0:  17%|█▋        | 121/723 [00:03<00:18, 33.20it/s]
Loading 0:  17%|█▋        | 125/723 [00:19<08:57,  1.11it/s]
Loading 0:  18%|█▊        | 131/723 [00:19<06:03,  1.63it/s]
Loading 0:  19%|█▉        | 140/723 [00:19<03:33,  2.73it/s]
Loading 0:  20%|██        | 146/723 [00:19<02:43,  3.54it/s]
Loading 0:  21%|██        | 151/723 [00:19<02:04,  4.58it/s]
Loading 0:  22%|██▏       | 157/723 [00:19<01:29,  6.32it/s]
Loading 0:  23%|██▎       | 166/723 [00:19<00:56,  9.93it/s]
Loading 0:  24%|██▍       | 172/723 [00:20<00:49, 11.04it/s]
Loading 0:  24%|██▍       | 177/723 [00:20<00:40, 13.32it/s]
Loading 0:  25%|██▌       | 184/723 [00:20<00:29, 18.02it/s]
Loading 0:  27%|██▋       | 194/723 [00:20<00:25, 21.14it/s]
Loading 0:  28%|██▊       | 199/723 [00:21<00:22, 23.13it/s]
Loading 0:  28%|██▊       | 204/723 [00:21<00:20, 25.47it/s]
Loading 0:  29%|██▉       | 211/723 [00:21<00:16, 31.54it/s]
Loading 0:  30%|███       | 218/723 [00:21<00:18, 26.90it/s]
Loading 0:  31%|███       | 222/723 [00:21<00:18, 27.34it/s]
Loading 0:  32%|███▏      | 229/723 [00:21<00:14, 33.90it/s]
Loading 0:  33%|███▎      | 236/723 [00:22<00:12, 39.25it/s]
Loading 0:  33%|███▎      | 242/723 [00:22<00:16, 29.63it/s]
Loading 0:  34%|███▍      | 247/723 [00:22<00:15, 31.01it/s]
Loading 0:  35%|███▌      | 255/723 [00:22<00:12, 38.15it/s]
Loading 0:  36%|███▌      | 260/723 [00:22<00:11, 39.24it/s]
Loading 0:  37%|███▋      | 265/723 [00:40<07:04,  1.08it/s]
Loading 0:  37%|███▋      | 268/723 [00:40<05:53,  1.29it/s]
Loading 0:  38%|███▊      | 272/723 [00:40<04:24,  1.71it/s]
Loading 0:  38%|███▊      | 276/723 [00:40<03:15,  2.29it/s]
Loading 0:  39%|███▉      | 283/723 [00:40<01:57,  3.74it/s]
Loading 0:  40%|████      | 292/723 [00:41<01:08,  6.29it/s]
Loading 0:  41%|████      | 298/723 [00:41<00:55,  7.59it/s]
Loading 0:  42%|████▏     | 303/723 [00:41<00:44,  9.54it/s]
Loading 0:  43%|████▎     | 310/723 [00:41<00:30, 13.34it/s]
Loading 0:  44%|████▍     | 320/723 [00:41<00:23, 17.09it/s]
Loading 0:  45%|████▍     | 325/723 [00:42<00:20, 19.25it/s]
Loading 0:  46%|████▌     | 329/723 [00:42<00:18, 20.83it/s]
Loading 0:  47%|████▋     | 337/723 [00:42<00:13, 27.78it/s]
Loading 0:  48%|████▊     | 344/723 [00:42<00:15, 24.96it/s]
Loading 0:  48%|████▊     | 348/723 [00:42<00:14, 25.66it/s]
Loading 0:  49%|████▉     | 355/723 [00:42<00:11, 32.03it/s]
Loading 0:  50%|█████     | 362/723 [00:43<00:09, 37.67it/s]
Loading 0:  51%|█████     | 368/723 [00:43<00:12, 29.28it/s]
Loading 0:  52%|█████▏    | 373/723 [00:43<00:11, 30.93it/s]
Loading 0:  53%|█████▎    | 381/723 [00:43<00:08, 38.37it/s]
Loading 0:  53%|█████▎    | 386/723 [00:43<00:08, 39.49it/s]
Loading 0:  54%|█████▍    | 394/723 [00:44<00:10, 30.86it/s]
Loading 0:  55%|█████▌    | 399/723 [00:44<00:10, 32.18it/s]
Loading 0:  55%|█████▌    | 400/723 [01:01<00:10, 32.18it/s]
Loading 0:  55%|█████▌    | 401/723 [01:01<05:45,  1.07s/it]
Loading 0:  57%|█████▋    | 409/723 [01:01<03:20,  1.57it/s]
Loading 0:  58%|█████▊    | 418/723 [01:01<01:58,  2.58it/s]
Loading 0:  59%|█████▊    | 424/723 [01:02<01:30,  3.30it/s]
Loading 0:  59%|█████▉    | 429/723 [01:02<01:09,  4.25it/s]
Loading 0:  60%|██████    | 436/723 [01:02<00:46,  6.13it/s]
Loading 0:  62%|██████▏   | 445/723 [01:02<00:29,  9.46it/s]
Loading 0:  62%|██████▏   | 451/723 [01:02<00:26, 10.32it/s]
Loading 0:  63%|██████▎   | 456/723 [01:03<00:21, 12.34it/s]
Loading 0:  64%|██████▍   | 463/723 [01:03<00:15, 16.40it/s]
Loading 0:  65%|██████▌   | 470/723 [01:03<00:15, 16.54it/s]
Loading 0:  66%|██████▌   | 474/723 [01:03<00:13, 17.80it/s]
Loading 0:  67%|██████▋   | 481/723 [01:03<00:10, 23.07it/s]
Loading 0:  67%|██████▋   | 488/723 [01:03<00:08, 28.36it/s]
Loading 0:  68%|██████▊   | 494/723 [01:04<00:10, 22.73it/s]
Loading 0:  69%|██████▉   | 499/723 [01:04<00:08, 25.00it/s]
Loading 0:  70%|███████   | 507/723 [01:04<00:06, 32.05it/s]
Loading 0:  71%|███████   | 512/723 [01:04<00:06, 34.27it/s]
Loading 0:  72%|███████▏  | 520/723 [01:05<00:07, 27.57it/s]
Loading 0:  73%|███████▎  | 525/723 [01:05<00:06, 29.30it/s]
Loading 0:  73%|███████▎  | 529/723 [01:05<00:06, 31.10it/s]
Loading 0:  74%|███████▍  | 535/723 [01:05<00:05, 35.48it/s]
Loading 0:  75%|███████▍  | 540/723 [01:22<00:05, 35.48it/s]
Loading 0:  75%|███████▍  | 541/723 [01:22<02:43,  1.12it/s]
Loading 0:  76%|███████▌  | 546/723 [01:22<01:58,  1.49it/s]
Loading 0:  76%|███████▌  | 550/723 [01:22<01:30,  1.91it/s]
Loading 0:  77%|███████▋  | 554/723 [01:22<01:07,  2.50it/s]
Loading 0:  78%|███████▊  | 562/723 [01:23<00:38,  4.19it/s]
Loading 0:  79%|███████▉  | 571/723 [01:23<00:22,  6.80it/s]
Loading 0:  80%|███████▉  | 577/723 [01:23<00:18,  7.87it/s]
Loading 0:  80%|████████  | 582/723 [01:23<00:14,  9.72it/s]
Loading 0:  81%|████████▏ | 589/723 [01:23<00:09, 13.41it/s]
Loading 0:  82%|████████▏ | 596/723 [01:24<00:08, 14.57it/s]
Loading 0:  83%|████████▎ | 600/723 [01:24<00:07, 16.16it/s]
Loading 0:  84%|████████▍ | 607/723 [01:24<00:05, 21.51it/s]
Loading 0:  85%|████████▍ | 614/723 [01:24<00:04, 27.07it/s]
Loading 0:  86%|████████▌ | 620/723 [01:25<00:04, 23.52it/s]
Loading 0:  86%|████████▋ | 625/723 [01:25<00:03, 25.71it/s]
Loading 0:  88%|████████▊ | 633/723 [01:25<00:02, 33.05it/s]
Loading 0:  88%|████████▊ | 638/723 [01:25<00:02, 35.41it/s]
Loading 0:  89%|████████▉ | 646/723 [01:25<00:02, 29.61it/s]
Loading 0:  90%|█████████ | 651/723 [01:25<00:02, 30.51it/s]
Loading 0:  91%|█████████ | 655/723 [01:26<00:02, 30.14it/s]
Loading 0:  91%|█████████▏| 661/723 [01:26<00:01, 32.02it/s]
Loading 0:  92%|█████████▏| 666/723 [01:26<00:01, 35.49it/s]
Loading 0:  93%|█████████▎| 672/723 [01:26<00:01, 28.00it/s]
Loading 0:  93%|█████████▎| 676/723 [01:26<00:01, 25.96it/s]
Loading 0:  94%|█████████▍| 679/723 [01:42<00:46,  1.06s/it]
Loading 0:  95%|█████████▌| 687/723 [01:42<00:21,  1.64it/s]
Loading 0:  96%|█████████▌| 691/723 [01:42<00:15,  2.11it/s]
Loading 0:  97%|█████████▋| 698/723 [01:42<00:07,  3.15it/s]
Loading 0:  97%|█████████▋| 701/723 [01:43<00:05,  3.69it/s]
Loading 0:  98%|█████████▊| 706/723 [01:43<00:03,  5.07it/s]
Loading 0:  98%|█████████▊| 711/723 [01:43<00:01,  6.95it/s]
Loading 0:  99%|█████████▉| 715/723 [01:43<00:00,  8.69it/s]
Loading 0: 100%|█████████▉| 721/723 [01:43<00:00, 12.48it/s]
Loading 0: 100%|█████████▉| 722/723 [01:53<00:00, 12.48it/s]
Loading 0: 100%|██████████| 723/723 [01:53<00:00,  1.24it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
failspy-llama-3-70b-inst-8684-v1-mkmlizer: quantized model in 127.049s
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Processed model failspy/llama-3-70B-Instruct-abliterated in 410.758s
failspy-llama-3-70b-inst-8684-v1-mkmlizer: creating bucket guanaco-mkml-models
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
failspy-llama-3-70b-inst-8684-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/tokenizer_config.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/special_tokens_map.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/config.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/tokenizer.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.5.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.0.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.1.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.2.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.3.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/failspy-llama-3-70b-inst-8684-v1/flywheel_model.4.safetensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
failspy-llama-3-70b-inst-8684-v1-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.
failspy-llama-3-70b-inst-8684-v1-mkmlizer:   warnings.warn(
failspy-llama-3-70b-inst-8684-v1-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.
failspy-llama-3-70b-inst-8684-v1-mkmlizer:   warnings.warn(
failspy-llama-3-70b-inst-8684-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.
failspy-llama-3-70b-inst-8684-v1-mkmlizer:   warnings.warn(
failspy-llama-3-70b-inst-8684-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()
failspy-llama-3-70b-inst-8684-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Saving duration: 0.283s
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.089s
failspy-llama-3-70b-inst-8684-v1-mkmlizer: creating bucket guanaco-reward-models
failspy-llama-3-70b-inst-8684-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
failspy-llama-3-70b-inst-8684-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/config.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/special_tokens_map.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/tokenizer_config.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/merges.txt
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/vocab.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/tokenizer.json
failspy-llama-3-70b-inst-8684-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/failspy-llama-3-70b-inst-8684-v1_reward/reward.tensors
Job failspy-llama-3-70b-inst-8684-v1-mkmlizer completed after 458.65s with status: succeeded
Stopping job with name failspy-llama-3-70b-inst-8684-v1-mkmlizer
Pipeline stage MKMLizer completed in 463.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service failspy-llama-3-70b-inst-8684-v1
Waiting for inference service failspy-llama-3-70b-inst-8684-v1 to be ready
Inference service failspy-llama-3-70b-inst-8684-v1 ready after 82.22634148597717s
Pipeline stage ISVCDeployer completed in 90.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.097530364990234s
Received healthy response to inference request in 4.22988748550415s
Received healthy response to inference request in 4.189443111419678s
Received healthy response to inference request in 4.180940866470337s
Received healthy response to inference request in 4.161496162414551s
5 requests
0 failed requests
5th percentile: 4.165385103225708
10th percentile: 4.169274044036865
20th percentile: 4.17705192565918
30th percentile: 4.182641315460205
40th percentile: 4.186042213439942
50th percentile: 4.189443111419678
60th percentile: 4.205620861053466
70th percentile: 4.221798610687256
80th percentile: 4.4034160614013675
90th percentile: 4.750473213195801
95th percentile: 4.924001789093017
99th percentile: 5.062824649810791
mean time: 4.37185959815979
Pipeline stage StressChecker completed in 22.62s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
failspy-llama-3-70b-inst_8684_v1 status is now deployed due to DeploymentManager action
failspy-llama-3-70b-inst_8684_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of failspy-llama-3-70b-inst_8684_v1
Running pipeline stage ISVCDeleter
Checking if service failspy-llama-3-70b-inst-8684-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key failspy-llama-3-70b-inst-8684-v1/config.json from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key failspy-llama-3-70b-inst-8684-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/config.json from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key failspy-llama-3-70b-inst-8684-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.71s
failspy-llama-3-70b-inst_8684_v1 status is now torndown due to DeploymentManager action