neversleep-llama-3-lumim_6533

submission_id: neversleep-llama-3-lumim_6533_v1
developer_uid: Meliodia
best_of: 2
celo_rating: 1159.87
display_name: neversleep_70B_OAS
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{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': 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': 2, 'max_output_tokens': 64}
is_internal_developer: True
language_model: NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: NeverSleep/Llama-3-Lumim
model_name: neversleep_70B_OAS
model_num_parameters: 70553706496.0
model_repo: NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS
model_size: 71B
num_battles: 19232
num_wins: 9264
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-19T14:28:01+00:00
us_pacific_date: 2024-05-19
win_ratio: 0.48169717138103163
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-6533-v1-mkmlizer
Waiting for job on neversleep-llama-3-lumim-6533-v1-mkmlizer to finish
neversleep-llama-3-lumim-6533-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║     _____            __           __                                ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║       /___/                                                         ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  belonging to:                                                      ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ║                                                                     ║
neversleep-llama-3-lumim-6533-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-6533-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.
neversleep-llama-3-lumim-6533-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-6533-v1-mkmlizer: Downloaded to shared memory in 208.164s
neversleep-llama-3-lumim-6533-v1-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-6533-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-6533-v1-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/723 [00:00<00:18, 39.08it/s]
Loading 0:   2%|▏         | 11/723 [00:00<00:13, 50.97it/s]
Loading 0:   2%|▏         | 17/723 [00:00<00:28, 24.43it/s]
Loading 0:   3%|▎         | 22/723 [00:00<00:25, 27.67it/s]
Loading 0:   4%|▍         | 30/723 [00:00<00:18, 36.66it/s]
Loading 0:   5%|▍         | 35/723 [00:00<00:17, 39.07it/s]
Loading 0:   6%|▌         | 42/723 [00:01<00:23, 29.33it/s]
Loading 0:   6%|▋         | 46/723 [00:01<00:23, 29.32it/s]
Loading 0:   7%|▋         | 50/723 [00:01<00:23, 29.18it/s]
Loading 0:   8%|▊         | 58/723 [00:01<00:17, 37.96it/s]
Loading 0:   9%|▉         | 68/723 [00:02<00:20, 31.51it/s]
Loading 0:  10%|▉         | 72/723 [00:02<00:20, 31.02it/s]
Loading 0:  11%|█         | 77/723 [00:02<00:19, 32.31it/s]
Loading 0:  12%|█▏        | 85/723 [00:02<00:15, 40.61it/s]
Loading 0:  13%|█▎        | 92/723 [00:02<00:20, 30.25it/s]
Loading 0:  13%|█▎        | 96/723 [00:03<00:20, 29.98it/s]
Loading 0:  14%|█▍        | 103/723 [00:03<00:17, 36.25it/s]
Loading 0:  15%|█▌        | 110/723 [00:03<00:14, 41.62it/s]
Loading 0:  16%|█▌        | 116/723 [00:03<00:20, 29.51it/s]
Loading 0:  17%|█▋        | 120/723 [00:03<00:19, 31.20it/s]
Loading 0:  17%|█▋        | 125/723 [00:12<05:15,  1.90it/s]
Loading 0:  18%|█▊        | 131/723 [00:12<03:36,  2.74it/s]
Loading 0:  19%|█▉        | 140/723 [00:13<02:08,  4.52it/s]
Loading 0:  20%|██        | 145/723 [00:13<01:49,  5.27it/s]
Loading 0:  21%|██        | 149/723 [00:13<01:30,  6.37it/s]
Loading 0:  22%|██▏       | 156/723 [00:13<01:00,  9.37it/s]
Loading 0:  22%|██▏       | 161/723 [00:13<00:47, 11.83it/s]
Loading 0:  23%|██▎       | 168/723 [00:14<00:41, 13.39it/s]
Loading 0:  24%|██▍       | 172/723 [00:14<00:36, 14.98it/s]
Loading 0:  24%|██▍       | 176/723 [00:14<00:32, 16.93it/s]
Loading 0:  25%|██▌       | 184/723 [00:14<00:22, 24.21it/s]
Loading 0:  27%|██▋       | 194/723 [00:15<00:22, 23.31it/s]
Loading 0:  27%|██▋       | 198/723 [00:15<00:21, 24.01it/s]
Loading 0:  28%|██▊       | 202/723 [00:15<00:19, 26.13it/s]
Loading 0:  29%|██▉       | 210/723 [00:15<00:15, 34.16it/s]
Loading 0:  30%|██▉       | 215/723 [00:15<00:13, 36.52it/s]
Loading 0:  30%|███       | 220/723 [00:16<00:20, 24.22it/s]
Loading 0:  32%|███▏      | 228/723 [00:16<00:15, 32.28it/s]
Loading 0:  32%|███▏      | 233/723 [00:16<00:14, 34.61it/s]
Loading 0:  33%|███▎      | 238/723 [00:16<00:12, 37.62it/s]
Loading 0:  34%|███▎      | 243/723 [00:16<00:17, 27.17it/s]
Loading 0:  34%|███▍      | 248/723 [00:16<00:16, 29.49it/s]
Loading 0:  35%|███▌      | 256/723 [00:16<00:12, 38.08it/s]
Loading 0:  36%|███▋      | 263/723 [00:17<00:10, 43.33it/s]
Loading 0:  37%|███▋      | 269/723 [00:26<03:41,  2.05it/s]
Loading 0:  38%|███▊      | 274/723 [00:27<02:45,  2.71it/s]
Loading 0:  39%|███▉      | 282/723 [00:27<01:45,  4.18it/s]
Loading 0:  40%|███▉      | 287/723 [00:27<01:20,  5.39it/s]
Loading 0:  41%|████      | 294/723 [00:27<00:59,  7.25it/s]
Loading 0:  41%|████      | 298/723 [00:27<00:49,  8.65it/s]
Loading 0:  42%|████▏     | 302/723 [00:27<00:40, 10.42it/s]
Loading 0:  43%|████▎     | 310/723 [00:27<00:26, 15.77it/s]
Loading 0:  44%|████▍     | 320/723 [00:28<00:20, 19.29it/s]
Loading 0:  45%|████▍     | 325/723 [00:28<00:18, 21.42it/s]
Loading 0:  46%|████▌     | 329/723 [00:28<00:17, 23.07it/s]
Loading 0:  47%|████▋     | 337/723 [00:28<00:12, 30.91it/s]
Loading 0:  48%|████▊     | 344/723 [00:28<00:14, 26.77it/s]
Loading 0:  48%|████▊     | 348/723 [00:29<00:13, 27.45it/s]
Loading 0:  49%|████▉     | 355/723 [00:29<00:10, 34.24it/s]
Loading 0:  50%|█████     | 362/723 [00:29<00:08, 40.40it/s]
Loading 0:  51%|█████     | 368/723 [00:29<00:11, 30.71it/s]
Loading 0:  52%|█████▏    | 373/723 [00:29<00:10, 32.59it/s]
Loading 0:  53%|█████▎    | 381/723 [00:29<00:08, 40.26it/s]
Loading 0:  53%|█████▎    | 386/723 [00:29<00:08, 41.69it/s]
Loading 0:  54%|█████▍    | 394/723 [00:30<00:10, 32.64it/s]
Loading 0:  55%|█████▌    | 399/723 [00:30<00:09, 34.05it/s]
Loading 0:  56%|█████▌    | 404/723 [00:39<02:34,  2.06it/s]
Loading 0:  57%|█████▋    | 410/723 [00:39<01:47,  2.91it/s]
Loading 0:  58%|█████▊    | 420/723 [00:39<01:04,  4.71it/s]
Loading 0:  59%|█████▊    | 424/723 [00:40<00:54,  5.50it/s]
Loading 0:  59%|█████▉    | 428/723 [00:40<00:43,  6.71it/s]
Loading 0:  60%|██████    | 436/723 [00:40<00:28, 10.23it/s]
Loading 0:  62%|██████▏   | 446/723 [00:40<00:20, 13.72it/s]
Loading 0:  62%|██████▏   | 450/723 [00:40<00:17, 15.18it/s]
Loading 0:  63%|██████▎   | 455/723 [00:41<00:15, 17.75it/s]
Loading 0:  64%|██████▍   | 463/723 [00:41<00:10, 24.30it/s]
Loading 0:  65%|██████▌   | 470/723 [00:41<00:10, 23.29it/s]
Loading 0:  66%|██████▌   | 474/723 [00:41<00:10, 24.54it/s]
Loading 0:  67%|██████▋   | 481/723 [00:41<00:07, 31.02it/s]
Loading 0:  67%|██████▋   | 488/723 [00:41<00:06, 37.05it/s]
Loading 0:  68%|██████▊   | 494/723 [00:42<00:07, 29.06it/s]
Loading 0:  69%|██████▉   | 499/723 [00:42<00:07, 31.15it/s]
Loading 0:  70%|███████   | 507/723 [00:42<00:05, 39.34it/s]
Loading 0:  71%|███████   | 512/723 [00:42<00:05, 39.64it/s]
Loading 0:  72%|███████▏  | 520/723 [00:42<00:06, 32.14it/s]
Loading 0:  73%|███████▎  | 525/723 [00:42<00:05, 33.10it/s]
Loading 0:  73%|███████▎  | 530/723 [00:43<00:05, 35.92it/s]
Loading 0:  74%|███████▍  | 536/723 [00:43<00:04, 37.91it/s]
Loading 0:  75%|███████▍  | 541/723 [00:52<01:34,  1.92it/s]
Loading 0:  76%|███████▌  | 546/723 [00:52<01:10,  2.50it/s]
Loading 0:  76%|███████▌  | 549/723 [00:53<00:58,  3.00it/s]
Loading 0:  77%|███████▋  | 554/723 [00:53<00:40,  4.21it/s]
Loading 0:  78%|███████▊  | 562/723 [00:53<00:23,  6.90it/s]
Loading 0:  79%|███████▉  | 572/723 [00:53<00:14, 10.08it/s]
Loading 0:  80%|███████▉  | 576/723 [00:53<00:12, 11.62it/s]
Loading 0:  80%|████████  | 581/723 [00:54<00:10, 14.10it/s]
Loading 0:  81%|████████▏ | 589/723 [00:54<00:06, 20.07it/s]
Loading 0:  82%|████████▏ | 596/723 [00:54<00:06, 19.76it/s]
Loading 0:  83%|████████▎ | 600/723 [00:54<00:05, 21.33it/s]
Loading 0:  84%|████████▍ | 607/723 [00:54<00:04, 27.48it/s]
Loading 0:  85%|████████▍ | 614/723 [00:54<00:03, 33.35it/s]
Loading 0:  86%|████████▌ | 620/723 [00:55<00:03, 26.16it/s]
Loading 0:  86%|████████▋ | 625/723 [00:55<00:03, 28.48it/s]
Loading 0:  88%|████████▊ | 633/723 [00:55<00:02, 36.47it/s]
Loading 0:  88%|████████▊ | 638/723 [00:55<00:02, 38.82it/s]
Loading 0:  89%|████████▉ | 646/723 [00:55<00:02, 29.79it/s]
Loading 0:  90%|█████████ | 651/723 [00:56<00:02, 31.56it/s]
Loading 0:  91%|█████████ | 656/723 [00:56<00:01, 34.79it/s]
Loading 0:  92%|█████████▏| 662/723 [00:56<00:01, 37.03it/s]
Loading 0:  93%|█████████▎| 672/723 [00:56<00:01, 32.64it/s]
Loading 0:  93%|█████████▎| 676/723 [00:56<00:01, 31.24it/s]
Loading 0:  94%|█████████▍| 680/723 [01:06<00:23,  1.85it/s]
Loading 0:  95%|█████████▌| 688/723 [01:06<00:11,  2.96it/s]
Loading 0:  97%|█████████▋| 698/723 [01:06<00:05,  4.62it/s]
Loading 0:  97%|█████████▋| 702/723 [01:07<00:03,  5.42it/s]
Loading 0:  98%|█████████▊| 706/723 [01:07<00:02,  6.63it/s]
Loading 0:  99%|█████████▉| 714/723 [01:07<00:00, 10.05it/s]
Loading 0:  99%|█████████▉| 719/723 [01:07<00:00, 12.57it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-6533-v1-mkmlizer: quantized model in 88.892s
neversleep-llama-3-lumim-6533-v1-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS in 305.700s
neversleep-llama-3-lumim-6533-v1-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-6533-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-6533-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/tokenizer_config.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/special_tokens_map.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/tokenizer.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/config.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.5.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.0.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.3.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.2.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.4.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-6533-v1/flywheel_model.1.safetensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-6533-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.
neversleep-llama-3-lumim-6533-v1-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-6533-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.
neversleep-llama-3-lumim-6533-v1-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-6533-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.
neversleep-llama-3-lumim-6533-v1-mkmlizer:   warnings.warn(
neversleep-llama-3-lumim-6533-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()
neversleep-llama-3-lumim-6533-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-6533-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-6533-v1-mkmlizer: Saving duration: 0.264s
neversleep-llama-3-lumim-6533-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.021s
neversleep-llama-3-lumim-6533-v1-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-6533-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-llama-3-lumim-6533-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/tokenizer_config.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/config.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/merges.txt
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/vocab.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/tokenizer.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/special_tokens_map.json
neversleep-llama-3-lumim-6533-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-6533-v1_reward/reward.tensors
Job neversleep-llama-3-lumim-6533-v1-mkmlizer completed after 350.33s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-6533-v1-mkmlizer
Pipeline stage MKMLizer completed in 353.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-6533-v1
Waiting for inference service neversleep-llama-3-lumim-6533-v1 to be ready
Inference service neversleep-llama-3-lumim-6533-v1 ready after 80.41788339614868s
Pipeline stage ISVCDeployer completed in 87.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.073967218399048s
Received healthy response to inference request in 4.105341196060181s
Received healthy response to inference request in 4.060638904571533s
Received healthy response to inference request in 4.08566689491272s
Received healthy response to inference request in 4.084350347518921s
5 requests
0 failed requests
5th percentile: 4.065381193161011
10th percentile: 4.070123481750488
20th percentile: 4.079608058929443
30th percentile: 4.08461365699768
40th percentile: 4.0851402759552
50th percentile: 4.08566689491272
60th percentile: 4.093536615371704
70th percentile: 4.1014063358306885
80th percentile: 4.299066400527955
90th percentile: 4.686516809463501
95th percentile: 4.880242013931274
99th percentile: 5.035222177505493
mean time: 4.2819929122924805
Pipeline stage StressChecker completed in 22.19s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-llama-3-lumim_6533_v1 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_6533_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_6533_v1
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-6533-v1 is running
Tearing down inference service neversleep-llama-3-lumim-6533-v1
Toredown service neversleep-llama-3-lumim-6533-v1
Pipeline stage ISVCDeleter completed in 5.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-6533-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
admin requested tearing down of sao10k-l3-rp-v2_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v2-v1 is running
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
admin requested tearing down of thetsar1209-llama3-carp-v0-4_v5
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Running pipeline stage ISVCDeleter
Tearing down inference service sao10k-l3-rp-v2-v1
Checking if service thetsar1209-llama3-carp-v0-4-v5 is running
Toredown service sao10k-l3-rp-v2-v1
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Pipeline stage ISVCDeleter completed in 4.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v2-v1/tokenizer.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-6533-v1_reward/config.json from bucket guanaco-reward-models
Cleaning model data from model cache
Tearing down inference service thetsar1209-llama3-carp-v0-4-v5
Deleting key neversleep-llama-3-lumim-6533-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-v1_reward/config.json from bucket guanaco-reward-models
Toredown service thetsar1209-llama3-carp-v0-4-v5
Deleting key neversleep-llama-3-lumim-6533-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6533-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Pipeline stage ISVCDeleter completed in 5.01s
Deleting key sao10k-l3-rp-v2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6533-v1_reward/tokenizer.json from bucket guanaco-reward-models
Running pipeline stage MKMLModelDeleter
Deleting key sao10k-l3-rp-v2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-6533-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Cleaning model data from S3
Deleting key neversleep-llama-3-lumim-6533-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 10.97s
Deleting key thetsar1209-llama3-carp-v0-4-v5/config.json from bucket guanaco-mkml-models
neversleep-llama-3-lumim_6533_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 5.34s
Deleting key thetsar1209-llama3-carp-v0-4-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models