submission_id: neversleep-llama-3-lumim_8244_v1
developer_uid: Meliodia
best_of: 4
celo_rating: 1180.87
display_name: neversleep70B
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: True
language_model: NeverSleep/Llama-3-Lumimaid-70B-v0.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: NeverSleep/Llama-3-Lumim
model_name: neversleep70B
model_num_parameters: 70553706496.0
model_repo: NeverSleep/Llama-3-Lumimaid-70B-v0.1
model_size: 71B
num_battles: 111864
num_wins: 54748
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: 2024-05-19T14:25:55+00:00
us_pacific_date: 2024-05-19
win_ratio: 0.48941571908746334
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-8244-v1-mkmlizer
Waiting for job on neversleep-llama-3-lumim-8244-v1-mkmlizer to finish
neversleep-llama-3-lumim-8244-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ _____ __ __ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ /___/ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ Version: 0.8.14 ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ https://mk1.ai ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ belonging to: ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ Chai Research Corp. ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-8244-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-8244-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-8244-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-8244-v1-mkmlizer: Downloaded to shared memory in 271.941s
neversleep-llama-3-lumim-8244-v1-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-8244-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-8244-v1-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 1%| | 4/723 [00:00<00:20, 35.87it/s] Loading 0: 1%|▏ | 10/723 [00:00<00:14, 48.85it/s] Loading 0: 2%|▏ | 16/723 [00:00<00:26, 26.51it/s] Loading 0: 3%|▎ | 20/723 [00:00<00:24, 28.70it/s] Loading 0: 3%|▎ | 24/723 [00:00<00:26, 26.79it/s] Loading 0: 4%|▍ | 31/723 [00:00<00:20, 33.27it/s] Loading 0: 5%|▌ | 38/723 [00:01<00:16, 41.56it/s] Loading 0: 6%|▌ | 43/723 [00:01<00:23, 28.78it/s] Loading 0: 7%|▋ | 47/723 [00:01<00:22, 29.81it/s] Loading 0: 7%|▋ | 51/723 [00:01<00:24, 27.81it/s] Loading 0: 8%|▊ | 58/723 [00:01<00:19, 33.42it/s] Loading 0: 9%|▉ | 65/723 [00:01<00:16, 41.09it/s] Loading 0: 10%|▉ | 70/723 [00:02<00:24, 26.70it/s] Loading 0: 10%|█ | 75/723 [00:02<00:22, 29.14it/s] Loading 0: 11%|█ | 79/723 [00:02<00:21, 29.88it/s] Loading 0: 12%|█▏ | 85/723 [00:02<00:19, 32.94it/s] Loading 0: 13%|█▎ | 91/723 [00:02<00:16, 38.52it/s] Loading 0: 13%|█▎ | 96/723 [00:03<00:26, 24.08it/s] Loading 0: 14%|█▍ | 103/723 [00:03<00:21, 29.30it/s] Loading 0: 15%|█▌ | 110/723 [00:03<00:18, 33.54it/s] Loading 0: 16%|█▌ | 116/723 [00:03<00:22, 27.30it/s] Loading 0: 17%|█▋ | 120/723 [00:03<00:20, 28.78it/s] Loading 0: 17%|█▋ | 124/723 [00:04<00:20, 29.59it/s] Loading 0: 18%|█▊ | 128/723 [00:19<10:16, 1.04s/it] Loading 0: 18%|█▊ | 130/723 [00:20<08:44, 1.13it/s] Loading 0: 19%|█▉ | 137/723 [00:20<04:59, 1.96it/s] Loading 0: 20%|█▉ | 142/723 [00:20<03:36, 2.68it/s] Loading 0: 20%|██ | 145/723 [00:20<02:56, 3.27it/s] Loading 0: 20%|██ | 148/723 [00:20<02:20, 4.09it/s] Loading 0: 22%|██▏ | 156/723 [00:20<01:18, 7.19it/s] Loading 0: 22%|██▏ | 160/723 [00:21<01:02, 8.94it/s] Loading 0: 23%|██▎ | 168/723 [00:21<00:44, 12.41it/s] Loading 0: 24%|██▍ | 172/723 [00:21<00:39, 13.88it/s] Loading 0: 24%|██▍ | 175/723 [00:21<00:35, 15.38it/s] Loading 0: 25%|██▌ | 181/723 [00:21<00:25, 21.00it/s] Loading 0: 26%|██▌ | 185/723 [00:21<00:24, 21.69it/s] Loading 0: 27%|██▋ | 194/723 [00:22<00:21, 24.86it/s] Loading 0: 27%|██▋ | 198/723 [00:22<00:21, 24.45it/s] Loading 0: 28%|██▊ | 202/723 [00:22<00:20, 25.92it/s] Loading 0: 29%|██▉ | 208/723 [00:22<00:16, 32.06it/s] Loading 0: 29%|██▉ | 212/723 [00:22<00:17, 29.74it/s] Loading 0: 30%|███ | 218/723 [00:23<00:19, 26.04it/s] Loading 0: 31%|███ | 222/723 [00:23<00:19, 25.11it/s] Loading 0: 32%|███▏ | 229/723 [00:23<00:16, 30.59it/s] Loading 0: 33%|███▎ | 236/723 [00:23<00:14, 34.63it/s] Loading 0: 33%|███▎ | 242/723 [00:23<00:17, 27.40it/s] Loading 0: 34%|███▍ | 246/723 [00:24<00:16, 28.84it/s] Loading 0: 35%|███▍ | 250/723 [00:24<00:15, 29.62it/s] Loading 0: 35%|███▌ | 256/723 [00:24<00:14, 32.74it/s] Loading 0: 36%|███▌ | 262/723 [00:24<00:12, 38.41it/s] Loading 0: 36%|███▋ | 263/723 [00:40<00:11, 38.41it/s] Loading 0: 37%|███▋ | 264/723 [00:40<08:33, 1.12s/it] Loading 0: 37%|███▋ | 268/723 [00:40<06:18, 1.20it/s] Loading 0: 38%|███▊ | 272/723 [00:41<04:33, 1.65it/s] Loading 0: 38%|███▊ | 276/723 [00:41<03:18, 2.25it/s] Loading 0: 39%|███▉ | 283/723 [00:41<01:57, 3.76it/s] Loading 0: 40%|████ | 291/723 [00:41<01:10, 6.10it/s] Loading 0: 41%|████ | 296/723 [00:41<00:59, 7.18it/s] Loading 0: 41%|████▏ | 300/723 [00:42<00:48, 8.81it/s] Loading 0: 42%|████▏ | 304/723 [00:42<00:38, 10.79it/s] Loading 0: 43%|████▎ | 310/723 [00:42<00:28, 14.58it/s] Loading 0: 44%|████▍ | 318/723 [00:42<00:18, 21.33it/s] Loading 0: 45%|████▍ | 323/723 [00:42<00:22, 17.76it/s] Loading 0: 45%|████▌ | 328/723 [00:42<00:18, 20.88it/s] Loading 0: 46%|████▋ | 336/723 [00:43<00:14, 27.28it/s] Loading 0: 47%|████▋ | 341/723 [00:43<00:13, 29.25it/s] Loading 0: 48%|████▊ | 346/723 [00:43<00:16, 22.37it/s] Loading 0: 49%|████▉ | 354/723 [00:43<00:12, 28.66it/s] Loading 0: 50%|████▉ | 358/723 [00:43<00:12, 29.33it/s] Loading 0: 50%|█████ | 363/723 [00:44<00:11, 30.50it/s] Loading 0: 51%|█████ | 368/723 [00:44<00:13, 25.66it/s] Loading 0: 51%|█████▏ | 372/723 [00:44<00:12, 27.60it/s] Loading 0: 52%|█████▏ | 376/723 [00:44<00:12, 28.83it/s] Loading 0: 53%|█████▎ | 382/723 [00:44<00:10, 32.41it/s] Loading 0: 54%|█████▍ | 389/723 [00:44<00:09, 36.52it/s] Loading 0: 54%|█████▍ | 394/723 [00:45<00:11, 29.08it/s] Loading 0: 55%|█████▌ | 398/723 [00:45<00:10, 30.14it/s] Loading 0: 55%|█████▌ | 400/723 [01:01<00:10, 30.14it/s] Loading 0: 55%|█████▌ | 401/723 [01:01<06:04, 1.13s/it] Loading 0: 57%|█████▋ | 409/723 [01:01<03:22, 1.55it/s] Loading 0: 58%|█████▊ | 417/723 [01:01<02:02, 2.49it/s] Loading 0: 58%|█████▊ | 422/723 [01:02<01:37, 3.10it/s] Loading 0: 59%|█████▉ | 426/723 [01:02<01:16, 3.90it/s] Loading 0: 59%|█████▉ | 430/723 [01:02<00:58, 4.98it/s] Loading 0: 60%|██████ | 436/723 [01:02<00:40, 7.13it/s] Loading 0: 61%|██████▏ | 444/723 [01:02<00:25, 11.06it/s] Loading 0: 62%|██████▏ | 449/723 [01:03<00:24, 11.39it/s] Loading 0: 63%|██████▎ | 454/723 [01:03<00:19, 14.09it/s] Loading 0: 64%|██████▍ | 462/723 [01:03<00:13, 19.57it/s] Loading 0: 65%|██████▍ | 467/723 [01:03<00:11, 22.26it/s] Loading 0: 65%|██████▌ | 472/723 [01:03<00:13, 18.93it/s] Loading 0: 66%|██████▋ | 480/723 [01:03<00:09, 25.02it/s] Loading 0: 67%|██████▋ | 484/723 [01:04<00:09, 26.34it/s] Loading 0: 68%|██████▊ | 489/723 [01:04<00:08, 28.36it/s] Loading 0: 68%|██████▊ | 494/723 [01:04<00:09, 24.71it/s] Loading 0: 69%|██████▉ | 498/723 [01:04<00:08, 26.65it/s] Loading 0: 69%|██████▉ | 502/723 [01:04<00:07, 28.16it/s] Loading 0: 70%|███████ | 508/723 [01:04<00:06, 31.72it/s] Loading 0: 71%|███████ | 515/723 [01:05<00:05, 35.80it/s] Loading 0: 72%|███████▏ | 520/723 [01:05<00:07, 28.73it/s] Loading 0: 72%|███████▏ | 524/723 [01:05<00:06, 29.93it/s] Loading 0: 73%|███████▎ | 528/723 [01:05<00:06, 28.03it/s] Loading 0: 74%|███████▍ | 535/723 [01:05<00:05, 33.42it/s] Loading 0: 75%|███████▍ | 540/723 [01:22<00:05, 33.42it/s] Loading 0: 75%|███████▍ | 541/723 [01:22<02:44, 1.11it/s] Loading 0: 76%|███████▌ | 546/723 [01:22<01:58, 1.49it/s] Loading 0: 76%|███████▌ | 549/723 [01:22<01:36, 1.80it/s] Loading 0: 76%|███████▋ | 553/723 [01:22<01:10, 2.42it/s] Loading 0: 78%|███████▊ | 561/723 [01:22<00:39, 4.12it/s] Loading 0: 78%|███████▊ | 565/723 [01:23<00:30, 5.20it/s] Loading 0: 79%|███████▉ | 572/723 [01:23<00:20, 7.32it/s] Loading 0: 80%|███████▉ | 576/723 [01:23<00:16, 8.70it/s] Loading 0: 80%|████████ | 580/723 [01:23<00:13, 10.63it/s] Loading 0: 81%|████████▏ | 588/723 [01:23<00:08, 15.92it/s] Loading 0: 82%|████████▏ | 592/723 [01:23<00:07, 18.09it/s] Loading 0: 82%|████████▏ | 596/723 [01:24<00:07, 17.10it/s] Loading 0: 83%|████████▎ | 599/723 [01:24<00:07, 17.18it/s] Loading 0: 84%|████████▍ | 607/723 [01:24<00:04, 24.59it/s] Loading 0: 85%|████████▍ | 614/723 [01:24<00:03, 29.62it/s] Loading 0: 86%|████████▌ | 620/723 [01:25<00:04, 24.84it/s] Loading 0: 86%|████████▋ | 624/723 [01:25<00:03, 26.62it/s] Loading 0: 87%|████████▋ | 628/723 [01:25<00:03, 27.95it/s] Loading 0: 88%|████████▊ | 634/723 [01:25<00:02, 31.47it/s] Loading 0: 89%|████████▊ | 641/723 [01:25<00:02, 35.85it/s] Loading 0: 89%|████████▉ | 646/723 [01:25<00:02, 28.53it/s] Loading 0: 90%|████████▉ | 650/723 [01:25<00:02, 29.74it/s] Loading 0: 90%|█████████ | 654/723 [01:26<00:02, 27.91it/s] Loading 0: 91%|█████████▏| 661/723 [01:26<00:01, 33.54it/s] Loading 0: 92%|█████████▏| 668/723 [01:26<00:01, 41.16it/s] Loading 0: 93%|█████████▎| 673/723 [01:26<00:01, 28.77it/s] Loading 0: 94%|█████████▎| 677/723 [01:26<00:01, 29.78it/s] Loading 0: 94%|█████████▍| 678/723 [01:42<00:01, 29.78it/s] Loading 0: 94%|█████████▍| 679/723 [01:42<00:52, 1.19s/it] Loading 0: 95%|█████████▌| 687/723 [01:43<00:23, 1.51it/s] Loading 0: 96%|█████████▌| 692/723 [01:43<00:14, 2.09it/s] Loading 0: 97%|█████████▋| 698/723 [01:43<00:08, 2.93it/s] Loading 0: 97%|█████████▋| 702/723 [01:43<00:05, 3.69it/s] Loading 0: 98%|█████████▊| 706/723 [01:43<00:03, 4.76it/s] Loading 0: 98%|█████████▊| 712/723 [01:44<00:01, 7.05it/s] Loading 0: 99%|█████████▉| 716/723 [01:44<00:00, 8.58it/s] Loading 0: 100%|█████████▉| 722/723 [01:54<00:00, 8.58it/s] Loading 0: 100%|██████████| 723/723 [01:54<00:00, 1.57it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-8244-v1-mkmlizer: quantized model in 130.370s
neversleep-llama-3-lumim-8244-v1-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-70B-v0.1 in 423.780s
neversleep-llama-3-lumim-8244-v1-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-8244-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-8244-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/config.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/special_tokens_map.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/tokenizer_config.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/tokenizer.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.5.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.0.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.3.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.4.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.2.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-8244-v1/flywheel_model.1.safetensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-8244-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-8244-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8244-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-8244-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8244-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-8244-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-8244-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-8244-v1-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-8244-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-8244-v1-mkmlizer: Saving duration: 0.381s
neversleep-llama-3-lumim-8244-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.289s
neversleep-llama-3-lumim-8244-v1-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-8244-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-llama-3-lumim-8244-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/config.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/special_tokens_map.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/tokenizer_config.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/merges.txt
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/vocab.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/tokenizer.json
neversleep-llama-3-lumim-8244-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-8244-v1_reward/reward.tensors
Job neversleep-llama-3-lumim-8244-v1-mkmlizer completed after 484.92s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-8244-v1-mkmlizer
Pipeline stage MKMLizer completed in 487.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-8244-v1
Waiting for inference service neversleep-llama-3-lumim-8244-v1 to be ready
Inference service neversleep-llama-3-lumim-8244-v1 ready after 90.4375102519989s
Pipeline stage ISVCDeployer completed in 97.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.185447454452515s
Received healthy response to inference request in 1.5957016944885254s
Received healthy response to inference request in 3.741309404373169s
Received healthy response to inference request in 2.159327983856201s
Received healthy response to inference request in 1.8371942043304443s
5 requests
0 failed requests
5th percentile: 1.644000196456909
10th percentile: 1.692298698425293
20th percentile: 1.7888957023620606
30th percentile: 1.9016209602355958
40th percentile: 2.0304744720458983
50th percentile: 2.159327983856201
60th percentile: 2.792120552062988
70th percentile: 3.424913120269775
80th percentile: 4.030137014389038
90th percentile: 4.607792234420776
95th percentile: 4.896619844436645
99th percentile: 5.127681932449341
mean time: 2.903796148300171
Pipeline stage StressChecker completed in 15.56s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-llama-3-lumim_8244_v1 status is now deployed due to DeploymentManager action
neversleep-llama-3-lumim_8244_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-llama-3-lumim_8244_v1
Running pipeline stage ISVCDeleter
Checking if service neversleep-llama-3-lumim-8244-v1 is running
Tearing down inference service neversleep-llama-3-lumim-8244-v1
Toredown service neversleep-llama-3-lumim-8244-v1
Pipeline stage ISVCDeleter completed in 4.07s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-8244-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-llama-3-lumim-8244-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-llama-3-lumim-8244-v1_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-llama-3-lumim-8244-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.50s
neversleep-llama-3-lumim_8244_v1 status is now torndown due to DeploymentManager action