alkahestry-pointer-mist

developer_uid: alkacchi
submission_id: alkahestry-pointer-mist_v36
model_name: pointer-mist-rw2
model_group: alkahestry/pointer-mist
status: torndown
timestamp: 2024-01-10T12:49:42+00:00
num_battles: 21299
num_wins: 9418
celo_rating: 1110.92
family_friendly_score: 0.0
submission_type: basic
model_repo: alkahestry/pointer-mist
reward_repo: alkahestry/gpt2-reward-rp
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: pointer-mist-rw2
is_internal_developer: False
language_model: alkahestry/pointer-mist
model_size: NoneB
ranking_group: single
us_pacific_date: 2024-01-10
win_ratio: 0.44218038405558946
generation_params: {'temperature': 1.0, 'top_p': 0.73, 'min_p': 0.0, 'top_k': 1000, 'presence_penalty': 0.24, 'frequency_penalty': 0.8, 'stopping_words': ['</s>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\n\nAs the assistant, your task is to fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}\n", 'prompt_template': '{prompt}\n\n', 'bot_template': '### Response:\n\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n\n{user_name}: {message}\n\n', 'response_template': '### Response:\n\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-pointer-mist-v36-mkmlizer
Waiting for job on alkahestry-pointer-mist-v36-mkmlizer to finish
Stopping job with name alkahestry-pointer-mist-v36-mkmlizer
%s, retrying in %s seconds...
Starting job with name alkahestry-pointer-mist-v36-mkmlizer
Waiting for job on alkahestry-pointer-mist-v36-mkmlizer to finish
Stopping job with name alkahestry-pointer-mist-v36-mkmlizer
%s, retrying in %s seconds...
Starting job with name alkahestry-pointer-mist-v36-mkmlizer
Waiting for job on alkahestry-pointer-mist-v36-mkmlizer to finish
alkahestry-pointer-mist-v36-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-pointer-mist-v36-mkmlizer: ║   _______ __  __ _______ _____                                      ║
alkahestry-pointer-mist-v36-mkmlizer: ║  |   |   |  |/  |   |   |     |_                                    ║
alkahestry-pointer-mist-v36-mkmlizer: ║  |       |     <|       |       |                                   ║
alkahestry-pointer-mist-v36-mkmlizer: ║  |__|_|__|__|\__|__|_|__|_______|                                   ║
alkahestry-pointer-mist-v36-mkmlizer: ║                                                                     ║
alkahestry-pointer-mist-v36-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alkahestry-pointer-mist-v36-mkmlizer: ║                                                                     ║
alkahestry-pointer-mist-v36-mkmlizer: ║  The license key for the current software has been verified as      ║
alkahestry-pointer-mist-v36-mkmlizer: ║  belonging to:                                                      ║
alkahestry-pointer-mist-v36-mkmlizer: ║                                                                     ║
alkahestry-pointer-mist-v36-mkmlizer: ║  Chai Research Corp.                                                ║
alkahestry-pointer-mist-v36-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alkahestry-pointer-mist-v36-mkmlizer: ║  Expiration: 2024-04-15 23:59:59                                    ║
alkahestry-pointer-mist-v36-mkmlizer: ║                                                                     ║
alkahestry-pointer-mist-v36-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-pointer-mist-v36-mkmlizer: loading model from alkahestry/pointer-mist
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
config.json:   0%|          | 0.00/680 [00:00<?, ?B/s]
config.json: 100%|██████████| 680/680 [00:00<00:00, 5.92MB/s]
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/1.14k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.14k/1.14k [00:00<00:00, 16.7MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 12.3MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 2.84MB/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 2.84MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
added_tokens.json:   0%|          | 0.00/60.0 [00:00<?, ?B/s]
added_tokens.json: 100%|██████████| 60.0/60.0 [00:00<00:00, 946kB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/96.0 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 96.0/96.0 [00:00<00:00, 786kB/s]
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model.bin.index.json:   0%|          | 0.00/29.9k [00:00<?, ?B/s]
pytorch_model.bin.index.json: 100%|██████████| 29.9k/29.9k [00:00<00:00, 190MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
Downloading shards:   0%|          | 0/3 [00:00<?, ?it/s]
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   0%|          | 0.00/9.95G [00:00<?, ?B/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   0%|          | 10.5M/9.95G [00:00<15:47, 10.5MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   0%|          | 21.0M/9.95G [00:01<07:55, 20.9MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   0%|          | 31.5M/9.95G [00:01<05:23, 30.6MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   1%|          | 62.9M/9.95G [00:01<02:14, 73.6MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   1%|          | 115M/9.95G [00:01<01:03, 154MB/s]  [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   1%|▏         | 147M/9.95G [00:01<00:56, 173MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   2%|▏         | 199M/9.95G [00:01<00:40, 238MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   5%|▍         | 493M/9.95G [00:01<00:11, 839MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   6%|▌         | 619M/9.95G [00:02<00:10, 869MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   7%|▋         | 734M/9.95G [00:02<00:10, 910MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:   9%|▉         | 891M/9.95G [00:02<00:08, 1.07GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:  91%|█████████ | 9.01G/9.95G [00:08<00:00, 1.40GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:  92%|█████████▏| 9.15G/9.95G [00:08<00:00, 1.35GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:  94%|█████████▎| 9.32G/9.95G [00:08<00:00, 1.43GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:  96%|█████████▌| 9.53G/9.95G [00:08<00:00, 1.55GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin:  98%|█████████▊| 9.76G/9.95G [00:09<00:00, 1.74GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.94G/9.95G [00:09<00:00, 1.09GB/s][A
pytorch_model-00001-of-00003.bin: 100%|█████████▉| 9.95G/9.95G [00:09<00:00, 1.05GB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
Downloading shards:  33%|███▎      | 1/3 [00:09<00:19,  9.85s/it]
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   0%|          | 0.00/9.90G [00:00<?, ?B/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   0%|          | 10.5M/9.90G [00:00<12:01, 13.7MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   0%|          | 21.0M/9.90G [00:00<05:57, 27.7MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   0%|          | 31.5M/9.90G [00:01<04:52, 33.8MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   1%|          | 62.9M/9.90G [00:01<02:03, 79.5MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   1%|▏         | 136M/9.90G [00:01<00:48, 202MB/s]  [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   3%|▎         | 273M/9.90G [00:01<00:24, 387MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   3%|▎         | 325M/9.90G [00:01<00:30, 312MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   4%|▍         | 430M/9.90G [00:01<00:22, 423MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   5%|▍         | 493M/9.90G [00:02<00:20, 457MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   6%|▌         | 556M/9.90G [00:02<00:20, 449MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   6%|▌         | 608M/9.90G [00:02<00:20, 455MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   7%|▋         | 682M/9.90G [00:02<00:18, 497MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   8%|▊         | 786M/9.90G [00:02<00:16, 546MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:   9%|▊         | 849M/9.90G [00:02<00:16, 540MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  10%|▉         | 986M/9.90G [00:02<00:12, 724MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  11%|█         | 1.07G/9.90G [00:02<00:12, 683MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  12%|█▏        | 1.14G/9.90G [00:03<00:14, 584MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  13%|█▎        | 1.28G/9.90G [00:03<00:11, 750MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  17%|█▋        | 1.73G/9.90G [00:03<00:04, 1.66GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  19%|█▉        | 1.93G/9.90G [00:03<00:05, 1.50GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  21%|██▏       | 2.11G/9.90G [00:03<00:07, 1.01GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  23%|██▎       | 2.24G/9.90G [00:03<00:07, 1.01GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  24%|██▍       | 2.37G/9.90G [00:04<00:07, 994MB/s] [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  25%|██▌       | 2.50G/9.90G [00:04<00:08, 849MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  27%|██▋       | 2.72G/9.90G [00:04<00:07, 989MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  29%|██▊       | 2.83G/9.90G [00:04<00:07, 1.00GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  30%|██▉       | 2.95G/9.90G [00:04<00:06, 998MB/s] [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  31%|███       | 3.06G/9.90G [00:04<00:07, 931MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  32%|███▏      | 3.17G/9.90G [00:04<00:07, 902MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  34%|███▍      | 3.39G/9.90G [00:05<00:05, 1.20GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  37%|███▋      | 3.63G/9.90G [00:05<00:04, 1.50GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  38%|███▊      | 3.80G/9.90G [00:05<00:03, 1.53GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  40%|████      | 3.96G/9.90G [00:05<00:04, 1.27GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  42%|████▏     | 4.11G/9.90G [00:05<00:04, 1.23GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  43%|████▎     | 4.25G/9.90G [00:05<00:04, 1.18GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  44%|████▍     | 4.37G/9.90G [00:05<00:04, 1.15GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  46%|████▌     | 4.51G/9.90G [00:05<00:04, 1.18GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  48%|████▊     | 4.72G/9.90G [00:06<00:03, 1.40GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  49%|████▉     | 4.87G/9.90G [00:06<00:04, 1.21GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  51%|█████     | 5.00G/9.90G [00:06<00:04, 1.16GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  53%|█████▎    | 5.23G/9.90G [00:06<00:03, 1.44GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  56%|█████▌    | 5.51G/9.90G [00:06<00:02, 1.71GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  57%|█████▋    | 5.68G/9.90G [00:06<00:02, 1.67GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  59%|█████▉    | 5.86G/9.90G [00:06<00:03, 1.30GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  61%|██████    | 6.01G/9.90G [00:06<00:03, 1.30GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  62%|██████▏   | 6.16G/9.90G [00:07<00:02, 1.26GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  64%|██████▎   | 6.29G/9.90G [00:07<00:02, 1.22GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  65%|██████▍   | 6.43G/9.90G [00:07<00:03, 895MB/s] [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  66%|██████▌   | 6.53G/9.90G [00:07<00:03, 875MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  68%|██████▊   | 6.71G/9.90G [00:07<00:02, 1.07GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  70%|███████   | 6.94G/9.90G [00:07<00:02, 1.35GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  73%|███████▎  | 7.18G/9.90G [00:07<00:01, 1.58GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  75%|███████▌  | 7.47G/9.90G [00:08<00:01, 1.81GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  77%|███████▋  | 7.67G/9.90G [00:08<00:01, 1.65GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  79%|███████▉  | 7.84G/9.90G [00:08<00:01, 1.47GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00002-of-00003.bin:  81%|████████  | 8.02G/9.90G [00:08<00:01, 1.54GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   4%|▎         | 220M/6.18G [00:01<00:26, 225MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   4%|▍         | 262M/6.18G [00:01<00:23, 250MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   5%|▍         | 304M/6.18G [00:02<00:27, 216MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   6%|▌         | 357M/6.18G [00:02<00:22, 264MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   6%|▋         | 398M/6.18G [00:02<00:20, 281MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   7%|▋         | 440M/6.18G [00:02<00:18, 304MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:   8%|▊         | 503M/6.18G [00:02<00:15, 368MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  10%|▉         | 608M/6.18G [00:02<00:10, 527MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  11%|█         | 671M/6.18G [00:03<00:15, 363MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  12%|█▏        | 724M/6.18G [00:03<00:14, 365MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  13%|█▎        | 797M/6.18G [00:03<00:12, 434MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  21%|██        | 1.30G/6.18G [00:03<00:03, 1.46GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  27%|██▋       | 1.65G/6.18G [00:03<00:02, 1.94GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  31%|███       | 1.89G/6.18G [00:04<00:05, 826MB/s] [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  33%|███▎      | 2.07G/6.18G [00:04<00:05, 816MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  36%|███▌      | 2.21G/6.18G [00:04<00:04, 814MB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  41%|████      | 2.52G/6.18G [00:04<00:03, 1.14GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  44%|████▍     | 2.71G/6.18G [00:04<00:03, 1.00GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  46%|████▋     | 2.86G/6.18G [00:05<00:03, 943MB/s] [A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  51%|█████     | 3.12G/6.18G [00:05<00:02, 1.21GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  53%|█████▎    | 3.29G/6.18G [00:05<00:02, 1.18GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  56%|█████▋    | 3.48G/6.18G [00:05<00:02, 1.29GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  59%|█████▉    | 3.64G/6.18G [00:05<00:02, 1.22GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  63%|██████▎   | 3.87G/6.18G [00:05<00:01, 1.44GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  65%|██████▌   | 4.04G/6.18G [00:05<00:01, 1.38GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  68%|██████▊   | 4.22G/6.18G [00:06<00:01, 1.47GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  71%|███████   | 4.38G/6.18G [00:06<00:01, 1.16GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  73%|███████▎  | 4.52G/6.18G [00:06<00:01, 1.14GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  75%|███████▌  | 4.65G/6.18G [00:06<00:01, 1.13GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  78%|███████▊  | 4.84G/6.18G [00:06<00:01, 1.32GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  81%|████████  | 4.99G/6.18G [00:06<00:01, 1.10GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  83%|████████▎ | 5.12G/6.18G [00:06<00:00, 1.12GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  85%|████████▍ | 5.24G/6.18G [00:07<00:00, 1.03GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  87%|████████▋ | 5.36G/6.18G [00:07<00:00, 1.02GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  90%|████████▉ | 5.55G/6.18G [00:07<00:00, 1.23GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  92%|█████████▏| 5.71G/6.18G [00:07<00:00, 1.27GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  95%|█████████▍| 5.84G/6.18G [00:07<00:00, 1.27GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin:  97%|█████████▋| 5.99G/6.18G [00:07<00:00, 1.29GB/s][A
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.17G/6.18G [00:07<00:00, 1.22GB/s][A
pytorch_model-00003-of-00003.bin: 100%|█████████▉| 6.18G/6.18G [00:07<00:00, 778MB/s] 
alkahestry-pointer-mist-v36-mkmlizer: 
Downloading shards: 100%|██████████| 3/3 [00:28<00:00,  9.29s/it]
Downloading shards: 100%|██████████| 3/3 [00:28<00:00,  9.49s/it]
alkahestry-pointer-mist-v36-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:07<00:14,  7.45s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:14<00:07,  7.04s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:18<00:00,  5.71s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:18<00:00,  6.11s/it]
alkahestry-pointer-mist-v36-mkmlizer: loaded model in 49.202s
alkahestry-pointer-mist-v36-mkmlizer: saved to disk in 82.793s
alkahestry-pointer-mist-v36-mkmlizer: quantizing model to /tmp/model_cache
alkahestry-pointer-mist-v36-mkmlizer: Saving mkml model at /tmp/model_cache
alkahestry-pointer-mist-v36-mkmlizer: Reading /tmp/tmp_ngyxklb/model.safetensors.index.json
alkahestry-pointer-mist-v36-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:02<17:14,  2.86s/it]
Profiling:   1%|          | 3/363 [00:04<07:26,  1.24s/it]
Profiling:   1%|          | 4/363 [00:05<07:41,  1.28s/it]
Profiling:   1%|▏         | 5/363 [00:06<07:51,  1.32s/it]
Profiling:   2%|▏         | 7/363 [00:07<04:57,  1.20it/s]
Profiling:   2%|▏         | 8/363 [00:08<04:35,  1.29it/s]
Profiling:   2%|▏         | 9/363 [00:08<04:18,  1.37it/s]
Profiling:   3%|▎         | 10/363 [00:09<04:01,  1.46it/s]
Profiling:   3%|▎         | 12/363 [00:10<04:00,  1.46it/s]
Profiling:   4%|▎         | 13/363 [00:12<05:00,  1.17it/s]
Profiling:   4%|▍         | 14/363 [00:13<05:50,  1.01s/it]
Profiling:   4%|▍         | 16/363 [00:14<04:06,  1.41it/s]
Profiling:   5%|▍         | 17/363 [00:14<03:59,  1.45it/s]
Profiling:   5%|▍         | 18/363 [00:15<03:51,  1.49it/s]
Profiling:   5%|▌         | 19/363 [00:16<03:45,  1.52it/s]
Profiling:   6%|▌         | 21/363 [00:17<03:51,  1.48it/s]
Profiling:   6%|▌         | 22/363 [00:18<04:46,  1.19it/s]
Profiling:   6%|▋         | 23/363 [00:20<05:28,  1.03it/s]
Profiling:   7%|▋         | 25/363 [00:20<03:54,  1.44it/s]
Profiling:   7%|▋         | 26/363 [00:21<03:46,  1.49it/s]
Profiling:   7%|▋         | 27/363 [00:21<03:37,  1.55it/s]
Profiling:   8%|▊         | 28/363 [00:22<03:40,  1.52it/s]
Profiling:   8%|▊         | 29/363 [00:23<03:34,  1.56it/s]
Profiling:   8%|▊         | 30/363 [00:23<03:26,  1.62it/s]
Profiling:   9%|▊         | 31/363 [00:24<03:24,  1.62it/s]
Profiling:   9%|▉         | 32/363 [00:25<03:23,  1.63it/s]
Profiling:   9%|▉         | 33/363 [00:25<02:33,  2.15it/s]
Profiling:   9%|▉         | 34/363 [00:26<04:03,  1.35it/s]
Profiling:  10%|▉         | 35/363 [00:27<05:10,  1.06it/s]
Profiling:  10%|▉         | 36/363 [00:29<05:59,  1.10s/it]
Profiling:  11%|█         | 39/363 [00:30<04:01,  1.34it/s]
Profiling:  11%|█         | 40/363 [00:32<04:42,  1.14it/s]
Profiling:  11%|█▏        | 41/363 [00:33<05:19,  1.01it/s]
Profiling:  12%|█▏        | 43/363 [00:34<03:48,  1.40it/s]
Profiling:  12%|█▏        | 44/363 [00:34<03:40,  1.44it/s]
Profiling:  12%|█▏        | 45/363 [00:35<03:31,  1.50it/s]
Profiling:  13%|█▎        | 46/363 [00:35<03:23,  1.56it/s]
Profiling:  13%|█▎        | 48/363 [00:37<03:31,  1.49it/s]
Profiling:  13%|█▎        | 49/363 [00:38<04:26,  1.18it/s]
Profiling:  14%|█▍        | 50/363 [00:40<05:06,  1.02it/s]
Profiling:  14%|█▍        | 52/363 [00:40<03:38,  1.42it/s]
Profiling:  15%|█▍        | 53/363 [00:41<03:32,  1.46it/s]
Profiling:  15%|█▍        | 54/363 [00:42<03:28,  1.48it/s]
Profiling:  15%|█▌        | 55/363 [00:42<03:20,  1.54it/s]
Profiling:  16%|█▌        | 57/363 [00:44<03:23,  1.50it/s]
Profiling:  16%|█▌        | 58/363 [00:45<04:11,  1.21it/s]
Profiling:  16%|█▋        | 59/363 [00:46<04:52,  1.04it/s]
Profiling:  17%|█▋        | 61/363 [00:47<03:27,  1.45it/s]
Profiling:  17%|█▋        | 62/363 [00:47<03:19,  1.51it/s]
Profiling:  17%|█▋        | 63/363 [00:48<03:14,  1.54it/s]
Profiling:  18%|█▊        | 64/363 [00:49<03:12,  1.56it/s]
Profiling:  18%|█▊        | 65/363 [00:49<03:05,  1.61it/s]
Profiling:  18%|█▊        | 66/363 [00:50<03:03,  1.62it/s]
Profiling:  18%|█▊        | 67/363 [00:50<03:02,  1.62it/s]
Profiling:  19%|█▉        | 69/363 [00:52<03:17,  1.49it/s]
Profiling:  19%|█▉        | 70/363 [00:53<04:09,  1.17it/s]
Profiling:  20%|█▉        | 71/363 [00:55<04:48,  1.01it/s]
Profiling:  20%|██        | 73/363 [00:55<03:21,  1.44it/s]
Profiling:  20%|██        | 74/363 [00:56<03:16,  1.47it/s]
Profiling:  21%|██        | 75/363 [00:57<03:08,  1.53it/s]
Profiling:  21%|██        | 76/363 [00:57<03:00,  1.59it/s]
Profiling:  21%|██        | 77/363 [00:58<02:59,  1.59it/s]
Profiling:  21%|██▏       | 78/363 [00:58<02:53,  1.65it/s]
Profiling:  22%|██▏       | 80/363 [01:00<02:57,  1.59it/s]
Profiling:  22%|██▏       | 81/363 [01:01<03:44,  1.25it/s]
Profiling:  23%|██▎       | 82/363 [01:02<04:27,  1.05it/s]
Profiling:  23%|██▎       | 84/363 [01:03<03:08,  1.48it/s]
Profiling:  24%|██▎       | 86/363 [01:04<03:08,  1.47it/s]
Profiling:  24%|██▍       | 87/363 [01:06<03:48,  1.21it/s]
Profiling:  24%|██▍       | 88/363 [01:07<04:20,  1.05it/s]
Profiling:  25%|██▍       | 90/363 [01:08<03:06,  1.46it/s]
Profiling:  25%|██▌       | 91/363 [01:08<03:00,  1.50it/s]
Profiling:  25%|██▌       | 92/363 [01:09<02:53,  1.57it/s]
Profiling:  26%|██▌       | 93/363 [01:09<02:46,  1.62it/s]
Profiling:  26%|██▌       | 95/363 [01:11<02:52,  1.55it/s]
Profiling:  26%|██▋       | 96/363 [01:12<03:35,  1.24it/s]
Profiling:  27%|██▋       | 97/363 [01:13<04:12,  1.05it/s]
Profiling:  27%|██▋       | 99/363 [01:14<03:00,  1.46it/s]
Profiling:  28%|██▊       | 100/363 [01:15<02:54,  1.51it/s]
Profiling:  28%|██▊       | 101/363 [01:15<02:47,  1.57it/s]
Profiling:  28%|██▊       | 102/363 [01:16<02:37,  1.66it/s]
Profiling:  29%|██▊       | 104/363 [01:17<02:44,  1.58it/s]
Profiling:  29%|██▉       | 105/363 [01:18<03:20,  1.29it/s]
Profiling:  29%|██▉       | 106/363 [01:20<03:50,  1.12it/s]
Profiling:  30%|██▉       | 108/363 [01:20<02:40,  1.59it/s]
Profiling:  30%|███       | 109/363 [01:21<02:33,  1.65it/s]
Profiling:  31%|███       | 111/363 [01:22<02:34,  1.63it/s]
Profiling:  31%|███       | 112/363 [01:23<03:08,  1.33it/s]
Profiling:  31%|███       | 113/363 [01:24<03:44,  1.11it/s]
Profiling:  32%|███▏      | 115/363 [01:25<02:37,  1.57it/s]
Profiling:  32%|███▏      | 116/363 [01:25<02:30,  1.64it/s]
Profiling:  32%|███▏      | 117/363 [01:26<02:23,  1.72it/s]
Profiling:  33%|███▎      | 118/363 [01:26<02:16,  1.80it/s]
Profiling:  33%|███▎      | 120/363 [01:28<02:22,  1.70it/s]
Profiling:  33%|███▎      | 121/363 [01:29<02:59,  1.35it/s]
Profiling:  34%|███▎      | 122/363 [01:30<03:31,  1.14it/s]
Profiling:  34%|███▍      | 124/363 [01:31<02:27,  1.62it/s]
Profiling:  34%|███▍      | 125/363 [01:31<02:21,  1.68it/s]
Profiling:  35%|███▍      | 126/363 [01:32<02:15,  1.75it/s]
Profiling:  35%|███▍      | 127/363 [01:32<02:11,  1.80it/s]
Profiling:  36%|███▌      | 129/363 [01:34<02:18,  1.69it/s]
Profiling:  36%|███▌      | 130/363 [01:35<03:01,  1.29it/s]
Profiling:  36%|███▌      | 131/363 [01:36<03:28,  1.11it/s]
Profiling:  37%|███▋      | 133/363 [01:37<02:25,  1.58it/s]
Profiling:  37%|███▋      | 134/363 [01:37<02:18,  1.66it/s]
Profiling:  37%|███▋      | 135/363 [01:38<02:12,  1.73it/s]
Profiling:  37%|███▋      | 136/363 [01:38<02:07,  1.78it/s]
Profiling:  38%|███▊      | 137/363 [01:39<01:59,  1.90it/s]
Profiling:  38%|███▊      | 139/363 [01:40<02:11,  1.70it/s]
Profiling:  39%|███▊      | 140/363 [01:41<02:45,  1.35it/s]
Profiling:  39%|███▉      | 141/363 [01:42<03:12,  1.15it/s]
Profiling:  39%|███▉      | 143/363 [01:43<02:13,  1.65it/s]
Profiling:  40%|███▉      | 144/363 [01:43<02:08,  1.71it/s]
Profiling:  40%|███▉      | 145/363 [01:44<02:03,  1.77it/s]
Profiling:  40%|████      | 147/363 [01:45<02:08,  1.69it/s]
Profiling:  41%|████      | 148/363 [01:46<02:39,  1.35it/s]
Profiling:  41%|████      | 149/363 [01:48<03:05,  1.16it/s]
Profiling:  42%|████▏     | 151/363 [01:48<02:10,  1.63it/s]
Profiling:  42%|████▏     | 152/363 [01:49<02:04,  1.69it/s]
Profiling:  42%|████▏     | 153/363 [01:49<01:59,  1.76it/s]
Profiling:  42%|████▏     | 154/363 [01:50<01:55,  1.80it/s]
Profiling:  43%|████▎     | 156/363 [01:51<02:02,  1.69it/s]
Profiling:  43%|████▎     | 157/363 [01:52<02:35,  1.33it/s]
Profiling:  44%|████▎     | 158/363 [01:54<03:01,  1.13it/s]
Profiling:  44%|████▍     | 160/363 [01:54<02:06,  1.60it/s]
Profiling:  44%|████▍     | 161/363 [01:55<02:00,  1.67it/s]
Profiling:  45%|████▍     | 162/363 [01:55<01:55,  1.74it/s]
Profiling:  45%|████▍     | 163/363 [01:56<01:51,  1.79it/s]
Profiling:  45%|████▌     | 165/363 [01:57<01:56,  1.69it/s]
Profiling:  46%|████▌     | 166/363 [01:58<02:26,  1.35it/s]
Profiling:  46%|████▌     | 167/363 [01:59<02:50,  1.15it/s]
Profiling:  47%|████▋     | 169/363 [02:00<01:59,  1.63it/s]
Profiling:  47%|████▋     | 170/363 [02:00<01:53,  1.70it/s]
Profiling:  47%|████▋     | 171/363 [02:01<01:48,  1.77it/s]
Profiling:  47%|████▋     | 172/363 [02:01<01:44,  1.83it/s]
Profiling:  48%|████▊     | 173/363 [02:02<01:20,  2.35it/s]
Profiling:  48%|████▊     | 174/363 [02:03<02:03,  1.53it/s]
Profiling:  48%|████▊     | 175/363 [02:04<02:33,  1.23it/s]
Profiling:  48%|████▊     | 176/363 [02:05<02:54,  1.07it/s]
Profiling:  49%|████▉     | 178/363 [02:06<01:53,  1.63it/s]
Profiling:  49%|████▉     | 179/363 [02:06<01:45,  1.75it/s]
Profiling:  50%|████▉     | 180/363 [02:07<01:41,  1.80it/s]
Profiling:  50%|████▉     | 181/363 [02:07<01:38,  1.84it/s]
Profiling:  50%|█████     | 183/363 [02:08<01:43,  1.74it/s]
Profiling:  51%|█████     | 184/363 [02:10<02:09,  1.38it/s]
Profiling:  51%|█████     | 185/363 [02:11<02:31,  1.17it/s]
Profiling:  52%|█████▏    | 187/363 [02:11<01:45,  1.66it/s]
Profiling:  52%|█████▏    | 188/363 [02:12<01:41,  1.72it/s]
Profiling:  52%|█████▏    | 189/363 [02:12<01:37,  1.78it/s]
Profiling:  52%|█████▏    | 190/363 [02:13<01:34,  1.83it/s]
Profiling:  53%|█████▎    | 192/363 [02:14<01:38,  1.74it/s]
Profiling:  53%|█████▎    | 193/363 [02:15<02:04,  1.36it/s]
Profiling:  53%|█████▎    | 194/363 [02:17<02:25,  1.16it/s]
Profiling:  54%|█████▍    | 196/363 [02:17<01:41,  1.64it/s]
Profiling:  54%|█████▍    | 197/363 [02:18<01:37,  1.71it/s]
Profiling:  55%|█████▍    | 198/363 [02:18<01:33,  1.77it/s]
Profiling:  55%|█████▍    | 199/363 [02:19<01:30,  1.81it/s]
Profiling:  55%|█████▌    | 200/363 [02:20<02:01,  1.34it/s]
Profiling:  55%|█████▌    | 201/363 [02:21<02:22,  1.14it/s]
Profiling:  56%|█████▌    | 202/363 [02:22<02:04,  1.29it/s]
Profiling:  56%|█████▌    | 203/363 [02:22<01:51,  1.44it/s]
Profiling:  56%|█████▌    | 204/363 [02:23<01:41,  1.57it/s]
Profiling:  56%|█████▋    | 205/363 [02:23<01:34,  1.67it/s]
Profiling:  57%|█████▋    | 206/363 [02:23<01:11,  2.20it/s]
Profiling:  57%|█████▋    | 207/363 [02:24<01:47,  1.46it/s]
Profiling:  58%|█████▊    | 210/363 [02:26<01:21,  1.87it/s]
Profiling:  58%|█████▊    | 211/363 [02:27<01:43,  1.47it/s]
Profiling:  58%|█████▊    | 212/363 [02:28<02:06,  1.19it/s]
Profiling:  59%|█████▉    | 214/363 [02:29<01:30,  1.65it/s]
Profiling:  59%|█████▉    | 215/363 [02:29<01:26,  1.71it/s]
Profiling:  60%|█████▉    | 216/363 [02:30<01:23,  1.76it/s]
Profiling:  60%|█████▉    | 217/363 [02:30<01:20,  1.81it/s]
Profiling:  60%|██████    | 219/363 [02:32<01:24,  1.71it/s]
Profiling:  61%|██████    | 220/363 [02:33<01:45,  1.36it/s]
Profiling:  61%|██████    | 221/363 [02:34<02:03,  1.15it/s]
Profiling:  61%|██████▏   | 223/363 [02:35<01:25,  1.63it/s]
Profiling:  62%|██████▏   | 224/363 [02:35<01:20,  1.73it/s]
Profiling:  62%|██████▏   | 225/363 [02:35<01:15,  1.83it/s]
Profiling:  62%|██████▏   | 226/363 [02:36<01:12,  1.88it/s]
Profiling:  63%|██████▎   | 228/363 [02:37<01:17,  1.74it/s]
Profiling:  63%|██████▎   | 229/363 [02:39<01:39,  1.34it/s]
Profiling:  63%|██████▎   | 230/363 [02:40<01:55,  1.15it/s]
Profiling:  64%|██████▍   | 232/363 [02:40<01:20,  1.63it/s]
Profiling:  64%|██████▍   | 233/363 [02:41<01:16,  1.69it/s]
Profiling:  64%|██████▍   | 234/363 [02:41<01:13,  1.75it/s]
Profiling:  65%|██████▍   | 235/363 [02:42<01:11,  1.80it/s]
Profiling:  65%|██████▌   | 236/363 [02:43<01:32,  1.37it/s]
Profiling:  65%|██████▌   | 237/363 [02:44<01:24,  1.49it/s]
Profiling:  66%|██████▌   | 238/363 [02:44<01:18,  1.60it/s]
Profiling:  66%|██████▌   | 239/363 [02:45<01:13,  1.69it/s]
Profiling:  66%|██████▌   | 240/363 [02:45<01:09,  1.77it/s]
Profiling:  67%|██████▋   | 242/363 [02:46<01:14,  1.62it/s]
Profiling:  67%|██████▋   | 243/363 [02:48<01:31,  1.31it/s]
Profiling:  68%|██████▊   | 246/363 [02:49<01:07,  1.74it/s]
Profiling:  68%|██████▊   | 247/363 [02:50<01:21,  1.43it/s]
Profiling:  68%|██████▊   | 248/363 [02:51<01:28,  1.30it/s]
Profiling:  69%|██████▉   | 250/363 [02:51<01:02,  1.80it/s]
Profiling:  69%|██████▉   | 251/363 [02:52<00:55,  2.01it/s]
Profiling:  69%|██████▉   | 252/363 [02:52<00:50,  2.21it/s]
Profiling:  70%|██████▉   | 253/363 [02:52<00:47,  2.32it/s]
Profiling:  70%|███████   | 255/363 [02:53<00:46,  2.34it/s]
Profiling:  71%|███████   | 256/363 [02:54<00:58,  1.82it/s]
Profiling:  71%|███████   | 257/363 [02:55<01:09,  1.52it/s]
Profiling:  71%|███████▏  | 259/363 [02:56<00:47,  2.17it/s]
Profiling:  72%|███████▏  | 260/363 [02:56<00:44,  2.32it/s]
Profiling:  72%|███████▏  | 261/363 [02:56<00:41,  2.46it/s]
Profiling:  72%|███████▏  | 262/363 [02:57<00:38,  2.59it/s]
Profiling:  73%|███████▎  | 264/363 [02:57<00:38,  2.60it/s]
Profiling:  73%|███████▎  | 265/363 [02:58<00:45,  2.14it/s]
Profiling:  73%|███████▎  | 266/363 [02:59<00:52,  1.85it/s]
Profiling:  74%|███████▍  | 268/363 [02:59<00:36,  2.58it/s]
Profiling:  74%|███████▍  | 269/363 [03:00<00:35,  2.68it/s]
Profiling:  74%|███████▍  | 270/363 [03:00<00:33,  2.76it/s]
Profiling:  75%|███████▍  | 271/363 [03:00<00:32,  2.83it/s]
Profiling:  75%|███████▍  | 272/363 [03:01<00:31,  2.89it/s]
Profiling:  75%|███████▌  | 273/363 [03:01<00:30,  2.93it/s]
Profiling:  75%|███████▌  | 274/363 [03:01<00:29,  2.98it/s]
Profiling:  76%|███████▌  | 275/363 [03:01<00:29,  2.98it/s]
Profiling:  76%|███████▋  | 277/363 [03:02<00:33,  2.54it/s]
Profiling:  77%|███████▋  | 278/363 [03:03<00:42,  2.01it/s]
Profiling:  77%|███████▋  | 279/363 [03:04<00:53,  1.58it/s]
Profiling:  78%|███████▊  | 282/363 [03:05<00:36,  2.22it/s]
Profiling:  78%|███████▊  | 283/363 [03:06<00:42,  1.88it/s]
Profiling:  78%|███████▊  | 284/363 [03:07<00:47,  1.66it/s]
Profiling:  79%|███████▉  | 286/363 [03:07<00:33,  2.32it/s]
Profiling:  79%|███████▉  | 287/363 [03:07<00:31,  2.45it/s]
Profiling:  79%|███████▉  | 288/363 [03:08<00:29,  2.57it/s]
Profiling:  80%|███████▉  | 289/363 [03:08<00:27,  2.71it/s]
Profiling:  80%|████████  | 291/363 [03:09<00:28,  2.50it/s]
Profiling:  80%|████████  | 292/363 [03:10<00:38,  1.84it/s]
Profiling:  81%|████████  | 293/363 [03:11<00:50,  1.39it/s]
Profiling:  81%|████████▏ | 295/363 [03:12<00:35,  1.90it/s]
Profiling:  82%|████████▏ | 296/363 [03:12<00:34,  1.92it/s]
Profiling:  82%|████████▏ | 297/363 [03:13<00:34,  1.93it/s]
Profiling:  82%|████████▏ | 298/363 [03:13<00:33,  1.94it/s]
Profiling:  83%|████████▎ | 300/363 [03:15<00:35,  1.78it/s]
Profiling:  83%|████████▎ | 301/363 [03:16<00:43,  1.42it/s]
Profiling:  83%|████████▎ | 302/363 [03:17<00:49,  1.24it/s]
Profiling:  84%|████████▎ | 304/363 [03:17<00:34,  1.73it/s]
Profiling:  84%|████████▍ | 305/363 [03:18<00:32,  1.78it/s]
Profiling:  84%|████████▍ | 306/363 [03:18<00:31,  1.82it/s]
Profiling:  85%|████████▍ | 307/363 [03:19<00:30,  1.85it/s]
Profiling:  85%|████████▍ | 308/363 [03:19<00:29,  1.84it/s]
Profiling:  85%|████████▌ | 309/363 [03:20<00:27,  1.98it/s]
Profiling:  85%|████████▌ | 310/363 [03:20<00:24,  2.13it/s]
Profiling:  86%|████████▌ | 311/363 [03:20<00:19,  2.72it/s]
Profiling:  86%|████████▌ | 312/363 [03:22<00:31,  1.61it/s]
Profiling:  86%|████████▌ | 313/363 [03:23<00:39,  1.25it/s]
Profiling:  87%|████████▋ | 314/363 [03:24<00:45,  1.08it/s]
Profiling:  87%|████████▋ | 316/363 [03:25<00:28,  1.63it/s]
Profiling:  88%|████████▊ | 318/363 [03:25<00:25,  1.77it/s]
Profiling:  88%|████████▊ | 319/363 [03:26<00:26,  1.66it/s]
Profiling:  88%|████████▊ | 320/363 [03:27<00:27,  1.58it/s]
Profiling:  89%|████████▊ | 322/363 [03:27<00:18,  2.26it/s]
Profiling:  89%|████████▉ | 323/363 [03:28<00:16,  2.36it/s]
Profiling:  89%|████████▉ | 324/363 [03:28<00:16,  2.41it/s]
Profiling:  90%|████████▉ | 325/363 [03:28<00:15,  2.39it/s]
Profiling:  90%|█████████ | 327/363 [03:29<00:15,  2.26it/s]
Profiling:  90%|█████████ | 328/363 [03:30<00:18,  1.86it/s]
Profiling:  91%|█████████ | 329/363 [03:31<00:20,  1.67it/s]
Profiling:  91%|█████████ | 331/363 [03:31<00:13,  2.40it/s]
Profiling:  91%|█████████▏| 332/363 [03:32<00:12,  2.51it/s]
Profiling:  92%|█████████▏| 333/363 [03:32<00:11,  2.62it/s]
Profiling:  92%|█████████▏| 334/363 [03:32<00:10,  2.70it/s]
Profiling:  93%|█████████▎| 336/363 [03:33<00:09,  2.70it/s]
Profiling:  93%|█████████▎| 337/363 [03:34<00:11,  2.27it/s]
Profiling:  93%|█████████▎| 338/363 [03:35<00:12,  1.95it/s]
Profiling:  94%|█████████▎| 340/363 [03:35<00:08,  2.72it/s]
Profiling:  94%|█████████▍| 341/363 [03:35<00:07,  2.80it/s]
Profiling:  94%|█████████▍| 342/363 [03:35<00:07,  2.87it/s]
Profiling:  94%|█████████▍| 343/363 [03:36<00:06,  2.92it/s]
Profiling:  95%|█████████▍| 344/363 [03:36<00:06,  2.93it/s]
Profiling:  95%|█████████▌| 345/363 [03:37<00:06,  2.75it/s]
Profiling:  95%|█████████▌| 346/363 [03:38<00:12,  1.32it/s]
Profiling:  96%|█████████▌| 348/363 [03:39<00:08,  1.71it/s]
Profiling:  96%|█████████▌| 349/363 [03:40<00:08,  1.61it/s]
Profiling:  96%|█████████▋| 350/363 [03:41<00:08,  1.54it/s]
Profiling:  97%|█████████▋| 352/363 [03:41<00:04,  2.26it/s]
Profiling:  97%|█████████▋| 353/363 [03:41<00:04,  2.40it/s]
Profiling:  98%|█████████▊| 355/363 [03:42<00:03,  2.56it/s]
Profiling:  98%|█████████▊| 356/363 [03:43<00:03,  2.19it/s]
Profiling:  98%|█████████▊| 357/363 [03:43<00:03,  1.91it/s]
Profiling:  99%|█████████▉| 359/363 [03:44<00:01,  2.58it/s]
Profiling:  99%|█████████▉| 360/363 [03:44<00:01,  2.67it/s]
Profiling:  99%|█████████▉| 361/363 [03:44<00:00,  2.89it/s]
Profiling: 100%|█████████▉| 362/363 [03:45<00:00,  3.11it/s]
Profiling: 100%|██████████| 363/363 [03:45<00:00,  1.61it/s]
alkahestry-pointer-mist-v36-mkmlizer: quantized model in 275.556s
alkahestry-pointer-mist-v36-mkmlizer: Processed model alkahestry/pointer-mist in 407.553s
alkahestry-pointer-mist-v36-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-pointer-mist-v36-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-pointer-mist-v36-mkmlizer: uploading /tmp/model_cache to s3://guanaco-mkml-models/alkahestry-pointer-mist-v36
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/config.json s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/config.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/added_tokens.json s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/added_tokens.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/tokenizer.model s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/tokenizer.model
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/tokenizer.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/special_tokens_map.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/tokenizer_config.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/model_cache/mkml_model.tensors s3://guanaco-mkml-models/alkahestry-pointer-mist-v36/mkml_model.tensors
alkahestry-pointer-mist-v36-mkmlizer: loading reward model from alkahestry/gpt2-reward-rp
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
config.json:   0%|          | 0.00/1.00k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.00k/1.00k [00:00<00:00, 11.1MB/s]
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/290 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 290/290 [00:00<00:00, 2.97MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
vocab.json:   0%|          | 0.00/798k [00:00<?, ?B/s]
vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 27.1MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]
merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 7.41MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.2MB/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.1MB/s]
alkahestry-pointer-mist-v36-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/131 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 131/131 [00:00<00:00, 1.14MB/s]
alkahestry-pointer-mist-v36-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-pointer-mist-v36-mkmlizer:   warnings.warn(
alkahestry-pointer-mist-v36-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/498M [00:00<?, ?B/s]
pytorch_model.bin:   2%|▏         | 10.5M/498M [00:01<00:56, 8.65MB/s]
pytorch_model.bin:   5%|▌         | 26.0M/498M [00:01<00:21, 22.4MB/s]
pytorch_model.bin:   9%|▉         | 46.9M/498M [00:01<00:10, 43.6MB/s]
pytorch_model.bin:  22%|██▏       | 110M/498M [00:01<00:03, 127MB/s]  
pytorch_model.bin:  39%|███▉      | 194M/498M [00:01<00:01, 241MB/s]
pytorch_model.bin:  66%|██████▋   | 330M/498M [00:01<00:00, 454MB/s]
pytorch_model.bin:  94%|█████████▎| 466M/498M [00:02<00:00, 244MB/s]
pytorch_model.bin: 100%|█████████▉| 498M/498M [00:02<00:00, 177MB/s]
alkahestry-pointer-mist-v36-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-pointer-mist-v36-mkmlizer: Saving duration: 0.107s
alkahestry-pointer-mist-v36-mkmlizer: Processed model alkahestry/gpt2-reward-rp in 5.970s
alkahestry-pointer-mist-v36-mkmlizer: creating bucket guanaco-reward-models
alkahestry-pointer-mist-v36-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alkahestry-pointer-mist-v36-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/config.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/special_tokens_map.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/merges.txt
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/tokenizer_config.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/vocab.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/tokenizer.json
alkahestry-pointer-mist-v36-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alkahestry-pointer-mist-v36_reward/reward.tensors
Job alkahestry-pointer-mist-v36-mkmlizer completed after 450.69s with status: succeeded
Stopping job with name alkahestry-pointer-mist-v36-mkmlizer
Pipeline stage MKMLizer completed in 457.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.18s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-pointer-mist-v36
Waiting for inference service alkahestry-pointer-mist-v36 to be ready
Inference service alkahestry-pointer-mist-v36 ready after 50.3097198009491s
Pipeline stage ISVCDeployer completed in 58.89s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.07s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
Running pipeline stage StressChecker
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received no response to inference request from service
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 7.23194694519043s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 9.22459077835083s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 7.207581281661987s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 2.29392671585083s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.300501823425293s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 1.9166104793548584s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.199579954147339s
Received healthy response to inference request with status code 200 in 1.6639859676361084s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 1.8597240447998047s
Received score %s for bot %s
Completed M-Eval for topic stay_in_character, average_score=8.479166666666666
Running M-Eval for topic user_preference
M-Eval Dataset for topic user_preference is loaded
Received healthy response to inference request with status code 200 in 2.4905378818511963s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 14.98514986038208s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.769298553466797s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 5.5860066413879395s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 5.888740539550781s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 3.596273183822632s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 5.7100605964660645s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.355168104171753s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 1.897721290588379s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 1.8442554473876953s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.240374803543091s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.033473491668701s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.2749648094177246s
Received score %s for bot %s
Completed M-Eval for topic user_preference, average_score=7.36
Running M-Eval for topic entertaining
M-Eval Dataset for topic entertaining is loaded
Received healthy response to inference request with status code 200 in 3.064277410507202s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 12.0795259475708s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 2.9154441356658936s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 2.843614101409912s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 2.5243966579437256s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.9979355335235596s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 3.048957347869873s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.5428860187530518s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request with status code 200 in 2.621884346008301s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.3183181285858154s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.2156059741973877s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.325096368789673s
Received score %s for bot %s
Received healthy response to inference request with status code 200 in 2.3280081748962402s
Received score %s for bot %s
Received score %s for bot %s
Completed M-Eval for topic entertaining, average_score=7.08
Received healthy response to inference request with status code 200 in 2.2503442764282227s
Received healthy response to inference request with status code 200 in 2.236631155014038s
Received healthy response to inference request with status code 200 in 2.222928285598755s
Received healthy response to inference request with status code 200 in 2.240023374557495s
Received healthy response to inference request with status code 200 in 2.7425994873046875s
Received healthy response to inference request with status code 200 in 3.088590383529663s
Received healthy response to inference request with status code 200 in 2.2581145763397217s
Received healthy response to inference request with status code 200 in 3.102666139602661s
Received healthy response to inference request with status code 200 in 3.128004550933838s
Received healthy response to inference request with status code 200 in 2.0700936317443848s
Received healthy response to inference request with status code 200 in 2.2176148891448975s
Received healthy response to inference request with status code 200 in 2.2645907402038574s
Received healthy response to inference request with status code 200 in 2.2752485275268555s
Received healthy response to inference request with status code 200 in 2.2113630771636963s
Received healthy response to inference request with status code 200 in 1.9323878288269043s
Received healthy response to inference request with status code 200 in 2.238666534423828s
Received healthy response to inference request with status code 200 in 2.2482986450195312s
Received healthy response to inference request with status code 200 in 2.2453036308288574s
Received healthy response to inference request with status code 200 in 2.2293496131896973s
Received healthy response to inference request with status code 200 in 2.257016658782959s
Received healthy response to inference request with status code 200 in 2.2336881160736084s
Received healthy response to inference request with status code 200 in 2.2126896381378174s
Received healthy response to inference request with status code 200 in 3.090541124343872s
Received healthy response to inference request with status code 200 in 3.1164093017578125s
Received healthy response to inference request with status code 200 in 3.036792516708374s
Received healthy response to inference request with status code 200 in 2.4668591022491455s
Received healthy response to inference request with status code 200 in 2.2592313289642334s
Received healthy response to inference request with status code 200 in 2.281629800796509s
Received healthy response to inference request with status code 200 in 3.075058698654175s
Received healthy response to inference request with status code 200 in 2.2690064907073975s
Received healthy response to inference request with status code 200 in 3.0995371341705322s
Received healthy response to inference request with status code 200 in 2.2734475135803223s
Received healthy response to inference request with status code 200 in 2.2841391563415527s
Received healthy response to inference request with status code 200 in 2.2006521224975586s
Received healthy response to inference request with status code 200 in 2.3580784797668457s
Received healthy response to inference request with status code 200 in 2.2370500564575195s
Received healthy response to inference request with status code 200 in 3.033151865005493s
Received healthy response to inference request with status code 200 in 2.2601022720336914s
Received healthy response to inference request with status code 200 in 2.238872528076172s
Received healthy response to inference request with status code 200 in 2.26792311668396s
Received healthy response to inference request with status code 200 in 2.2222981452941895s
Received healthy response to inference request with status code 200 in 2.238652229309082s
Received healthy response to inference request with status code 200 in 2.2480976581573486s
Received healthy response to inference request with status code 200 in 2.245004177093506s
Received healthy response to inference request with status code 200 in 2.2833375930786133s
Received healthy response to inference request with status code 200 in 2.263892889022827s
Received healthy response to inference request with status code 200 in 2.2310900688171387s
Received healthy response to inference request with status code 200 in 2.2040598392486572s
Received healthy response to inference request with status code 200 in 2.2020084857940674s
Received healthy response to inference request with status code 200 in 0.7121665477752686s
Received healthy response to inference request with status code 200 in 1.143531322479248s
Received healthy response to inference request with status code 200 in 2.216428518295288s
Received healthy response to inference request with status code 200 in 2.2349140644073486s
Received healthy response to inference request with status code 200 in 2.2618565559387207s
Received healthy response to inference request with status code 200 in 2.0166406631469727s
Received healthy response to inference request with status code 200 in 1.0035924911499023s
Received healthy response to inference request with status code 200 in 2.2380716800689697s
Received healthy response to inference request with status code 200 in 2.2477715015411377s
Received healthy response to inference request with status code 200 in 1.4524197578430176s
Received healthy response to inference request with status code 200 in 2.23435115814209s
Received healthy response to inference request with status code 200 in 2.218372344970703s
Received healthy response to inference request with status code 200 in 1.9273731708526611s
Received healthy response to inference request with status code 200 in 2.1253042221069336s
Received healthy response to inference request with status code 200 in 1.1456067562103271s
100 requests
1 failed requests
5th percentile: 1.653407657146454
10th percentile: 1.9262969017028808
20th percentile: 2.2099024295806884
30th percentile: 2.232908701896667
40th percentile: 2.2402342319488526
50th percentile: 2.2596668004989624
60th percentile: 2.2823129177093504
70th percentile: 2.4739627361297605
80th percentile: 3.0338799953460693
90th percentile: 3.1748314142227216
95th percentile: 7.208799564838409
99th percentile: 15.03621802091601
mean time: 2.985599274635315
Pipeline stage StressChecker completed in 316.02s
alkahestry-pointer-mist_v36 status is now deployed due to admin request
alkahestry-pointer-mist_v36 status is now inactive due to auto deactivation removed underperforming models
alkahestry-pointer-mist_v36 status is now deployed due to admin request
alkahestry-pointer-mist_v36 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of alkahestry-pointer-mist_v36
Running pipeline stage ISVCDeleter
Checking if service alkahestry-pointer-mist-v36 is running
Tearing down inference service alkahestry-pointer-mist-v36
Toredown service alkahestry-pointer-mist-v36
Pipeline stage ISVCDeleter completed in 4.13s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key alkahestry-pointer-mist-v36/added_tokens.json from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/config.json from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/tokenizer.json from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/tokenizer.model from bucket guanaco-mkml-models
Deleting key alkahestry-pointer-mist-v36/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key alkahestry-pointer-mist-v36_reward/config.json from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/merges.txt from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/reward.tensors from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key alkahestry-pointer-mist-v36_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.87s
alkahestry-pointer-mist_v36 status is now torndown due to DeploymentManager action