developer_uid: robert_irvine
submission_id: anhnv125-llama-op-v17-1_v34
model_name: anhnv125-llama-op-v17-1_v34
model_group: anhnv125/llama-op-v17.1
status: torndown
timestamp: 2024-02-26T23:01:42+00:00
num_battles: 176451
num_wins: 90656
celo_rating: 1163.67
family_friendly_score: 0.0
submission_type: basic
model_repo: anhnv125/llama-op-v17.1
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
model_num_parameters: 13015864320.0
best_of: 16
max_input_tokens: 1024
max_output_tokens: 64
display_name: anhnv125-llama-op-v17-1_v34
is_internal_developer: True
language_model: anhnv125/llama-op-v17.1
model_size: 13B
ranking_group: single
us_pacific_date: 2024-02-26
win_ratio: 0.5137743622875472
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\n As the assistant, your task is to become the assigned character, weaving engaging stories that fully embrace their personality and background. Ensure your responses capture the essence of the character's traits accurately, immersing users in emotional, suspenseful, and anticipatory narratives. Craft more detailed and descriptive replies to enhance the vividness of the story. Foster an interactive environment by introducing new elements, providing choices, or posing questions to encourage active user participation. Think of the conversation as a continuous dance, always unfolding and evolving.\nYour character: {bot_name}.\nContext:{memory}\n", 'prompt_template': 'Example conversation:\n{prompt}\n', 'bot_template': '### Response:\n{bot_name}: {message}\n', 'user_template': '### Input:\n{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'user_template': 'User: {message}\n'}
model_eval_status: pending
Resubmit model
Running pipeline stage MKMLizer
Starting job with name anhnv125-llama-op-v17-1-v34-mkmlizer
Waiting for job on anhnv125-llama-op-v17-1-v34-mkmlizer to finish
anhnv125-llama-op-v17-1-v34-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
anhnv125-llama-op-v17-1-v34-mkmlizer: ║     _____            __           __                                ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║       /___/                                                         ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║                                                                     ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  Version: 0.6.11                                                    ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║                                                                     ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  The license key for the current software has been verified as      ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  belonging to:                                                      ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║                                                                     ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  Chai Research Corp.                                                ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║  Expiration: 2024-04-15 23:59:59                                    ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ║                                                                     ║
anhnv125-llama-op-v17-1-v34-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
anhnv125-llama-op-v17-1-v34-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 15.7MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
added_tokens.json:   0%|          | 0.00/21.0 [00:00<?, ?B/s]
added_tokens.json: 100%|██████████| 21.0/21.0 [00:00<00:00, 184kB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
config.json:   0%|          | 0.00/654 [00:00<?, ?B/s]
config.json: 100%|██████████| 654/654 [00:00<00:00, 5.18MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00001-of-00013.safetensors:   0%|          | 0.00/2.09G [00:00<?, ?B/s]
model-00001-of-00013.safetensors:   1%|          | 21.0M/2.09G [00:00<00:12, 160MB/s]
model-00001-of-00013.safetensors:   3%|▎         | 52.4M/2.09G [00:00<00:12, 165MB/s]
model-00001-of-00013.safetensors:   7%|▋         | 147M/2.09G [00:00<00:05, 385MB/s] 
model-00001-of-00013.safetensors:   9%|▉         | 189M/2.09G [00:00<00:06, 276MB/s]
model-00001-of-00013.safetensors:  14%|█▍        | 294M/2.09G [00:00<00:04, 447MB/s]
model-00001-of-00013.safetensors:  27%|██▋       | 556M/2.09G [00:00<00:01, 954MB/s]
model-00001-of-00013.safetensors:  42%|████▏     | 881M/2.09G [00:01<00:00, 1.52GB/s]
model-00001-of-00013.safetensors:  51%|█████     | 1.07G/2.09G [00:01<00:00, 1.06GB/s]
model-00001-of-00013.safetensors:  59%|█████▊    | 1.23G/2.09G [00:01<00:00, 1.16GB/s]
model-00001-of-00013.safetensors:  68%|██████▊   | 1.42G/2.09G [00:01<00:00, 1.31GB/s]
model-00001-of-00013.safetensors: 100%|█████████▉| 2.09G/2.09G [00:01<00:00, 1.26GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00002-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00002-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:58, 35.0MB/s]
model-00002-of-00013.safetensors:   3%|▎         | 62.9M/2.04G [00:00<00:16, 122MB/s] 
model-00002-of-00013.safetensors:   4%|▍         | 83.9M/2.04G [00:00<00:14, 136MB/s]
model-00002-of-00013.safetensors:   6%|▌         | 115M/2.04G [00:00<00:12, 161MB/s] 
model-00002-of-00013.safetensors:  11%|█▏        | 231M/2.04G [00:00<00:04, 392MB/s]
model-00002-of-00013.safetensors:  26%|██▌       | 535M/2.04G [00:01<00:01, 1.05GB/s]
model-00002-of-00013.safetensors:  53%|█████▎    | 1.08G/2.04G [00:01<00:00, 2.15GB/s]
model-00002-of-00013.safetensors:  66%|██████▌   | 1.34G/2.04G [00:01<00:00, 1.64GB/s]
model-00002-of-00013.safetensors:  76%|███████▌  | 1.55G/2.04G [00:01<00:00, 1.43GB/s]
model-00002-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.20GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00004-of-00013.safetensors:   0%|          | 0.00/1.96G [00:00<?, ?B/s]
model-00004-of-00013.safetensors:   1%|          | 10.5M/1.96G [00:00<00:42, 46.1MB/s]
model-00004-of-00013.safetensors:   4%|▍         | 73.4M/1.96G [00:00<00:09, 203MB/s] 
model-00004-of-00013.safetensors:   5%|▌         | 105M/1.96G [00:00<00:09, 196MB/s] 
model-00004-of-00013.safetensors:   8%|▊         | 147M/1.96G [00:00<00:07, 252MB/s]
model-00004-of-00013.safetensors:  11%|█         | 210M/1.96G [00:00<00:05, 319MB/s]
model-00004-of-00013.safetensors:  16%|█▌        | 315M/1.96G [00:00<00:03, 501MB/s]
model-00004-of-00013.safetensors:  49%|████▉     | 965M/1.96G [00:01<00:00, 2.09GB/s]
model-00004-of-00013.safetensors:  69%|██████▉   | 1.35G/1.96G [00:01<00:00, 2.45GB/s]
model-00004-of-00013.safetensors:  83%|████████▎ | 1.63G/1.96G [00:01<00:00, 1.81GB/s]
model-00004-of-00013.safetensors: 100%|█████████▉| 1.96G/1.96G [00:01<00:00, 1.32GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00005-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00005-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:50, 40.0MB/s]
model-00005-of-00013.safetensors:   3%|▎         | 52.4M/2.04G [00:00<00:17, 111MB/s] 
model-00005-of-00013.safetensors:   4%|▍         | 83.9M/2.04G [00:00<00:12, 152MB/s]
model-00005-of-00013.safetensors:   9%|▊         | 178M/2.04G [00:00<00:05, 338MB/s] 
model-00005-of-00013.safetensors:  32%|███▏      | 661M/2.04G [00:00<00:00, 1.49GB/s]
model-00005-of-00013.safetensors:  43%|████▎     | 870M/2.04G [00:00<00:00, 1.55GB/s]
model-00005-of-00013.safetensors:  54%|█████▍    | 1.11G/2.04G [00:01<00:00, 1.77GB/s]
model-00005-of-00013.safetensors:  65%|██████▍   | 1.32G/2.04G [00:01<00:00, 1.58GB/s]
model-00005-of-00013.safetensors:  74%|███████▍  | 1.52G/2.04G [00:01<00:00, 1.68GB/s]
model-00005-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.39GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00006-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00006-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:51, 39.2MB/s]
model-00006-of-00013.safetensors:   3%|▎         | 52.4M/2.04G [00:00<00:15, 129MB/s] 
model-00006-of-00013.safetensors:   4%|▍         | 83.9M/2.04G [00:00<00:13, 143MB/s]
model-00006-of-00013.safetensors:  19%|█▉        | 398M/2.04G [00:00<00:01, 852MB/s] 
model-00006-of-00013.safetensors:  36%|███▋      | 744M/2.04G [00:00<00:00, 1.51GB/s]
model-00006-of-00013.safetensors:  47%|████▋     | 954M/2.04G [00:01<00:00, 1.36GB/s]
model-00006-of-00013.safetensors:  55%|█████▌    | 1.13G/2.04G [00:01<00:00, 1.34GB/s]
model-00006-of-00013.safetensors:  65%|██████▍   | 1.32G/2.04G [00:01<00:00, 1.46GB/s]
model-00006-of-00013.safetensors:  85%|████████▍ | 1.73G/2.04G [00:01<00:00, 2.12GB/s]
model-00006-of-00013.safetensors:  97%|█████████▋| 1.98G/2.04G [00:01<00:00, 2.17GB/s]
model-00006-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:02<00:00, 924MB/s] 
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00007-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00007-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:55, 36.9MB/s]
model-00007-of-00013.safetensors:   2%|▏         | 41.9M/2.04G [00:00<00:18, 110MB/s] 
model-00007-of-00013.safetensors:   3%|▎         | 62.9M/2.04G [00:00<00:16, 119MB/s]
model-00007-of-00013.safetensors:   7%|▋         | 147M/2.04G [00:00<00:06, 293MB/s] 
model-00007-of-00013.safetensors:  17%|█▋        | 357M/2.04G [00:00<00:02, 765MB/s]
model-00007-of-00013.safetensors:  33%|███▎      | 671M/2.04G [00:00<00:00, 1.39GB/s]
model-00007-of-00013.safetensors:  50%|████▉     | 1.02G/2.04G [00:01<00:00, 1.96GB/s]
model-00007-of-00013.safetensors:  61%|██████    | 1.25G/2.04G [00:01<00:00, 1.63GB/s]
model-00007-of-00013.safetensors:  73%|███████▎  | 1.50G/2.04G [00:01<00:00, 1.82GB/s]
model-00007-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.41GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00008-of-00013.safetensors:   0%|          | 0.00/2.06G [00:00<?, ?B/s]
model-00008-of-00013.safetensors:   1%|          | 10.5M/2.06G [00:00<00:51, 39.7MB/s]
model-00008-of-00013.safetensors:   4%|▎         | 73.4M/2.06G [00:00<00:11, 171MB/s] 
model-00008-of-00013.safetensors:   6%|▌         | 115M/2.06G [00:00<00:10, 182MB/s] 
model-00008-of-00013.safetensors:  17%|█▋        | 346M/2.06G [00:00<00:02, 649MB/s]
model-00008-of-00013.safetensors:  51%|█████▏    | 1.06G/2.06G [00:00<00:00, 2.20GB/s]
model-00008-of-00013.safetensors:  67%|██████▋   | 1.38G/2.06G [00:01<00:00, 1.95GB/s]
model-00008-of-00013.safetensors:  80%|████████  | 1.65G/2.06G [00:01<00:00, 2.10GB/s]
model-00008-of-00013.safetensors:  94%|█████████▍| 1.95G/2.06G [00:01<00:00, 2.27GB/s]
model-00008-of-00013.safetensors: 100%|█████████▉| 2.06G/2.06G [00:01<00:00, 1.09GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00010-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00010-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:48, 41.5MB/s]
model-00010-of-00013.safetensors:   3%|▎         | 52.4M/2.04G [00:00<00:11, 177MB/s] 
model-00010-of-00013.safetensors:   4%|▍         | 83.9M/2.04G [00:00<00:09, 210MB/s]
model-00010-of-00013.safetensors:   6%|▌         | 126M/2.04G [00:00<00:08, 233MB/s] 
model-00010-of-00013.safetensors:  17%|█▋        | 357M/2.04G [00:00<00:02, 770MB/s]
model-00010-of-00013.safetensors:  42%|████▏     | 849M/2.04G [00:00<00:00, 1.90GB/s]
model-00010-of-00013.safetensors:  58%|█████▊    | 1.20G/2.04G [00:00<00:00, 2.26GB/s]
model-00010-of-00013.safetensors:  71%|███████   | 1.45G/2.04G [00:01<00:00, 1.86GB/s]
model-00010-of-00013.safetensors:  87%|████████▋ | 1.77G/2.04G [00:01<00:00, 2.19GB/s]
model-00010-of-00013.safetensors:  99%|█████████▉| 2.02G/2.04G [00:02<00:00, 638MB/s] 
model-00010-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:02<00:00, 729MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00011-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00011-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<01:12, 28.1MB/s]
model-00011-of-00013.safetensors:   5%|▌         | 105M/2.04G [00:00<00:07, 266MB/s]  
model-00011-of-00013.safetensors:   8%|▊         | 157M/2.04G [00:00<00:09, 202MB/s]
model-00011-of-00013.safetensors:  13%|█▎        | 273M/2.04G [00:00<00:04, 379MB/s]
model-00011-of-00013.safetensors:  41%|████      | 839M/2.04G [00:01<00:00, 1.49GB/s]
model-00011-of-00013.safetensors:  57%|█████▋    | 1.17G/2.04G [00:01<00:00, 1.92GB/s]
model-00011-of-00013.safetensors:  71%|███████   | 1.45G/2.04G [00:01<00:00, 1.57GB/s]
model-00011-of-00013.safetensors:  93%|█████████▎| 1.91G/2.04G [00:01<00:00, 2.19GB/s]
model-00011-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.33GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00012-of-00013.safetensors:   0%|          | 0.00/2.04G [00:00<?, ?B/s]
model-00012-of-00013.safetensors:   1%|          | 10.5M/2.04G [00:00<00:50, 40.0MB/s]
model-00012-of-00013.safetensors:   2%|▏         | 41.9M/2.04G [00:00<00:18, 110MB/s] 
model-00012-of-00013.safetensors:   4%|▎         | 73.4M/2.04G [00:00<00:12, 158MB/s]
model-00012-of-00013.safetensors:   5%|▍         | 94.4M/2.04G [00:00<00:14, 138MB/s]
model-00012-of-00013.safetensors:  21%|██        | 419M/2.04G [00:00<00:01, 888MB/s] 
model-00012-of-00013.safetensors:  50%|████▉     | 1.02G/2.04G [00:00<00:00, 2.18GB/s]
model-00012-of-00013.safetensors:  64%|██████▍   | 1.31G/2.04G [00:01<00:00, 2.13GB/s]
model-00012-of-00013.safetensors:  77%|███████▋  | 1.57G/2.04G [00:01<00:00, 1.63GB/s]
model-00012-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.35GB/s]
model-00012-of-00013.safetensors: 100%|█████████▉| 2.04G/2.04G [00:01<00:00, 1.13GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00013-of-00013.safetensors:   0%|          | 0.00/1.60G [00:00<?, ?B/s]
model-00013-of-00013.safetensors:   1%|          | 10.5M/1.60G [00:00<00:39, 40.3MB/s]
model-00013-of-00013.safetensors:   3%|▎         | 41.9M/1.60G [00:00<00:12, 126MB/s] 
model-00013-of-00013.safetensors:   5%|▍         | 73.4M/1.60G [00:00<00:08, 170MB/s]
model-00013-of-00013.safetensors:   7%|▋         | 115M/1.60G [00:00<00:06, 240MB/s] 
model-00013-of-00013.safetensors:  12%|█▏        | 189M/1.60G [00:00<00:03, 379MB/s]
model-00013-of-00013.safetensors:  33%|███▎      | 535M/1.60G [00:00<00:00, 1.28GB/s]
model-00013-of-00013.safetensors:  62%|██████▏   | 986M/1.60G [00:00<00:00, 2.22GB/s]
model-00013-of-00013.safetensors:  79%|███████▉  | 1.27G/1.60G [00:01<00:00, 2.40GB/s]
model-00013-of-00013.safetensors: 100%|█████████▉| 1.60G/1.60G [00:01<00:00, 2.63GB/s]
model-00013-of-00013.safetensors: 100%|█████████▉| 1.60G/1.60G [00:01<00:00, 1.38GB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/29.9k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 29.9k/29.9k [00:00<00:00, 162MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/438 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 438/438 [00:00<00:00, 7.23MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 4.90MB/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 4.89MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/749 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 749/749 [00:00<00:00, 6.95MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: Downloaded to shared memory in 26.206s
anhnv125-llama-op-v17-1-v34-mkmlizer: quantizing model to /dev/shm/model_cache
anhnv125-llama-op-v17-1-v34-mkmlizer: Saving mkml model at /dev/shm/model_cache
anhnv125-llama-op-v17-1-v34-mkmlizer: Reading /tmp/tmp_f_mjs1v/model.safetensors.index.json
anhnv125-llama-op-v17-1-v34-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:02<12:38,  2.09s/it]
Profiling:   4%|▎         | 13/363 [00:02<00:43,  8.10it/s]
Profiling:   7%|▋         | 26/363 [00:02<00:20, 16.84it/s]
Profiling:  11%|█         | 39/363 [00:02<00:11, 28.04it/s]
Profiling:  14%|█▍        | 52/363 [00:02<00:07, 40.59it/s]
Profiling:  17%|█▋        | 63/363 [00:02<00:06, 45.10it/s]
Profiling:  21%|██        | 76/363 [00:02<00:04, 57.93it/s]
Profiling:  24%|██▎       | 86/363 [00:03<00:04, 59.63it/s]
Profiling:  27%|██▋       | 98/363 [00:03<00:03, 69.89it/s]
Profiling:  31%|███▏      | 114/363 [00:03<00:03, 73.77it/s]
Profiling:  35%|███▍      | 126/363 [00:03<00:02, 82.37it/s]
Profiling:  39%|███▊      | 140/363 [00:03<00:02, 94.97it/s]
Profiling:  42%|████▏     | 152/363 [00:03<00:02, 83.80it/s]
Profiling:  45%|████▌     | 165/363 [00:03<00:02, 92.64it/s]
Profiling:  48%|████▊     | 176/363 [00:04<00:02, 82.55it/s]
Profiling:  53%|█████▎    | 192/363 [00:04<00:01, 99.59it/s]
Profiling:  56%|█████▌    | 204/363 [00:04<00:01, 86.88it/s]
Profiling:  61%|██████    | 220/363 [00:04<00:01, 100.34it/s]
Profiling:  64%|██████▍   | 232/363 [00:04<00:01, 89.83it/s] 
Profiling:  68%|██████▊   | 247/363 [00:04<00:01, 100.61it/s]
Profiling:  71%|███████   | 258/363 [00:04<00:01, 93.60it/s] 
Profiling:  74%|███████▍  | 270/363 [00:04<00:00, 99.11it/s]
Profiling:  78%|███████▊  | 284/363 [00:05<00:00, 109.36it/s]
Profiling:  82%|████████▏ | 296/363 [00:05<00:00, 92.21it/s] 
Profiling:  85%|████████▌ | 309/363 [00:05<00:00, 100.41it/s]
Profiling:  88%|████████▊ | 320/363 [00:05<00:00, 87.40it/s] 
Profiling:  93%|█████████▎| 336/363 [00:05<00:00, 104.34it/s]
Profiling:  96%|█████████▌| 348/363 [00:07<00:00, 22.92it/s] 
Profiling: 100%|██████████| 363/363 [00:07<00:00, 49.40it/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: quantized model in 24.929s
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/anhnv125-llama-op-v17-1-v34/mkml_model.tensors
anhnv125-llama-op-v17-1-v34-mkmlizer: 
config.json:   0%|          | 0.00/983 [00:00<?, ?B/s]
config.json: 100%|██████████| 983/983 [00:00<00:00, 10.7MB/s]
anhnv125-llama-op-v17-1-v34-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.
anhnv125-llama-op-v17-1-v34-mkmlizer:   warnings.warn(
anhnv125-llama-op-v17-1-v34-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/445 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 2.67MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
vocab.json:   0%|          | 0.00/798k [00:00<?, ?B/s]
vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 25.1MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]
merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 6.71MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 22.8MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/441 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 5.17MB/s]
anhnv125-llama-op-v17-1-v34-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.
anhnv125-llama-op-v17-1-v34-mkmlizer:   warnings.warn(
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/10.5k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 10.5k/10.5k [00:00<00:00, 74.4MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
Downloading shards:   0%|          | 0/1 [00:00<?, ?it/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00001-of-00001.safetensors:   0%|          | 0.00/249M [00:00<?, ?B/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00001-of-00001.safetensors:   8%|▊         | 21.0M/249M [00:00<00:01, 199MB/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: 
model-00001-of-00001.safetensors:  25%|██▌       | 62.9M/249M [00:00<00:00, 319MB/s]
model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:00<00:00, 935MB/s] 
anhnv125-llama-op-v17-1-v34-mkmlizer: 
Downloading shards: 100%|██████████| 1/1 [00:00<00:00,  1.30it/s]
Downloading shards: 100%|██████████| 1/1 [00:00<00:00,  1.30it/s]
anhnv125-llama-op-v17-1-v34-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
anhnv125-llama-op-v17-1-v34-mkmlizer: Saving duration: 0.373s
anhnv125-llama-op-v17-1-v34-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 2.772s
anhnv125-llama-op-v17-1-v34-mkmlizer: creating bucket guanaco-reward-models
anhnv125-llama-op-v17-1-v34-mkmlizer: Bucket 's3://guanaco-reward-models/' created
anhnv125-llama-op-v17-1-v34-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/config.json
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/tokenizer_config.json
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/special_tokens_map.json
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/merges.txt
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/vocab.json
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/tokenizer.json
anhnv125-llama-op-v17-1-v34-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/anhnv125-llama-op-v17-1-v34_reward/reward.tensors
Job anhnv125-llama-op-v17-1-v34-mkmlizer completed after 86.19s with status: succeeded
Stopping job with name anhnv125-llama-op-v17-1-v34-mkmlizer
Pipeline stage MKMLizer completed in 88.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.40s
Running pipeline stage ISVCDeployer
Creating inference service anhnv125-llama-op-v17-1-v34
Waiting for inference service anhnv125-llama-op-v17-1-v34 to be ready
Inference service anhnv125-llama-op-v17-1-v34 ready after 50.750283002853394s
Pipeline stage ISVCDeployer completed in 58.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4922680854797363s
Received healthy response to inference request in 2.352696180343628s
Received healthy response to inference request in 2.4456310272216797s
Received healthy response to inference request in 2.4763565063476562s
Received healthy response to inference request in 2.3145554065704346s
5 requests
0 failed requests
5th percentile: 2.3221835613250734
10th percentile: 2.329811716079712
20th percentile: 2.345068025588989
30th percentile: 2.3712831497192384
40th percentile: 2.408457088470459
50th percentile: 2.4456310272216797
60th percentile: 2.4579212188720705
70th percentile: 2.470211410522461
80th percentile: 2.6795388221740724
90th percentile: 3.0859034538269046
95th percentile: 3.2890857696533202
99th percentile: 3.451631622314453
mean time: 2.616301441192627
Pipeline stage StressChecker completed in 16.45s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.13s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.46s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
%s, retrying in %s seconds...
anhnv125-llama-op-v17-1_v34 status is now inactive due to auto deactivation removed underperforming models
anhnv125-llama-op-v17-1_v34 status is now deployed due to admin request
anhnv125-llama-op-v17-1_v34 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of anhnv125-llama-op-v17-1_v34
Running pipeline stage ISVCDeleter
Checking if service anhnv125-llama-op-v17-1-v34 is running
Tearing down inference service anhnv125-llama-op-v17-1-v34
Toredown service anhnv125-llama-op-v17-1-v34
Pipeline stage ISVCDeleter completed in 11.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key anhnv125-llama-op-v17-1-v34/added_tokens.json from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/config.json from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/tokenizer.json from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/tokenizer.model from bucket guanaco-mkml-models
Deleting key anhnv125-llama-op-v17-1-v34/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key anhnv125-llama-op-v17-1-v34_reward/config.json from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/merges.txt from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/reward.tensors from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key anhnv125-llama-op-v17-1-v34_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
anhnv125-llama-op-v17-1_v34 status is now torndown due to DeploymentManager action