submission_id: khanhnto-khanhnto_v64
developer_uid: chai_backend_admin
status: torndown
model_repo: khanhnto/khanhnto
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 0.7, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.8, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '<\\s>', '###'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\n\n{bot_name}'s Persona: {memory}.\n\nPlay the role of {bot_name}. Engage in a chat with {user_name} while stay in character. Do not write dialogues and narration for {user_name}. {bot_name} should response with messages of medium length.", '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}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-03-31T01:48:44+00:00
model_name: khanhnto-64
model_eval_status: success
model_group: khanhnto/khanhnto
num_battles: 129143
num_wins: 64840
celo_rating: 1154.21
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: khanhnto-64
ineligible_reason: propriety_total_count < 800
language_model: khanhnto/khanhnto
model_size: 13B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-30
win_ratio: 0.502079090620475
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name khanhnto-khanhnto-v64-mkmlizer
Waiting for job on khanhnto-khanhnto-v64-mkmlizer to finish
khanhnto-khanhnto-v64-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
khanhnto-khanhnto-v64-mkmlizer: ║     _____            __           __                                ║
khanhnto-khanhnto-v64-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
khanhnto-khanhnto-v64-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
khanhnto-khanhnto-v64-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
khanhnto-khanhnto-v64-mkmlizer: ║       /___/                                                         ║
khanhnto-khanhnto-v64-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v64-mkmlizer: ║  Version: 0.6.11                                                    ║
khanhnto-khanhnto-v64-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
khanhnto-khanhnto-v64-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v64-mkmlizer: ║  The license key for the current software has been verified as      ║
khanhnto-khanhnto-v64-mkmlizer: ║  belonging to:                                                      ║
khanhnto-khanhnto-v64-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v64-mkmlizer: ║  Chai Research Corp.                                                ║
khanhnto-khanhnto-v64-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
khanhnto-khanhnto-v64-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
khanhnto-khanhnto-v64-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v64-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
khanhnto-khanhnto-v64-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.1MB/s]
khanhnto-khanhnto-v64-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, 174kB/s]
khanhnto-khanhnto-v64-mkmlizer: 
config.json:   0%|          | 0.00/702 [00:00<?, ?B/s]
config.json: 100%|██████████| 702/702 [00:00<00:00, 9.62MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
generation_config.json:   0%|          | 0.00/137 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 2.28MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
model-00001-of-00006.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]
model-00001-of-00006.safetensors:   0%|          | 10.5M/4.98G [00:00<02:07, 39.0MB/s]
model-00001-of-00006.safetensors:   1%|          | 31.5M/4.98G [00:00<00:50, 97.2MB/s]
model-00001-of-00006.safetensors:   2%|▏         | 83.9M/4.98G [00:00<00:22, 216MB/s] 
model-00001-of-00006.safetensors:   4%|▍         | 210M/4.98G [00:00<00:09, 527MB/s] 
model-00001-of-00006.safetensors:   6%|▌         | 283M/4.98G [00:00<00:08, 530MB/s]
model-00001-of-00006.safetensors:   8%|▊         | 419M/4.98G [00:00<00:06, 724MB/s]
model-00001-of-00006.safetensors:  11%|█         | 545M/4.98G [00:00<00:05, 866MB/s]
model-00001-of-00006.safetensors:  13%|█▎        | 640M/4.98G [00:01<00:05, 781MB/s]
model-00001-of-00006.safetensors:  15%|█▍        | 734M/4.98G [00:01<00:06, 699MB/s]
model-00001-of-00006.safetensors:  17%|█▋        | 849M/4.98G [00:01<00:05, 797MB/s]
model-00001-of-00006.safetensors:  20%|█▉        | 975M/4.98G [00:01<00:04, 875MB/s]
model-00001-of-00006.safetensors:  22%|██▏       | 1.08G/4.98G [00:01<00:04, 915MB/s]
model-00001-of-00006.safetensors:  24%|██▍       | 1.18G/4.98G [00:01<00:04, 850MB/s]
model-00001-of-00006.safetensors:  26%|██▋       | 1.31G/4.98G [00:01<00:04, 888MB/s]
model-00001-of-00006.safetensors:  28%|██▊       | 1.41G/4.98G [00:01<00:04, 868MB/s]
model-00001-of-00006.safetensors:  31%|███       | 1.52G/4.98G [00:02<00:03, 923MB/s]
model-00001-of-00006.safetensors:  32%|███▏      | 1.61G/4.98G [00:02<00:04, 772MB/s]
model-00001-of-00006.safetensors:  34%|███▍      | 1.71G/4.98G [00:02<00:04, 813MB/s]
model-00001-of-00006.safetensors:  36%|███▌      | 1.80G/4.98G [00:02<00:04, 777MB/s]
model-00001-of-00006.safetensors:  39%|███▉      | 1.94G/4.98G [00:02<00:03, 912MB/s]
model-00001-of-00006.safetensors:  41%|████      | 2.04G/4.98G [00:02<00:03, 883MB/s]
model-00001-of-00006.safetensors:  44%|████▍     | 2.20G/4.98G [00:02<00:02, 1.03GB/s]
model-00001-of-00006.safetensors:  47%|████▋     | 2.32G/4.98G [00:03<00:02, 920MB/s] 
model-00001-of-00006.safetensors:  49%|████▉     | 2.45G/4.98G [00:03<00:02, 977MB/s]
model-00001-of-00006.safetensors:  51%|█████▏    | 2.56G/4.98G [00:03<00:02, 984MB/s]
model-00001-of-00006.safetensors:  54%|█████▎    | 2.66G/4.98G [00:03<00:02, 976MB/s]
model-00001-of-00006.safetensors:  56%|█████▌    | 2.77G/4.98G [00:03<00:02, 954MB/s]
model-00001-of-00006.safetensors:  58%|█████▊    | 2.87G/4.98G [00:03<00:02, 915MB/s]
model-00001-of-00006.safetensors:  60%|█████▉    | 2.98G/4.98G [00:03<00:02, 948MB/s]
model-00001-of-00006.safetensors:  62%|██████▏   | 3.08G/4.98G [00:03<00:02, 867MB/s]
model-00001-of-00006.safetensors:  64%|██████▍   | 3.18G/4.98G [00:03<00:02, 811MB/s]
model-00001-of-00006.safetensors:  66%|██████▌   | 3.26G/4.98G [00:04<00:02, 787MB/s]
model-00001-of-00006.safetensors:  67%|██████▋   | 3.36G/4.98G [00:04<00:02, 804MB/s]
model-00001-of-00006.safetensors:  70%|███████   | 3.49G/4.98G [00:04<00:01, 944MB/s]
model-00001-of-00006.safetensors:  72%|███████▏  | 3.61G/4.98G [00:04<00:01, 979MB/s]
model-00001-of-00006.safetensors:  75%|███████▍  | 3.71G/4.98G [00:04<00:01, 982MB/s]
model-00001-of-00006.safetensors:  78%|███████▊  | 3.88G/4.98G [00:04<00:00, 1.17GB/s]
model-00001-of-00006.safetensors:  81%|████████  | 4.04G/4.98G [00:04<00:00, 1.24GB/s]
model-00001-of-00006.safetensors:  85%|████████▍ | 4.21G/4.98G [00:04<00:00, 1.35GB/s]
model-00001-of-00006.safetensors:  87%|████████▋ | 4.35G/4.98G [00:04<00:00, 1.30GB/s]
model-00001-of-00006.safetensors:  90%|█████████ | 4.50G/4.98G [00:05<00:00, 1.31GB/s]
model-00001-of-00006.safetensors:  95%|█████████▍| 4.71G/4.98G [00:05<00:00, 1.44GB/s]
model-00001-of-00006.safetensors:  97%|█████████▋| 4.85G/4.98G [00:05<00:00, 1.20GB/s]
model-00001-of-00006.safetensors: 100%|█████████▉| 4.98G/4.98G [00:10<00:00, 85.2MB/s]
model-00001-of-00006.safetensors: 100%|█████████▉| 4.98G/4.98G [00:10<00:00, 455MB/s] 
khanhnto-khanhnto-v64-mkmlizer: 
model-00002-of-00006.safetensors:   0%|          | 0.00/4.97G [00:00<?, ?B/s]
model-00002-of-00006.safetensors:   0%|          | 10.5M/4.97G [00:00<01:10, 70.4MB/s]
model-00002-of-00006.safetensors:   1%|          | 41.9M/4.97G [00:00<00:28, 170MB/s] 
model-00002-of-00006.safetensors:   3%|▎         | 136M/4.97G [00:00<00:11, 438MB/s] 
model-00002-of-00006.safetensors:   4%|▍         | 220M/4.97G [00:00<00:08, 571MB/s]
model-00002-of-00006.safetensors:   7%|▋         | 357M/4.97G [00:00<00:05, 825MB/s]
model-00002-of-00006.safetensors:  10%|█         | 514M/4.97G [00:00<00:04, 963MB/s]
model-00002-of-00006.safetensors:  13%|█▎        | 640M/4.97G [00:00<00:04, 1.04GB/s]
model-00002-of-00006.safetensors:  18%|█▊        | 891M/4.97G [00:00<00:02, 1.46GB/s]
model-00002-of-00006.safetensors:  21%|██        | 1.05G/4.97G [00:01<00:03, 1.13GB/s]
model-00002-of-00006.safetensors:  24%|██▍       | 1.18G/4.97G [00:01<00:04, 941MB/s] 
model-00002-of-00006.safetensors:  27%|██▋       | 1.33G/4.97G [00:01<00:03, 1.05GB/s]
model-00002-of-00006.safetensors:  29%|██▉       | 1.46G/4.97G [00:01<00:03, 930MB/s] 
model-00002-of-00006.safetensors:  31%|███▏      | 1.56G/4.97G [00:01<00:04, 806MB/s]
model-00002-of-00006.safetensors:  34%|███▍      | 1.70G/4.97G [00:01<00:03, 908MB/s]
model-00002-of-00006.safetensors:  37%|███▋      | 1.85G/4.97G [00:02<00:03, 1.03GB/s]
model-00002-of-00006.safetensors:  39%|███▉      | 1.96G/4.97G [00:02<00:03, 998MB/s] 
model-00002-of-00006.safetensors:  42%|████▏     | 2.08G/4.97G [00:02<00:03, 880MB/s]
model-00002-of-00006.safetensors:  44%|████▍     | 2.18G/4.97G [00:02<00:03, 885MB/s]
model-00002-of-00006.safetensors:  46%|████▌     | 2.28G/4.97G [00:02<00:03, 776MB/s]
model-00002-of-00006.safetensors:  49%|████▉     | 2.45G/4.97G [00:02<00:02, 990MB/s]
model-00002-of-00006.safetensors:  52%|█████▏    | 2.58G/4.97G [00:02<00:02, 1.04GB/s]
model-00002-of-00006.safetensors:  54%|█████▍    | 2.69G/4.97G [00:03<00:02, 839MB/s] 
model-00002-of-00006.safetensors:  57%|█████▋    | 2.81G/4.97G [00:03<00:02, 896MB/s]
model-00002-of-00006.safetensors:  59%|█████▊    | 2.92G/4.97G [00:03<00:02, 705MB/s]
model-00002-of-00006.safetensors:  62%|██████▏   | 3.06G/4.97G [00:03<00:02, 856MB/s]
model-00002-of-00006.safetensors:  64%|██████▎   | 3.17G/4.97G [00:03<00:02, 828MB/s]
model-00002-of-00006.safetensors:  66%|██████▌   | 3.26G/4.97G [00:03<00:02, 833MB/s]
model-00002-of-00006.safetensors:  69%|██████▊   | 3.41G/4.97G [00:03<00:01, 893MB/s]
model-00002-of-00006.safetensors:  70%|███████   | 3.50G/4.97G [00:03<00:01, 829MB/s]
model-00002-of-00006.safetensors:  73%|███████▎  | 3.63G/4.97G [00:04<00:01, 892MB/s]
model-00002-of-00006.safetensors:  75%|███████▍  | 3.72G/4.97G [00:04<00:01, 859MB/s]
model-00002-of-00006.safetensors:  77%|███████▋  | 3.83G/4.97G [00:04<00:01, 905MB/s]
model-00002-of-00006.safetensors:  79%|███████▉  | 3.94G/4.97G [00:04<00:01, 918MB/s]
model-00002-of-00006.safetensors:  82%|████████▏ | 4.07G/4.97G [00:04<00:00, 996MB/s]
model-00002-of-00006.safetensors:  85%|████████▍ | 4.22G/4.97G [00:04<00:00, 1.11GB/s]
model-00002-of-00006.safetensors:  87%|████████▋ | 4.33G/4.97G [00:04<00:00, 1.07GB/s]
model-00002-of-00006.safetensors:  90%|█████████ | 4.49G/4.97G [00:04<00:00, 1.21GB/s]
model-00002-of-00006.safetensors:  97%|█████████▋| 4.84G/4.97G [00:04<00:00, 1.86GB/s]
model-00002-of-00006.safetensors: 100%|█████████▉| 4.97G/4.97G [00:05<00:00, 966MB/s] 
khanhnto-khanhnto-v64-mkmlizer: 
model-00003-of-00006.safetensors:   0%|          | 0.00/4.97G [00:00<?, ?B/s]
model-00003-of-00006.safetensors:   0%|          | 10.5M/4.97G [00:00<01:02, 79.1MB/s]
model-00003-of-00006.safetensors:   2%|▏         | 83.9M/4.97G [00:00<00:12, 384MB/s] 
model-00003-of-00006.safetensors:   3%|▎         | 126M/4.97G [00:00<00:12, 388MB/s] 
model-00003-of-00006.safetensors:   4%|▍         | 189M/4.97G [00:00<00:10, 474MB/s]
model-00003-of-00006.safetensors:   7%|▋         | 336M/4.97G [00:00<00:05, 810MB/s]
model-00003-of-00006.safetensors:   8%|▊         | 419M/4.97G [00:00<00:05, 776MB/s]
model-00003-of-00006.safetensors:  11%|█         | 535M/4.97G [00:00<00:04, 889MB/s]
model-00003-of-00006.safetensors:  13%|█▎        | 629M/4.97G [00:00<00:06, 713MB/s]
model-00003-of-00006.safetensors:  16%|█▌        | 786M/4.97G [00:01<00:04, 930MB/s]
model-00003-of-00006.safetensors:  18%|█▊        | 891M/4.97G [00:01<00:04, 905MB/s]
model-00003-of-00006.safetensors:  21%|██        | 1.04G/4.97G [00:01<00:03, 1.04GB/s]
model-00003-of-00006.safetensors:  23%|██▎       | 1.16G/4.97G [00:01<00:03, 1.09GB/s]
model-00003-of-00006.safetensors:  28%|██▊       | 1.37G/4.97G [00:01<00:02, 1.32GB/s]
model-00003-of-00006.safetensors:  30%|███       | 1.51G/4.97G [00:01<00:03, 878MB/s] 
model-00003-of-00006.safetensors:  33%|███▎      | 1.64G/4.97G [00:01<00:03, 942MB/s]
model-00003-of-00006.safetensors:  36%|███▌      | 1.77G/4.97G [00:02<00:03, 1.01GB/s]
model-00003-of-00006.safetensors:  43%|████▎     | 2.16G/4.97G [00:02<00:01, 1.69GB/s]
model-00003-of-00006.safetensors:  47%|████▋     | 2.36G/4.97G [00:02<00:01, 1.66GB/s]
model-00003-of-00006.safetensors:  51%|█████▏    | 2.56G/4.97G [00:02<00:01, 1.72GB/s]
model-00003-of-00006.safetensors:  55%|█████▌    | 2.75G/4.97G [00:02<00:01, 1.63GB/s]
model-00003-of-00006.safetensors:  59%|█████▉    | 2.93G/4.97G [00:02<00:01, 1.50GB/s]
model-00003-of-00006.safetensors:  64%|██████▍   | 3.18G/4.97G [00:02<00:01, 1.70GB/s]
model-00003-of-00006.safetensors:  69%|██████▉   | 3.45G/4.97G [00:02<00:00, 1.91GB/s]
model-00003-of-00006.safetensors:  75%|███████▌  | 3.73G/4.97G [00:02<00:00, 2.13GB/s]
model-00003-of-00006.safetensors:  80%|███████▉  | 3.96G/4.97G [00:03<00:00, 2.16GB/s]
model-00003-of-00006.safetensors:  85%|████████▌ | 4.25G/4.97G [00:03<00:00, 2.28GB/s]
model-00003-of-00006.safetensors:  90%|█████████ | 4.49G/4.97G [00:03<00:00, 2.30GB/s]
model-00003-of-00006.safetensors:  98%|█████████▊| 4.87G/4.97G [00:03<00:00, 2.71GB/s]
model-00003-of-00006.safetensors: 100%|█████████▉| 4.97G/4.97G [00:03<00:00, 1.42GB/s]
khanhnto-khanhnto-v64-mkmlizer: 
model-00004-of-00006.safetensors:   0%|          | 0.00/4.93G [00:00<?, ?B/s]
model-00004-of-00006.safetensors:   0%|          | 10.5M/4.93G [00:00<01:42, 48.1MB/s]
model-00004-of-00006.safetensors:   1%|▏         | 62.9M/4.93G [00:00<00:26, 183MB/s] 
model-00004-of-00006.safetensors:   5%|▍         | 241M/4.93G [00:00<00:07, 648MB/s] 
model-00004-of-00006.safetensors:   8%|▊         | 388M/4.93G [00:00<00:05, 885MB/s]
model-00004-of-00006.safetensors:  11%|█▏        | 566M/4.93G [00:00<00:03, 1.15GB/s]
model-00004-of-00006.safetensors:  15%|█▌        | 744M/4.93G [00:00<00:03, 1.32GB/s]
model-00004-of-00006.safetensors:  20%|█▉        | 975M/4.93G [00:00<00:02, 1.61GB/s]
model-00004-of-00006.safetensors:  23%|██▎       | 1.15G/4.93G [00:01<00:02, 1.49GB/s]
model-00004-of-00006.safetensors:  27%|██▋       | 1.32G/4.93G [00:01<00:02, 1.22GB/s]
model-00004-of-00006.safetensors:  30%|██▉       | 1.46G/4.93G [00:01<00:02, 1.21GB/s]
model-00004-of-00006.safetensors:  32%|███▏      | 1.59G/4.93G [00:01<00:03, 1.07GB/s]
model-00004-of-00006.safetensors:  35%|███▍      | 1.72G/4.93G [00:01<00:03, 1.00GB/s]
model-00004-of-00006.safetensors:  37%|███▋      | 1.84G/4.93G [00:01<00:03, 995MB/s] 
model-00004-of-00006.safetensors:  39%|███▉      | 1.94G/4.93G [00:01<00:03, 945MB/s]
model-00004-of-00006.safetensors:  42%|████▏     | 2.08G/4.93G [00:02<00:02, 1.04GB/s]
model-00004-of-00006.safetensors:  45%|████▌     | 2.23G/4.93G [00:02<00:02, 1.16GB/s]
model-00004-of-00006.safetensors:  48%|████▊     | 2.39G/4.93G [00:02<00:02, 1.26GB/s]
model-00004-of-00006.safetensors:  52%|█████▏    | 2.57G/4.93G [00:02<00:01, 1.38GB/s]
model-00004-of-00006.safetensors:  57%|█████▋    | 2.82G/4.93G [00:02<00:01, 1.68GB/s]
model-00004-of-00006.safetensors:  61%|██████    | 3.00G/4.93G [00:02<00:01, 1.43GB/s]
model-00004-of-00006.safetensors:  64%|██████▍   | 3.17G/4.93G [00:02<00:01, 1.46GB/s]
model-00004-of-00006.safetensors:  67%|██████▋   | 3.32G/4.93G [00:02<00:01, 1.38GB/s]
model-00004-of-00006.safetensors:  72%|███████▏  | 3.58G/4.93G [00:02<00:00, 1.56GB/s]
model-00004-of-00006.safetensors:  76%|███████▋  | 3.76G/4.93G [00:03<00:00, 1.64GB/s]
model-00004-of-00006.safetensors:  81%|████████▏ | 4.02G/4.93G [00:03<00:00, 1.84GB/s]
model-00004-of-00006.safetensors:  86%|████████▋ | 4.26G/4.93G [00:03<00:00, 1.90GB/s]
model-00004-of-00006.safetensors:  94%|█████████▍| 4.65G/4.93G [00:03<00:00, 2.44GB/s]
model-00004-of-00006.safetensors: 100%|█████████▉| 4.91G/4.93G [00:03<00:00, 2.11GB/s]
model-00004-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:03<00:00, 1.25GB/s]
khanhnto-khanhnto-v64-mkmlizer: 
model-00005-of-00006.safetensors:   0%|          | 0.00/4.93G [00:00<?, ?B/s]
model-00005-of-00006.safetensors:   0%|          | 10.5M/4.93G [00:00<01:01, 80.6MB/s]
model-00005-of-00006.safetensors:   2%|▏         | 115M/4.93G [00:00<00:08, 564MB/s]  
model-00005-of-00006.safetensors:   4%|▍         | 189M/4.93G [00:00<00:07, 618MB/s]
model-00005-of-00006.safetensors:   6%|▌         | 283M/4.93G [00:00<00:06, 714MB/s]
model-00005-of-00006.safetensors:   7%|▋         | 367M/4.93G [00:00<00:06, 747MB/s]
model-00005-of-00006.safetensors:  11%|█         | 524M/4.93G [00:00<00:05, 853MB/s]
model-00005-of-00006.safetensors:  14%|█▍        | 682M/4.93G [00:00<00:04, 1.01GB/s]
model-00005-of-00006.safetensors:  17%|█▋        | 839M/4.93G [00:00<00:03, 1.10GB/s]
model-00005-of-00006.safetensors:  19%|█▉        | 954M/4.93G [00:01<00:04, 925MB/s] 
model-00005-of-00006.safetensors:  23%|██▎       | 1.15G/4.93G [00:01<00:03, 1.13GB/s]
model-00005-of-00006.safetensors:  26%|██▌       | 1.28G/4.93G [00:01<00:03, 1.12GB/s]
model-00005-of-00006.safetensors:  29%|██▉       | 1.45G/4.93G [00:01<00:02, 1.26GB/s]
model-00005-of-00006.safetensors:  33%|███▎      | 1.63G/4.93G [00:01<00:02, 1.39GB/s]
model-00005-of-00006.safetensors:  36%|███▋      | 1.79G/4.93G [00:01<00:02, 1.43GB/s]
model-00005-of-00006.safetensors:  40%|███▉      | 1.97G/4.93G [00:01<00:01, 1.51GB/s]
model-00005-of-00006.safetensors:  44%|████▍     | 2.17G/4.93G [00:01<00:01, 1.61GB/s]
model-00005-of-00006.safetensors:  49%|████▊     | 2.40G/4.93G [00:01<00:01, 1.77GB/s]
model-00005-of-00006.safetensors:  52%|█████▏    | 2.59G/4.93G [00:02<00:01, 1.77GB/s]
model-00005-of-00006.safetensors:  56%|█████▌    | 2.77G/4.93G [00:02<00:01, 1.60GB/s]
model-00005-of-00006.safetensors:  61%|██████    | 3.00G/4.93G [00:02<00:01, 1.77GB/s]
model-00005-of-00006.safetensors:  65%|██████▍   | 3.19G/4.93G [00:02<00:01, 1.73GB/s]
model-00005-of-00006.safetensors:  68%|██████▊   | 3.37G/4.93G [00:02<00:00, 1.70GB/s]
model-00005-of-00006.safetensors:  73%|███████▎  | 3.61G/4.93G [00:02<00:00, 1.88GB/s]
model-00005-of-00006.safetensors:  77%|███████▋  | 3.81G/4.93G [00:02<00:00, 1.83GB/s]
model-00005-of-00006.safetensors:  83%|████████▎ | 4.08G/4.93G [00:02<00:00, 2.07GB/s]
model-00005-of-00006.safetensors:  87%|████████▋ | 4.31G/4.93G [00:02<00:00, 2.14GB/s]
model-00005-of-00006.safetensors:  97%|█████████▋| 4.77G/4.93G [00:03<00:00, 2.83GB/s]
model-00005-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:03<00:00, 1.39GB/s]
khanhnto-khanhnto-v64-mkmlizer: 
model-00006-of-00006.safetensors:   0%|          | 0.00/1.25G [00:00<?, ?B/s]
model-00006-of-00006.safetensors:   1%|          | 10.5M/1.25G [00:00<00:31, 39.4MB/s]
model-00006-of-00006.safetensors:   9%|▉         | 115M/1.25G [00:00<00:03, 367MB/s]  
model-00006-of-00006.safetensors:  21%|██        | 262M/1.25G [00:00<00:01, 701MB/s]
model-00006-of-00006.safetensors:  33%|███▎      | 409M/1.25G [00:00<00:00, 935MB/s]
model-00006-of-00006.safetensors:  43%|████▎     | 535M/1.25G [00:00<00:00, 1.02GB/s]
model-00006-of-00006.safetensors:  55%|█████▍    | 679M/1.25G [00:00<00:00, 1.14GB/s]
model-00006-of-00006.safetensors:  77%|███████▋  | 962M/1.25G [00:00<00:00, 1.64GB/s]
model-00006-of-00006.safetensors: 100%|█████████▉| 1.25G/1.25G [00:01<00:00, 1.24GB/s]
khanhnto-khanhnto-v64-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, 15.5MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/548 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 548/548 [00:00<00:00, 5.91MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 17.9MB/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 17.8MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 58.4MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/1.02k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.02k/1.02k [00:00<00:00, 12.2MB/s]
khanhnto-khanhnto-v64-mkmlizer: Downloaded to shared memory in 30.846s
khanhnto-khanhnto-v64-mkmlizer: quantizing model to /dev/shm/model_cache
khanhnto-khanhnto-v64-mkmlizer: Saving mkml model at /dev/shm/model_cache
khanhnto-khanhnto-v64-mkmlizer: Reading /tmp/tmp7gj6rlpg/model.safetensors.index.json
khanhnto-khanhnto-v64-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:01<09:32,  1.58s/it]
Profiling:   2%|▏         | 8/363 [00:01<00:55,  6.36it/s]
Profiling:   4%|▍         | 16/363 [00:01<00:24, 14.11it/s]
Profiling:   7%|▋         | 25/363 [00:01<00:14, 23.84it/s]
Profiling:   9%|▉         | 32/363 [00:02<00:10, 30.71it/s]
Profiling:  11%|█▏        | 41/363 [00:02<00:07, 40.80it/s]
Profiling:  14%|█▍        | 50/363 [00:02<00:06, 50.05it/s]
Profiling:  16%|█▋        | 59/363 [00:02<00:05, 58.15it/s]
Profiling:  19%|█▉        | 69/363 [00:02<00:06, 43.22it/s]
Profiling:  21%|██        | 76/363 [00:02<00:06, 45.93it/s]
Profiling:  23%|██▎       | 83/363 [00:02<00:05, 49.84it/s]
Profiling:  25%|██▍       | 90/363 [00:03<00:05, 53.07it/s]
Profiling:  27%|██▋       | 99/363 [00:03<00:04, 60.28it/s]
Profiling:  30%|██▉       | 108/363 [00:03<00:03, 65.09it/s]
Profiling:  33%|███▎      | 118/363 [00:03<00:03, 71.70it/s]
Profiling:  35%|███▍      | 126/363 [00:03<00:03, 71.82it/s]
Profiling:  37%|███▋      | 134/363 [00:03<00:03, 72.90it/s]
Profiling:  39%|███▉      | 142/363 [00:03<00:05, 42.56it/s]
Profiling:  41%|████      | 149/363 [00:04<00:04, 47.32it/s]
Profiling:  44%|████▎     | 158/363 [00:04<00:03, 54.92it/s]
Profiling:  46%|████▌     | 167/363 [00:04<00:03, 60.15it/s]
Profiling:  48%|████▊     | 175/363 [00:04<00:02, 64.00it/s]
Profiling:  50%|█████     | 183/363 [00:04<00:02, 67.43it/s]
Profiling:  53%|█████▎    | 191/363 [00:04<00:02, 69.72it/s]
Profiling:  55%|█████▍    | 199/363 [00:04<00:02, 68.43it/s]
Profiling:  57%|█████▋    | 207/363 [00:04<00:02, 68.81it/s]
Profiling:  59%|█████▉    | 215/363 [00:05<00:03, 41.63it/s]
Profiling:  61%|██████    | 221/363 [00:05<00:03, 44.76it/s]
Profiling:  63%|██████▎   | 229/363 [00:05<00:02, 51.40it/s]
Profiling:  65%|██████▌   | 237/363 [00:05<00:02, 57.44it/s]
Profiling:  68%|██████▊   | 246/363 [00:05<00:01, 63.16it/s]
Profiling:  70%|███████   | 255/363 [00:05<00:01, 66.83it/s]
Profiling:  73%|███████▎  | 264/363 [00:05<00:01, 70.19it/s]
Profiling:  75%|███████▍  | 272/363 [00:05<00:01, 69.93it/s]
Profiling:  77%|███████▋  | 280/363 [00:06<00:01, 44.24it/s]
Profiling:  79%|███████▉  | 288/363 [00:06<00:01, 50.62it/s]
Profiling:  82%|████████▏ | 296/363 [00:06<00:01, 56.55it/s]
Profiling:  84%|████████▎ | 304/363 [00:06<00:00, 61.39it/s]
Profiling:  86%|████████▌ | 312/363 [00:06<00:00, 64.92it/s]
Profiling:  88%|████████▊ | 320/363 [00:06<00:00, 63.50it/s]
Profiling:  90%|█████████ | 328/363 [00:06<00:00, 67.46it/s]
Profiling:  93%|█████████▎| 337/363 [00:07<00:00, 68.39it/s]
Profiling:  95%|█████████▌| 345/363 [00:07<00:00, 67.94it/s]
Profiling:  97%|█████████▋| 353/363 [00:09<00:00, 12.11it/s]
Profiling:  99%|█████████▉| 360/363 [00:09<00:00, 15.56it/s]
Profiling: 100%|██████████| 363/363 [00:09<00:00, 38.82it/s]
khanhnto-khanhnto-v64-mkmlizer: quantized model in 29.662s
khanhnto-khanhnto-v64-mkmlizer: Processed model khanhnto/khanhnto in 62.353s
khanhnto-khanhnto-v64-mkmlizer: creating bucket guanaco-mkml-models
khanhnto-khanhnto-v64-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
khanhnto-khanhnto-v64-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/khanhnto-khanhnto-v64
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v64/config.json
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/khanhnto-khanhnto-v64/special_tokens_map.json
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/khanhnto-khanhnto-v64/added_tokens.json
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v64/tokenizer_config.json
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/khanhnto-khanhnto-v64/tokenizer.model
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/khanhnto-khanhnto-v64/tokenizer.json
khanhnto-khanhnto-v64-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/khanhnto-khanhnto-v64/mkml_model.tensors
khanhnto-khanhnto-v64-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
khanhnto-khanhnto-v64-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.
khanhnto-khanhnto-v64-mkmlizer:   warnings.warn(
khanhnto-khanhnto-v64-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 13.1MB/s]
khanhnto-khanhnto-v64-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|          | 10.5M/1.44G [00:00<00:15, 93.1MB/s]
pytorch_model.bin:   4%|▎         | 52.4M/1.44G [00:00<00:06, 214MB/s] 
pytorch_model.bin:  12%|█▏        | 168M/1.44G [00:00<00:02, 554MB/s] 
pytorch_model.bin:  16%|█▌        | 231M/1.44G [00:00<00:02, 496MB/s]
pytorch_model.bin:  20%|██        | 294M/1.44G [00:00<00:02, 511MB/s]
pytorch_model.bin:  37%|███▋      | 535M/1.44G [00:00<00:00, 1.03GB/s]
pytorch_model.bin:  48%|████▊     | 700M/1.44G [00:00<00:00, 1.14GB/s]
pytorch_model.bin:  59%|█████▉    | 857M/1.44G [00:00<00:00, 1.19GB/s]
pytorch_model.bin:  69%|██████▉   | 994M/1.44G [00:01<00:00, 1.18GB/s]
pytorch_model.bin:  87%|████████▋ | 1.26G/1.44G [00:01<00:00, 1.56GB/s]
pytorch_model.bin:  99%|█████████▊| 1.42G/1.44G [00:01<00:00, 867MB/s] 
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 600MB/s]
khanhnto-khanhnto-v64-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
khanhnto-khanhnto-v64-mkmlizer: Saving duration: 0.292s
khanhnto-khanhnto-v64-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.753s
khanhnto-khanhnto-v64-mkmlizer: creating bucket guanaco-reward-models
khanhnto-khanhnto-v64-mkmlizer: Bucket 's3://guanaco-reward-models/' created
khanhnto-khanhnto-v64-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/config.json
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/special_tokens_map.json
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/tokenizer_config.json
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/merges.txt
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/vocab.json
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/tokenizer.json
khanhnto-khanhnto-v64-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/khanhnto-khanhnto-v64_reward/reward.tensors
Failed to get response for submission thanhdaonguyen-once-upon-a-t_v35: HTTPConnectionPool(host='thanhdaonguyen-once-upon-a-t-v35-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
Exception raised while processing tagging_function
Traceback (most recent call last):
  File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api
    conversation_tag = self.tagging_function(conversation_state)
  File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length
TypeError: 'ConversationState' object is not subscriptable

Job khanhnto-khanhnto-v64-mkmlizer completed after 96.02s with status: succeeded
Stopping job with name khanhnto-khanhnto-v64-mkmlizer
Pipeline stage MKMLizer completed in 96.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service khanhnto-khanhnto-v64
Waiting for inference service khanhnto-khanhnto-v64 to be ready
Inference service khanhnto-khanhnto-v64 ready after 50.34459185600281s
Pipeline stage ISVCDeployer completed in 56.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.236497163772583s
Received healthy response to inference request in 0.9389247894287109s
Received healthy response to inference request in 1.7187120914459229s
Received healthy response to inference request in 1.521423101425171s
Failed to get response for submission thanhdaonguyen-once-upon-a-t_v35: HTTPConnectionPool(host='thanhdaonguyen-once-upon-a-t-v35-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
Received healthy response to inference request in 1.40797758102417s
5 requests
0 failed requests
5th percentile: 1.0327353477478027
10th percentile: 1.1265459060668945
20th percentile: 1.3141670227050781
30th percentile: 1.4306666851043701
40th percentile: 1.4760448932647705
50th percentile: 1.521423101425171
60th percentile: 1.6003386974334717
70th percentile: 1.6792542934417725
80th percentile: 1.822269105911255
90th percentile: 2.029383134841919
95th percentile: 2.132940149307251
99th percentile: 2.2157857608795166
mean time: 1.5647069454193114
Pipeline stage StressChecker completed in 8.65s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
khanhnto-khanhnto_v64 status is now deployed due to DeploymentManager action
AUTO_DEACTIVATION: submission %s deactivated %s
khanhnto-khanhnto_v64 status is now inactive due to auto deactivation removed underperforming models
khanhnto-khanhnto_v64 status is now deployed due to admin request
khanhnto-khanhnto_v64 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of khanhnto-khanhnto_v64
Running pipeline stage ISVCDeleter
Checking if service khanhnto-khanhnto-v64 is running
Tearing down inference service khanhnto-khanhnto-v64
Toredown service khanhnto-khanhnto-v64
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key khanhnto-khanhnto-v64/added_tokens.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/config.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/tokenizer.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/tokenizer.model from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v64/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key khanhnto-khanhnto-v64_reward/config.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/merges.txt from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/reward.tensors from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v64_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.48s
khanhnto-khanhnto_v64 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics