submission_id: khanhnto-khanhnto_v67
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': 156}
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: 2024-03-31T01:51:19+00:00
model_name: khanhnto-156
model_eval_status: success
model_group: khanhnto/khanhnto
num_battles: 129457
num_wins: 67257
celo_rating: 1166.29
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: 156
display_name: khanhnto-156
ineligible_reason: max_output_tokens!=64
language_model: khanhnto/khanhnto
model_size: 13B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-30
win_ratio: 0.5195315819152305
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name khanhnto-khanhnto-v67-mkmlizer
Waiting for job on khanhnto-khanhnto-v67-mkmlizer to finish
khanhnto-khanhnto-v67-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
khanhnto-khanhnto-v67-mkmlizer: ║     _____            __           __                                ║
khanhnto-khanhnto-v67-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
khanhnto-khanhnto-v67-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
khanhnto-khanhnto-v67-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
khanhnto-khanhnto-v67-mkmlizer: ║       /___/                                                         ║
khanhnto-khanhnto-v67-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v67-mkmlizer: ║  Version: 0.6.11                                                    ║
khanhnto-khanhnto-v67-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
khanhnto-khanhnto-v67-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v67-mkmlizer: ║  The license key for the current software has been verified as      ║
khanhnto-khanhnto-v67-mkmlizer: ║  belonging to:                                                      ║
khanhnto-khanhnto-v67-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v67-mkmlizer: ║  Chai Research Corp.                                                ║
khanhnto-khanhnto-v67-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
khanhnto-khanhnto-v67-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
khanhnto-khanhnto-v67-mkmlizer: ║                                                                     ║
khanhnto-khanhnto-v67-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
khanhnto-khanhnto-v67-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.9MB/s]
khanhnto-khanhnto-v67-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, 319kB/s]
khanhnto-khanhnto-v67-mkmlizer: 
config.json:   0%|          | 0.00/702 [00:00<?, ?B/s]
config.json: 100%|██████████| 702/702 [00:00<00:00, 10.7MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
generation_config.json:   0%|          | 0.00/137 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.27MB/s]
khanhnto-khanhnto-v67-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<01:25, 57.8MB/s]
model-00002-of-00006.safetensors:   1%|          | 41.9M/4.97G [00:00<00:34, 142MB/s] 
model-00002-of-00006.safetensors:   2%|▏         | 83.9M/4.97G [00:00<00:21, 223MB/s]
model-00002-of-00006.safetensors:   3%|▎         | 157M/4.97G [00:00<00:12, 384MB/s] 
model-00002-of-00006.safetensors:   5%|▍         | 231M/4.97G [00:00<00:09, 477MB/s]
model-00002-of-00006.safetensors:   7%|▋         | 336M/4.97G [00:00<00:07, 639MB/s]
model-00002-of-00006.safetensors:  11%|█         | 524M/4.97G [00:00<00:04, 986MB/s]
model-00002-of-00006.safetensors:  14%|█▍        | 713M/4.97G [00:00<00:03, 1.25GB/s]
model-00002-of-00006.safetensors:  18%|█▊        | 902M/4.97G [00:01<00:02, 1.42GB/s]
model-00002-of-00006.safetensors:  22%|██▏       | 1.10G/4.97G [00:01<00:02, 1.49GB/s]
model-00002-of-00006.safetensors:  25%|██▌       | 1.26G/4.97G [00:01<00:02, 1.40GB/s]
model-00002-of-00006.safetensors:  28%|██▊       | 1.41G/4.97G [00:01<00:02, 1.38GB/s]
model-00002-of-00006.safetensors:  31%|███       | 1.55G/4.97G [00:01<00:02, 1.28GB/s]
model-00002-of-00006.safetensors:  34%|███▍      | 1.69G/4.97G [00:01<00:02, 1.10GB/s]
model-00002-of-00006.safetensors:  37%|███▋      | 1.82G/4.97G [00:01<00:02, 1.11GB/s]
model-00002-of-00006.safetensors:  39%|███▉      | 1.94G/4.97G [00:02<00:03, 781MB/s] 
model-00002-of-00006.safetensors:  41%|████      | 2.03G/4.97G [00:02<00:03, 787MB/s]
model-00002-of-00006.safetensors:  43%|████▎     | 2.13G/4.97G [00:02<00:04, 694MB/s]
model-00002-of-00006.safetensors:  45%|████▍     | 2.21G/4.97G [00:02<00:04, 591MB/s]
model-00002-of-00006.safetensors:  46%|████▌     | 2.29G/4.97G [00:02<00:05, 536MB/s]
model-00002-of-00006.safetensors:  47%|████▋     | 2.35G/4.97G [00:02<00:04, 531MB/s]
model-00002-of-00006.safetensors:  49%|████▊     | 2.41G/4.97G [00:03<00:04, 551MB/s]
model-00002-of-00006.safetensors:  50%|█████     | 2.51G/4.97G [00:03<00:03, 617MB/s]
model-00002-of-00006.safetensors:  52%|█████▏    | 2.60G/4.97G [00:03<00:03, 692MB/s]
model-00002-of-00006.safetensors:  54%|█████▍    | 2.67G/4.97G [00:03<00:03, 694MB/s]
model-00002-of-00006.safetensors:  55%|█████▌    | 2.75G/4.97G [00:03<00:03, 585MB/s]
model-00002-of-00006.safetensors:  57%|█████▋    | 2.83G/4.97G [00:03<00:03, 634MB/s]
model-00002-of-00006.safetensors:  59%|█████▉    | 2.93G/4.97G [00:03<00:03, 676MB/s]
model-00002-of-00006.safetensors:  61%|██████    | 3.03G/4.97G [00:03<00:02, 761MB/s]
model-00002-of-00006.safetensors:  63%|██████▎   | 3.11G/4.97G [00:04<00:02, 683MB/s]
model-00002-of-00006.safetensors:  64%|██████▍   | 3.20G/4.97G [00:04<00:02, 722MB/s]
model-00002-of-00006.safetensors:  67%|██████▋   | 3.31G/4.97G [00:04<00:01, 834MB/s]
model-00002-of-00006.safetensors:  69%|██████▊   | 3.41G/4.97G [00:04<00:01, 795MB/s]
model-00002-of-00006.safetensors:  70%|███████   | 3.49G/4.97G [00:04<00:01, 798MB/s]
model-00002-of-00006.safetensors:  73%|███████▎  | 3.65G/4.97G [00:04<00:01, 979MB/s]
model-00002-of-00006.safetensors:  76%|███████▌  | 3.75G/4.97G [00:04<00:01, 972MB/s]
model-00002-of-00006.safetensors:  78%|███████▊  | 3.86G/4.97G [00:04<00:01, 811MB/s]
model-00002-of-00006.safetensors:  80%|███████▉  | 3.95G/4.97G [00:05<00:01, 742MB/s]
model-00002-of-00006.safetensors:  82%|████████▏ | 4.07G/4.97G [00:05<00:01, 835MB/s]
model-00002-of-00006.safetensors:  84%|████████▍ | 4.16G/4.97G [00:05<00:01, 576MB/s]
model-00002-of-00006.safetensors:  85%|████████▌ | 4.24G/4.97G [00:05<00:01, 382MB/s]
model-00002-of-00006.safetensors:  86%|████████▋ | 4.30G/4.97G [00:06<00:02, 293MB/s]
model-00002-of-00006.safetensors:  88%|████████▊ | 4.35G/4.97G [00:07<00:04, 149MB/s]
model-00002-of-00006.safetensors:  88%|████████▊ | 4.39G/4.97G [00:07<00:04, 131MB/s]
model-00002-of-00006.safetensors:  89%|████████▉ | 4.43G/4.97G [00:07<00:04, 132MB/s]
model-00002-of-00006.safetensors:  90%|████████▉ | 4.46G/4.97G [00:08<00:03, 140MB/s]
model-00002-of-00006.safetensors:  90%|█████████ | 4.48G/4.97G [00:08<00:03, 125MB/s]
model-00002-of-00006.safetensors:  91%|█████████▏| 4.54G/4.97G [00:08<00:02, 179MB/s]
model-00002-of-00006.safetensors:  93%|█████████▎| 4.61G/4.97G [00:08<00:01, 245MB/s]
model-00002-of-00006.safetensors:  94%|█████████▍| 4.69G/4.97G [00:08<00:00, 290MB/s]
model-00002-of-00006.safetensors:  96%|█████████▋| 4.79G/4.97G [00:08<00:00, 412MB/s]
model-00002-of-00006.safetensors: 100%|█████████▉| 4.95G/4.97G [00:09<00:00, 559MB/s]
model-00002-of-00006.safetensors: 100%|█████████▉| 4.97G/4.97G [00:09<00:00, 509MB/s]
khanhnto-khanhnto-v67-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<01:16, 64.6MB/s]
model-00003-of-00006.safetensors:   1%|▏         | 62.9M/4.97G [00:00<00:21, 229MB/s] 
model-00003-of-00006.safetensors:   3%|▎         | 157M/4.97G [00:00<00:11, 436MB/s] 
model-00003-of-00006.safetensors:   6%|▌         | 304M/4.97G [00:00<00:06, 727MB/s]
model-00003-of-00006.safetensors:   9%|▊         | 430M/4.97G [00:00<00:05, 883MB/s]
model-00003-of-00006.safetensors:  11%|█         | 556M/4.97G [00:00<00:04, 965MB/s]
model-00003-of-00006.safetensors:  15%|█▍        | 744M/4.97G [00:00<00:03, 1.23GB/s]
model-00003-of-00006.safetensors:  19%|█▉        | 954M/4.97G [00:01<00:03, 1.31GB/s]
model-00003-of-00006.safetensors:  22%|██▏       | 1.09G/4.97G [00:01<00:04, 876MB/s]
model-00003-of-00006.safetensors:  24%|██▍       | 1.22G/4.97G [00:01<00:04, 938MB/s]
model-00003-of-00006.safetensors:  27%|██▋       | 1.33G/4.97G [00:01<00:04, 745MB/s]
model-00003-of-00006.safetensors:  29%|██▊       | 1.43G/4.97G [00:01<00:04, 720MB/s]
model-00003-of-00006.safetensors:  31%|███       | 1.54G/4.97G [00:01<00:04, 787MB/s]
model-00003-of-00006.safetensors:  33%|███▎      | 1.64G/4.97G [00:02<00:04, 686MB/s]
model-00003-of-00006.safetensors:  35%|███▍      | 1.73G/4.97G [00:02<00:04, 701MB/s]
model-00003-of-00006.safetensors:  36%|███▋      | 1.81G/4.97G [00:02<00:04, 655MB/s]
model-00003-of-00006.safetensors:  38%|███▊      | 1.89G/4.97G [00:02<00:05, 599MB/s]
model-00003-of-00006.safetensors:  39%|███▉      | 1.96G/4.97G [00:02<00:05, 530MB/s]
model-00003-of-00006.safetensors:  41%|████      | 2.02G/4.97G [00:02<00:05, 503MB/s]
model-00003-of-00006.safetensors:  42%|████▏     | 2.10G/4.97G [00:03<00:05, 497MB/s]
model-00003-of-00006.safetensors:  43%|████▎     | 2.15G/4.97G [00:03<00:06, 454MB/s]
model-00003-of-00006.safetensors:  46%|████▌     | 2.28G/4.97G [00:03<00:04, 608MB/s]
model-00003-of-00006.safetensors:  47%|████▋     | 2.35G/4.97G [00:03<00:04, 628MB/s]
model-00003-of-00006.safetensors:  49%|████▊     | 2.42G/4.97G [00:03<00:03, 652MB/s]
model-00003-of-00006.safetensors:  50%|█████     | 2.50G/4.97G [00:03<00:04, 608MB/s]
model-00003-of-00006.safetensors:  52%|█████▏    | 2.57G/4.97G [00:03<00:03, 629MB/s]
model-00003-of-00006.safetensors:  53%|█████▎    | 2.65G/4.97G [00:03<00:03, 648MB/s]
model-00003-of-00006.safetensors:  55%|█████▍    | 2.73G/4.97G [00:04<00:04, 522MB/s]
model-00003-of-00006.safetensors:  56%|█████▌    | 2.79G/4.97G [00:04<00:04, 516MB/s]
model-00003-of-00006.safetensors:  58%|█████▊    | 2.86G/4.97G [00:04<00:03, 560MB/s]
model-00003-of-00006.safetensors:  60%|█████▉    | 2.97G/4.97G [00:04<00:02, 674MB/s]
model-00003-of-00006.safetensors:  61%|██████    | 3.04G/4.97G [00:04<00:03, 633MB/s]
model-00003-of-00006.safetensors:  63%|██████▎   | 3.11G/4.97G [00:04<00:03, 617MB/s]
model-00003-of-00006.safetensors:  65%|██████▌   | 3.24G/4.97G [00:04<00:02, 752MB/s]
model-00003-of-00006.safetensors:  67%|██████▋   | 3.32G/4.97G [00:04<00:02, 753MB/s]
model-00003-of-00006.safetensors:  69%|██████▊   | 3.41G/4.97G [00:05<00:02, 723MB/s]
model-00003-of-00006.safetensors:  70%|███████   | 3.49G/4.97G [00:05<00:02, 643MB/s]
model-00003-of-00006.safetensors:  72%|███████▏  | 3.57G/4.97G [00:05<00:02, 641MB/s]
model-00003-of-00006.safetensors:  73%|███████▎  | 3.64G/4.97G [00:05<00:02, 572MB/s]
model-00003-of-00006.safetensors:  74%|███████▍  | 3.70G/4.97G [00:05<00:02, 575MB/s]
model-00003-of-00006.safetensors:  76%|███████▌  | 3.79G/4.97G [00:05<00:01, 637MB/s]
model-00003-of-00006.safetensors:  78%|███████▊  | 3.87G/4.97G [00:05<00:01, 646MB/s]
model-00003-of-00006.safetensors:  79%|███████▉  | 3.94G/4.97G [00:05<00:01, 658MB/s]
model-00003-of-00006.safetensors:  81%|████████  | 4.02G/4.97G [00:06<00:01, 616MB/s]
model-00003-of-00006.safetensors:  82%|████████▏ | 4.10G/4.97G [00:06<00:01, 655MB/s]
model-00003-of-00006.safetensors:  84%|████████▍ | 4.17G/4.97G [00:06<00:01, 452MB/s]
model-00003-of-00006.safetensors:  85%|████████▌ | 4.24G/4.97G [00:06<00:02, 263MB/s]
model-00003-of-00006.safetensors:  86%|████████▌ | 4.28G/4.97G [00:07<00:02, 284MB/s]
model-00003-of-00006.safetensors:  87%|████████▋ | 4.32G/4.97G [00:07<00:02, 253MB/s]
model-00003-of-00006.safetensors:  88%|████████▊ | 4.36G/4.97G [00:07<00:02, 215MB/s]
model-00003-of-00006.safetensors:  88%|████████▊ | 4.39G/4.97G [00:07<00:02, 195MB/s]
model-00003-of-00006.safetensors:  89%|████████▉ | 4.43G/4.97G [00:07<00:02, 198MB/s]
model-00003-of-00006.safetensors:  90%|█████████ | 4.48G/4.97G [00:08<00:02, 225MB/s]
model-00003-of-00006.safetensors:  91%|█████████ | 4.51G/4.97G [00:08<00:02, 226MB/s]
model-00003-of-00006.safetensors:  91%|█████████▏| 4.54G/4.97G [00:08<00:02, 203MB/s]
model-00003-of-00006.safetensors:  92%|█████████▏| 4.59G/4.97G [00:08<00:01, 260MB/s]
model-00003-of-00006.safetensors:  93%|█████████▎| 4.63G/4.97G [00:08<00:01, 266MB/s]
model-00003-of-00006.safetensors:  94%|█████████▍| 4.67G/4.97G [00:08<00:01, 273MB/s]
model-00003-of-00006.safetensors:  95%|█████████▍| 4.72G/4.97G [00:08<00:00, 322MB/s]
model-00003-of-00006.safetensors:  96%|█████████▌| 4.76G/4.97G [00:09<00:00, 294MB/s]
model-00003-of-00006.safetensors:  97%|█████████▋| 4.80G/4.97G [00:09<00:00, 306MB/s]
model-00003-of-00006.safetensors:  98%|█████████▊| 4.88G/4.97G [00:09<00:00, 405MB/s]
model-00003-of-00006.safetensors:  99%|█████████▉| 4.93G/4.97G [00:09<00:00, 373MB/s]
model-00003-of-00006.safetensors: 100%|█████████▉| 4.97G/4.97G [00:09<00:00, 516MB/s]
khanhnto-khanhnto-v67-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<01:37, 50.5MB/s]
model-00004-of-00006.safetensors:   3%|▎         | 147M/4.93G [00:00<00:08, 578MB/s]  
model-00004-of-00006.safetensors:   7%|▋         | 346M/4.93G [00:00<00:04, 976MB/s]
model-00004-of-00006.safetensors:   9%|▉         | 461M/4.93G [00:00<00:05, 866MB/s]
model-00004-of-00006.safetensors:  11%|█▏        | 566M/4.93G [00:00<00:05, 835MB/s]
model-00004-of-00006.safetensors:  14%|█▍        | 692M/4.93G [00:00<00:04, 893MB/s]
model-00004-of-00006.safetensors:  16%|█▌        | 797M/4.93G [00:00<00:04, 876MB/s]
model-00004-of-00006.safetensors:  18%|█▊        | 891M/4.93G [00:01<00:05, 771MB/s]
model-00004-of-00006.safetensors:  20%|██        | 996M/4.93G [00:01<00:04, 832MB/s]
model-00004-of-00006.safetensors:  24%|██▎       | 1.16G/4.93G [00:01<00:03, 1.04GB/s]
model-00004-of-00006.safetensors:  28%|██▊       | 1.39G/4.93G [00:01<00:02, 1.38GB/s]
model-00004-of-00006.safetensors:  35%|███▍      | 1.71G/4.93G [00:01<00:01, 1.72GB/s]
model-00004-of-00006.safetensors:  38%|███▊      | 1.89G/4.93G [00:01<00:01, 1.54GB/s]
model-00004-of-00006.safetensors:  42%|████▏     | 2.06G/4.93G [00:01<00:01, 1.46GB/s]
model-00004-of-00006.safetensors:  45%|████▌     | 2.24G/4.93G [00:01<00:01, 1.54GB/s]
model-00004-of-00006.safetensors:  50%|█████     | 2.49G/4.93G [00:02<00:01, 1.75GB/s]
model-00004-of-00006.safetensors:  54%|█████▍    | 2.67G/4.93G [00:02<00:01, 1.64GB/s]
model-00004-of-00006.safetensors:  58%|█████▊    | 2.85G/4.93G [00:02<00:01, 1.64GB/s]
model-00004-of-00006.safetensors:  61%|██████    | 3.02G/4.93G [00:02<00:01, 1.59GB/s]
model-00004-of-00006.safetensors:  66%|██████▌   | 3.26G/4.93G [00:02<00:00, 1.80GB/s]
model-00004-of-00006.safetensors:  70%|██████▉   | 3.45G/4.93G [00:02<00:00, 1.56GB/s]
model-00004-of-00006.safetensors:  73%|███████▎  | 3.62G/4.93G [00:02<00:01, 1.27GB/s]
model-00004-of-00006.safetensors:  76%|███████▋  | 3.76G/4.93G [00:03<00:01, 1.14GB/s]
model-00004-of-00006.safetensors:  79%|███████▉  | 3.92G/4.93G [00:03<00:00, 1.23GB/s]
model-00004-of-00006.safetensors:  82%|████████▏ | 4.05G/4.93G [00:03<00:00, 1.21GB/s]
model-00004-of-00006.safetensors:  86%|████████▌ | 4.24G/4.93G [00:03<00:00, 1.37GB/s]
model-00004-of-00006.safetensors:  89%|████████▉ | 4.39G/4.93G [00:03<00:00, 1.32GB/s]
model-00004-of-00006.safetensors:  92%|█████████▏| 4.56G/4.93G [00:03<00:00, 1.39GB/s]
model-00004-of-00006.safetensors:  96%|█████████▌| 4.72G/4.93G [00:03<00:00, 1.44GB/s]
model-00004-of-00006.safetensors:  99%|█████████▉| 4.88G/4.93G [00:04<00:00, 981MB/s] 
model-00004-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:05<00:00, 887MB/s]
khanhnto-khanhnto-v67-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<01:20, 61.1MB/s]
model-00005-of-00006.safetensors:   2%|▏         | 115M/4.93G [00:00<00:12, 401MB/s]  
model-00005-of-00006.safetensors:   7%|▋         | 346M/4.93G [00:00<00:04, 1.01GB/s]
model-00005-of-00006.safetensors:  10%|▉         | 472M/4.93G [00:00<00:04, 984MB/s] 
model-00005-of-00006.safetensors:  12%|█▏        | 587M/4.93G [00:00<00:04, 887MB/s]
model-00005-of-00006.safetensors:  14%|█▍        | 713M/4.93G [00:00<00:04, 979MB/s]
model-00005-of-00006.safetensors:  17%|█▋        | 839M/4.93G [00:00<00:03, 1.05GB/s]
model-00005-of-00006.safetensors:  20%|█▉        | 965M/4.93G [00:01<00:03, 1.08GB/s]
model-00005-of-00006.safetensors:  22%|██▏       | 1.08G/4.93G [00:01<00:03, 983MB/s]
model-00005-of-00006.safetensors:  24%|██▍       | 1.21G/4.93G [00:01<00:03, 1.01GB/s]
model-00005-of-00006.safetensors:  27%|██▋       | 1.31G/4.93G [00:01<00:03, 972MB/s] 
model-00005-of-00006.safetensors:  29%|██▉       | 1.44G/4.93G [00:01<00:03, 989MB/s]
model-00005-of-00006.safetensors:  34%|███▍      | 1.69G/4.93G [00:01<00:02, 1.35GB/s]
model-00005-of-00006.safetensors:  37%|███▋      | 1.84G/4.93G [00:01<00:02, 1.38GB/s]
model-00005-of-00006.safetensors:  41%|████      | 2.03G/4.93G [00:01<00:01, 1.54GB/s]
model-00005-of-00006.safetensors:  45%|████▍     | 2.20G/4.93G [00:02<00:02, 1.33GB/s]
model-00005-of-00006.safetensors:  48%|████▊     | 2.37G/4.93G [00:02<00:01, 1.36GB/s]
model-00005-of-00006.safetensors:  51%|█████     | 2.52G/4.93G [00:02<00:01, 1.39GB/s]
model-00005-of-00006.safetensors:  57%|█████▋    | 2.79G/4.93G [00:02<00:01, 1.74GB/s]
model-00005-of-00006.safetensors:  60%|██████    | 2.98G/4.93G [00:02<00:01, 1.70GB/s]
model-00005-of-00006.safetensors:  65%|██████▍   | 3.19G/4.93G [00:02<00:01, 1.66GB/s]
model-00005-of-00006.safetensors:  68%|██████▊   | 3.37G/4.93G [00:02<00:01, 1.54GB/s]
model-00005-of-00006.safetensors:  72%|███████▏  | 3.53G/4.93G [00:02<00:00, 1.40GB/s]
model-00005-of-00006.safetensors:  75%|███████▌  | 3.71G/4.93G [00:02<00:00, 1.48GB/s]
model-00005-of-00006.safetensors:  81%|████████  | 3.97G/4.93G [00:03<00:00, 1.76GB/s]
model-00005-of-00006.safetensors:  85%|████████▌ | 4.19G/4.93G [00:03<00:00, 1.85GB/s]
model-00005-of-00006.safetensors:  90%|█████████ | 4.45G/4.93G [00:03<00:00, 2.01GB/s]
model-00005-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:03<00:00, 1.43GB/s]
khanhnto-khanhnto-v67-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<00:15, 79.3MB/s]
model-00006-of-00006.safetensors:   3%|▎         | 41.9M/1.25G [00:00<00:06, 196MB/s] 
model-00006-of-00006.safetensors:  19%|█▊        | 231M/1.25G [00:00<00:01, 857MB/s] 
model-00006-of-00006.safetensors:  35%|███▍      | 430M/1.25G [00:00<00:00, 1.21GB/s]
model-00006-of-00006.safetensors:  45%|████▍     | 556M/1.25G [00:00<00:00, 991MB/s] 
model-00006-of-00006.safetensors:  57%|█████▋    | 710M/1.25G [00:00<00:00, 1.14GB/s]
model-00006-of-00006.safetensors:  77%|███████▋  | 962M/1.25G [00:00<00:00, 1.50GB/s]
model-00006-of-00006.safetensors:  99%|█████████▉| 1.23G/1.25G [00:00<00:00, 1.83GB/s]
model-00006-of-00006.safetensors: 100%|█████████▉| 1.25G/1.25G [00:01<00:00, 848MB/s] 
khanhnto-khanhnto-v67-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, 16.0MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/548 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 548/548 [00:00<00:00, 4.49MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 26.8MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 62.2MB/s]
khanhnto-khanhnto-v67-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, 11.3MB/s]
khanhnto-khanhnto-v67-mkmlizer: Downloaded to shared memory in 37.330s
khanhnto-khanhnto-v67-mkmlizer: quantizing model to /dev/shm/model_cache
khanhnto-khanhnto-v67-mkmlizer: Saving mkml model at /dev/shm/model_cache
khanhnto-khanhnto-v67-mkmlizer: Reading /tmp/tmpwrdtwyci/model.safetensors.index.json
khanhnto-khanhnto-v67-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:01<09:13,  1.53s/it]
Profiling:   2%|▏         | 9/363 [00:01<00:47,  7.43it/s]
Profiling:   5%|▍         | 18/363 [00:01<00:21, 16.38it/s]
Profiling:   8%|▊         | 28/363 [00:01<00:12, 27.33it/s]
Profiling:  10%|█         | 37/363 [00:01<00:08, 37.00it/s]
Profiling:  13%|█▎        | 46/363 [00:02<00:06, 46.66it/s]
Profiling:  16%|█▌        | 57/363 [00:02<00:05, 58.10it/s]
Profiling:  19%|█▊        | 68/363 [00:02<00:04, 69.00it/s]
Profiling:  21%|██▏       | 78/363 [00:02<00:06, 42.55it/s]
Profiling:  24%|██▎       | 86/363 [00:02<00:05, 48.27it/s]
Profiling:  27%|██▋       | 97/363 [00:02<00:04, 58.18it/s]
Profiling:  29%|██▉       | 107/363 [00:03<00:03, 64.22it/s]
Profiling:  33%|███▎      | 118/363 [00:03<00:03, 72.37it/s]
Profiling:  35%|███▍      | 127/363 [00:03<00:03, 76.35it/s]
Profiling:  38%|███▊      | 137/363 [00:03<00:02, 82.19it/s]
Profiling:  40%|████      | 147/363 [00:03<00:04, 45.69it/s]
Profiling:  43%|████▎     | 156/363 [00:03<00:04, 51.71it/s]
Profiling:  45%|████▌     | 165/363 [00:04<00:03, 57.87it/s]
Profiling:  48%|████▊     | 174/363 [00:04<00:02, 64.23it/s]
Profiling:  50%|█████     | 183/363 [00:04<00:02, 67.07it/s]
Profiling:  53%|█████▎    | 192/363 [00:04<00:02, 69.07it/s]
Profiling:  55%|█████▌    | 200/363 [00:04<00:02, 71.60it/s]
Profiling:  57%|█████▋    | 208/363 [00:04<00:02, 69.25it/s]
Profiling:  60%|█████▉    | 216/363 [00:05<00:03, 39.44it/s]
Profiling:  62%|██████▏   | 224/363 [00:05<00:03, 46.09it/s]
Profiling:  64%|██████▍   | 232/363 [00:05<00:02, 52.47it/s]
Profiling:  66%|██████▌   | 239/363 [00:05<00:02, 55.73it/s]
Profiling:  68%|██████▊   | 248/363 [00:05<00:01, 61.59it/s]
Profiling:  71%|███████   | 257/363 [00:05<00:01, 66.31it/s]
Profiling:  73%|███████▎  | 266/363 [00:05<00:01, 70.66it/s]
Profiling:  76%|███████▌  | 275/363 [00:05<00:01, 75.35it/s]
Profiling:  78%|███████▊  | 283/363 [00:06<00:01, 44.24it/s]
Profiling:  81%|████████  | 293/363 [00:06<00:01, 52.64it/s]
Profiling:  83%|████████▎ | 302/363 [00:06<00:01, 59.78it/s]
Profiling:  86%|████████▌ | 313/363 [00:06<00:00, 70.09it/s]
Profiling:  89%|████████▉ | 323/363 [00:06<00:00, 76.88it/s]
Profiling:  91%|█████████▏| 332/363 [00:06<00:00, 78.95it/s]
Profiling:  94%|█████████▍| 342/363 [00:06<00:00, 82.90it/s]
Profiling:  97%|█████████▋| 351/363 [00:08<00:00, 14.19it/s]
Profiling:  99%|█████████▉| 360/363 [00:08<00:00, 18.72it/s]
Profiling: 100%|██████████| 363/363 [00:08<00:00, 40.78it/s]
khanhnto-khanhnto-v67-mkmlizer: quantized model in 30.616s
khanhnto-khanhnto-v67-mkmlizer: Processed model khanhnto/khanhnto in 70.887s
khanhnto-khanhnto-v67-mkmlizer: creating bucket guanaco-mkml-models
khanhnto-khanhnto-v67-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
khanhnto-khanhnto-v67-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/khanhnto-khanhnto-v67
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v67/config.json
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/khanhnto-khanhnto-v67/added_tokens.json
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v67/tokenizer_config.json
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/khanhnto-khanhnto-v67/tokenizer.model
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/khanhnto-khanhnto-v67/special_tokens_map.json
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/khanhnto-khanhnto-v67/tokenizer.json
khanhnto-khanhnto-v67-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/khanhnto-khanhnto-v67/mkml_model.tensors
khanhnto-khanhnto-v67-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
khanhnto-khanhnto-v67-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-v67-mkmlizer:   warnings.warn(
khanhnto-khanhnto-v67-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.9MB/s]
khanhnto-khanhnto-v67-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.
khanhnto-khanhnto-v67-mkmlizer:   warnings.warn(
khanhnto-khanhnto-v67-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.76MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 13.1MB/s]
khanhnto-khanhnto-v67-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 73.1MB/s]
khanhnto-khanhnto-v67-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.
khanhnto-khanhnto-v67-mkmlizer:   warnings.warn(
khanhnto-khanhnto-v67-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:08, 161MB/s]
pytorch_model.bin:   4%|▎         | 52.4M/1.44G [00:00<00:06, 227MB/s]
pytorch_model.bin:   6%|▌         | 83.9M/1.44G [00:00<00:05, 260MB/s]
pytorch_model.bin:   9%|▉         | 136M/1.44G [00:00<00:04, 320MB/s] 
pytorch_model.bin:  15%|█▍        | 210M/1.44G [00:00<00:02, 413MB/s]
pytorch_model.bin:  20%|██        | 294M/1.44G [00:00<00:02, 536MB/s]
pytorch_model.bin:  25%|██▍       | 357M/1.44G [00:00<00:02, 497MB/s]
pytorch_model.bin:  28%|██▊       | 409M/1.44G [00:00<00:02, 452MB/s]
pytorch_model.bin:  32%|███▏      | 461M/1.44G [00:01<00:02, 466MB/s]
pytorch_model.bin:  42%|████▏     | 608M/1.44G [00:01<00:01, 728MB/s]
pytorch_model.bin:  51%|█████     | 734M/1.44G [00:01<00:00, 863MB/s]
pytorch_model.bin:  70%|██████▉   | 1.01G/1.44G [00:01<00:00, 1.38GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 936MB/s] 
khanhnto-khanhnto-v67-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
khanhnto-khanhnto-v67-mkmlizer: Saving duration: 0.278s
khanhnto-khanhnto-v67-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.224s
khanhnto-khanhnto-v67-mkmlizer: creating bucket guanaco-reward-models
khanhnto-khanhnto-v67-mkmlizer: Bucket 's3://guanaco-reward-models/' created
khanhnto-khanhnto-v67-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/config.json
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/special_tokens_map.json
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/tokenizer_config.json
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/merges.txt
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/vocab.json
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/tokenizer.json
khanhnto-khanhnto-v67-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/khanhnto-khanhnto-v67_reward/reward.tensors
Job khanhnto-khanhnto-v67-mkmlizer completed after 95.36s with status: succeeded
Stopping job with name khanhnto-khanhnto-v67-mkmlizer
Pipeline stage MKMLizer completed in 98.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service khanhnto-khanhnto-v67
Waiting for inference service khanhnto-khanhnto-v67 to be ready
Inference service khanhnto-khanhnto-v67 ready after 60.28372931480408s
Pipeline stage ISVCDeployer completed in 66.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1019928455352783s
Received healthy response to inference request in 1.0638048648834229s
Received healthy response to inference request in 1.348240613937378s
Received healthy response to inference request in 1.5476593971252441s
Received healthy response to inference request in 1.9437508583068848s
5 requests
0 failed requests
5th percentile: 1.1206920146942139
10th percentile: 1.1775791645050049
20th percentile: 1.291353464126587
30th percentile: 1.388124370574951
40th percentile: 1.4678918838500976
50th percentile: 1.5476593971252441
60th percentile: 1.7060959815979004
70th percentile: 1.8645325660705565
80th percentile: 1.9753992557525635
90th percentile: 2.038696050643921
95th percentile: 2.0703444480895996
99th percentile: 2.0956631660461427
mean time: 1.6010897159576416
Pipeline stage StressChecker completed in 9.13s
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_v67 status is now deployed due to DeploymentManager action
khanhnto-khanhnto_v67 status is now inactive due to auto deactivation removed underperforming models
khanhnto-khanhnto_v67 status is now deployed due to admin request
khanhnto-khanhnto_v67 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of khanhnto-khanhnto_v67
Running pipeline stage ISVCDeleter
Checking if service khanhnto-khanhnto-v67 is running
Tearing down inference service khanhnto-khanhnto-v67
Toredown service khanhnto-khanhnto-v67
Pipeline stage ISVCDeleter completed in 3.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key khanhnto-khanhnto-v67/added_tokens.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/config.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/tokenizer.json from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/tokenizer.model from bucket guanaco-mkml-models
Deleting key khanhnto-khanhnto-v67/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key khanhnto-khanhnto-v67_reward/config.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/merges.txt from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/reward.tensors from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key khanhnto-khanhnto-v67_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.02s
khanhnto-khanhnto_v67 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics