submission_id: a100-khanhnto-khanhnto_v54
developer_uid: chai_backend_admin
status: inactive
model_repo: khanhnto/khanhnto
reward_repo: rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
generation_params: {'temperature': 1.2, 'top_p': 0.7, 'top_k': 50, 'presence_penalty': 0.8, 'frequency_penalty': 0.2, 'stopping_words': ['<\\s>', '###', '\n'], '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}:'}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:'}
timestamp: 2024-02-25T02:07:13+00:00
model_name: khanhnto-khanhnto_v54
model_eval_status: success
safety_score: 0.98
entertaining: 6.88
stay_in_character: 8.54
user_preference: 7.32
double_thumbs_up: 811
thumbs_up: 1090
thumbs_down: 545
num_battles: 104122
num_wins: 50631
win_ratio: 0.48626611090835753
celo_rating: 1147.47
Resubmit model
Running pipeline stage MKMLizer
Starting job with name khanhnto-khanhnto-v54-mkmlizer
Waiting for job on khanhnto-khanhnto-v54-mkmlizer to finish
khanhnto-khanhnto-v54-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
khanhnto-khanhnto-v54-mkmlizer: ║ _____ __ __ ║
khanhnto-khanhnto-v54-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
khanhnto-khanhnto-v54-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
khanhnto-khanhnto-v54-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
khanhnto-khanhnto-v54-mkmlizer: ║ /___/ ║
khanhnto-khanhnto-v54-mkmlizer: ║ ║
khanhnto-khanhnto-v54-mkmlizer: ║ Version: 0.6.11 ║
khanhnto-khanhnto-v54-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
khanhnto-khanhnto-v54-mkmlizer: ║ ║
khanhnto-khanhnto-v54-mkmlizer: ║ The license key for the current software has been verified as ║
khanhnto-khanhnto-v54-mkmlizer: ║ belonging to: ║
khanhnto-khanhnto-v54-mkmlizer: ║ ║
khanhnto-khanhnto-v54-mkmlizer: ║ Chai Research Corp. ║
khanhnto-khanhnto-v54-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
khanhnto-khanhnto-v54-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
khanhnto-khanhnto-v54-mkmlizer: ║ ║
khanhnto-khanhnto-v54-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
khanhnto-khanhnto-v54-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.8MB/s]
khanhnto-khanhnto-v54-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, 284kB/s]
khanhnto-khanhnto-v54-mkmlizer: config.json: 0%| | 0.00/702 [00:00<?, ?B/s] config.json: 100%|██████████| 702/702 [00:00<00:00, 5.49MB/s]
khanhnto-khanhnto-v54-mkmlizer: generation_config.json: 0%| | 0.00/137 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 2.24MB/s]
khanhnto-khanhnto-v54-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<01:18, 63.7MB/s] model-00001-of-00006.safetensors: 0%| | 21.0M/4.98G [00:00<01:21, 61.0MB/s] model-00001-of-00006.safetensors: 1%| | 41.9M/4.98G [00:00<00:54, 90.4MB/s] model-00001-of-00006.safetensors: 3%|▎ | 126M/4.98G [00:00<00:16, 297MB/s] model-00001-of-00006.safetensors: 5%|▍ | 231M/4.98G [00:00<00:09, 492MB/s] model-00001-of-00006.safetensors: 6%|▋ | 315M/4.98G [00:00<00:08, 568MB/s] model-00001-of-00006.safetensors: 9%|▊ | 430M/4.98G [00:00<00:06, 683MB/s] model-00001-of-00006.safetensors: 10%|█ | 503M/4.98G [00:01<00:07, 631MB/s] model-00001-of-00006.safetensors: 12%|█▏ | 587M/4.98G [00:01<00:06, 669MB/s] model-00001-of-00006.safetensors: 14%|█▍ | 692M/4.98G [00:01<00:05, 766MB/s] model-00001-of-00006.safetensors: 16%|█▌ | 776M/4.98G [00:01<00:05, 726MB/s] model-00001-of-00006.safetensors: 17%|█▋ | 860M/4.98G [00:01<00:05, 750MB/s] model-00001-of-00006.safetensors: 19%|█▉ | 944M/4.98G [00:01<00:07, 550MB/s] model-00001-of-00006.safetensors: 20%|██ | 1.02G/4.98G [00:01<00:07, 505MB/s] model-00001-of-00006.safetensors: 22%|██▏ | 1.09G/4.98G [00:02<00:07, 528MB/s] model-00001-of-00006.safetensors: 23%|██▎ | 1.15G/4.98G [00:02<00:07, 508MB/s] model-00001-of-00006.safetensors: 25%|██▍ | 1.23G/4.98G [00:02<00:08, 455MB/s] model-00001-of-00006.safetensors: 26%|██▌ | 1.28G/4.98G [00:02<00:09, 391MB/s] model-00001-of-00006.safetensors: 28%|██▊ | 1.41G/4.98G [00:02<00:06, 551MB/s] model-00001-of-00006.safetensors: 30%|██▉ | 1.48G/4.98G [00:03<00:08, 412MB/s] model-00001-of-00006.safetensors: 33%|███▎ | 1.64G/4.98G [00:03<00:05, 606MB/s] model-00001-of-00006.safetensors: 35%|███▍ | 1.72G/4.98G [00:03<00:06, 501MB/s] model-00001-of-00006.safetensors: 36%|███▌ | 1.79G/4.98G [00:03<00:05, 533MB/s] model-00001-of-00006.safetensors: 38%|███▊ | 1.90G/4.98G [00:03<00:04, 630MB/s] model-00001-of-00006.safetensors: 40%|███▉ | 1.98G/4.98G [00:03<00:05, 548MB/s] model-00001-of-00006.safetensors: 41%|████▏ | 2.06G/4.98G [00:04<00:05, 501MB/s] model-00001-of-00006.safetensors: 44%|████▎ | 2.17G/4.98G [00:04<00:04, 627MB/s] model-00001-of-00006.safetensors: 45%|████▌ | 2.25G/4.98G [00:04<00:04, 674MB/s] model-00001-of-00006.safetensors: 47%|████▋ | 2.34G/4.98G [00:04<00:04, 593MB/s] model-00001-of-00006.safetensors: 48%|████▊ | 2.41G/4.98G [00:04<00:04, 578MB/s] model-00001-of-00006.safetensors: 50%|████▉ | 2.49G/4.98G [00:04<00:05, 452MB/s] model-00001-of-00006.safetensors: 52%|█████▏ | 2.59G/4.98G [00:04<00:04, 566MB/s] model-00001-of-00006.safetensors: 54%|█████▎ | 2.66G/4.98G [00:05<00:05, 447MB/s] model-00001-of-00006.safetensors: 56%|█████▌ | 2.80G/4.98G [00:05<00:03, 597MB/s] model-00001-of-00006.safetensors: 58%|█████▊ | 2.88G/4.98G [00:05<00:03, 630MB/s] model-00001-of-00006.safetensors: 60%|█████▉ | 2.97G/4.98G [00:05<00:03, 593MB/s] model-00001-of-00006.safetensors: 61%|██████ | 3.04G/4.98G [00:05<00:03, 614MB/s] model-00001-of-00006.safetensors: 63%|██████▎ | 3.11G/4.98G [00:05<00:03, 616MB/s] model-00001-of-00006.safetensors: 64%|██████▍ | 3.19G/4.98G [00:05<00:03, 572MB/s] model-00001-of-00006.safetensors: 66%|██████▌ | 3.26G/4.98G [00:06<00:02, 594MB/s] model-00001-of-00006.safetensors: 67%|██████▋ | 3.34G/4.98G [00:06<00:02, 576MB/s] model-00001-of-00006.safetensors: 68%|██████▊ | 3.41G/4.98G [00:06<00:03, 507MB/s] model-00001-of-00006.safetensors: 70%|███████ | 3.50G/4.98G [00:06<00:02, 600MB/s] model-00001-of-00006.safetensors: 72%|███████▏ | 3.58G/4.98G [00:06<00:03, 443MB/s] model-00001-of-00006.safetensors: 74%|███████▎ | 3.67G/4.98G [00:06<00:02, 521MB/s] model-00001-of-00006.safetensors: 75%|███████▍ | 3.73G/4.98G [00:07<00:02, 481MB/s] model-00001-of-00006.safetensors: 77%|███████▋ | 3.82G/4.98G [00:07<00:02, 530MB/s] model-00001-of-00006.safetensors: 78%|███████▊ | 3.89G/4.98G [00:07<00:02, 468MB/s] model-00001-of-00006.safetensors: 79%|███████▉ | 3.94G/4.98G [00:07<00:02, 429MB/s] model-00001-of-00006.safetensors: 82%|████████▏ | 4.07G/4.98G [00:07<00:01, 585MB/s] model-00001-of-00006.safetensors: 83%|████████▎ | 4.15G/4.98G [00:07<00:01, 613MB/s] model-00001-of-00006.safetensors: 85%|████████▍ | 4.22G/4.98G [00:07<00:01, 620MB/s] model-00001-of-00006.safetensors: 88%|████████▊ | 4.38G/4.98G [00:07<00:00, 846MB/s] model-00001-of-00006.safetensors: 92%|█████████▏| 4.58G/4.98G [00:08<00:00, 1.12GB/s] model-00001-of-00006.safetensors: 95%|█████████▍| 4.71G/4.98G [00:08<00:00, 902MB/s] model-00001-of-00006.safetensors: 97%|█████████▋| 4.84G/4.98G [00:08<00:00, 962MB/s] model-00001-of-00006.safetensors: 100%|█████████▉| 4.96G/4.98G [00:08<00:00, 615MB/s] model-00001-of-00006.safetensors: 100%|█████████▉| 4.98G/4.98G [00:09<00:00, 542MB/s]
khanhnto-khanhnto-v54-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<02:41, 30.7MB/s] model-00002-of-00006.safetensors: 0%| | 21.0M/4.97G [00:00<01:40, 49.5MB/s] model-00002-of-00006.safetensors: 2%|▏ | 105M/4.97G [00:00<00:17, 273MB/s] model-00002-of-00006.safetensors: 8%|▊ | 419M/4.97G [00:00<00:04, 938MB/s] model-00002-of-00006.safetensors: 11%|█ | 524M/4.97G [00:00<00:05, 801MB/s] model-00002-of-00006.safetensors: 13%|█▎ | 629M/4.97G [00:01<00:05, 847MB/s] model-00002-of-00006.safetensors: 15%|█▍ | 724M/4.97G [00:01<00:06, 676MB/s] model-00002-of-00006.safetensors: 16%|█▌ | 807M/4.97G [00:01<00:06, 657MB/s] model-00002-of-00006.safetensors: 18%|█▊ | 891M/4.97G [00:01<00:06, 664MB/s] model-00002-of-00006.safetensors: 22%|██▏ | 1.09G/4.97G [00:01<00:03, 972MB/s] model-00002-of-00006.safetensors: 24%|██▍ | 1.21G/4.97G [00:01<00:04, 892MB/s] model-00002-of-00006.safetensors: 26%|██▋ | 1.31G/4.97G [00:01<00:04, 888MB/s] model-00002-of-00006.safetensors: 29%|██▊ | 1.43G/4.97G [00:01<00:03, 890MB/s] model-00002-of-00006.safetensors: 31%|███ | 1.52G/4.97G [00:02<00:04, 819MB/s] model-00002-of-00006.safetensors: 35%|███▍ | 1.72G/4.97G [00:02<00:03, 1.08GB/s] model-00002-of-00006.safetensors: 37%|███▋ | 1.84G/4.97G [00:02<00:03, 1.01GB/s] model-00002-of-00006.safetensors: 39%|███▉ | 1.95G/4.97G [00:02<00:03, 989MB/s] model-00002-of-00006.safetensors: 41%|████▏ | 2.06G/4.97G [00:02<00:03, 886MB/s] model-00002-of-00006.safetensors: 43%|████▎ | 2.15G/4.97G [00:02<00:03, 859MB/s] model-00002-of-00006.safetensors: 46%|████▌ | 2.28G/4.97G [00:02<00:02, 931MB/s] model-00002-of-00006.safetensors: 48%|████▊ | 2.38G/4.97G [00:03<00:02, 900MB/s] model-00002-of-00006.safetensors: 50%|████▉ | 2.47G/4.97G [00:03<00:02, 882MB/s] model-00002-of-00006.safetensors: 52%|█████▏ | 2.60G/4.97G [00:03<00:02, 942MB/s] model-00002-of-00006.safetensors: 54%|█████▍ | 2.71G/4.97G [00:03<00:02, 925MB/s] model-00002-of-00006.safetensors: 57%|█████▋ | 2.82G/4.97G [00:03<00:02, 982MB/s] model-00002-of-00006.safetensors: 59%|█████▉ | 2.93G/4.97G [00:03<00:02, 720MB/s] model-00002-of-00006.safetensors: 61%|██████ | 3.04G/4.97G [00:03<00:02, 812MB/s] model-00002-of-00006.safetensors: 63%|██████▎ | 3.14G/4.97G [00:03<00:02, 784MB/s] model-00002-of-00006.safetensors: 66%|██████▌ | 3.29G/4.97G [00:04<00:01, 919MB/s] model-00002-of-00006.safetensors: 68%|██████▊ | 3.40G/4.97G [00:04<00:02, 733MB/s] model-00002-of-00006.safetensors: 70%|███████ | 3.48G/4.97G [00:04<00:01, 753MB/s] model-00002-of-00006.safetensors: 72%|███████▏ | 3.60G/4.97G [00:04<00:01, 815MB/s] model-00002-of-00006.safetensors: 74%|███████▍ | 3.69G/4.97G [00:04<00:01, 823MB/s] model-00002-of-00006.safetensors: 76%|███████▌ | 3.79G/4.97G [00:04<00:01, 815MB/s] model-00002-of-00006.safetensors: 78%|███████▊ | 3.90G/4.97G [00:04<00:01, 838MB/s] model-00002-of-00006.safetensors: 80%|████████ | 4.00G/4.97G [00:04<00:01, 829MB/s] model-00002-of-00006.safetensors: 82%|████████▏ | 4.09G/4.97G [00:05<00:01, 825MB/s] model-00002-of-00006.safetensors: 84%|████████▍ | 4.17G/4.97G [00:05<00:00, 805MB/s] model-00002-of-00006.safetensors: 86%|████████▋ | 4.29G/4.97G [00:05<00:00, 871MB/s] model-00002-of-00006.safetensors: 88%|████████▊ | 4.38G/4.97G [00:05<00:00, 874MB/s] model-00002-of-00006.safetensors: 90%|█████████ | 4.49G/4.97G [00:05<00:00, 921MB/s] model-00002-of-00006.safetensors: 93%|█████████▎| 4.61G/4.97G [00:05<00:00, 1.00GB/s] model-00002-of-00006.safetensors: 95%|█████████▍| 4.72G/4.97G [00:05<00:00, 800MB/s] model-00002-of-00006.safetensors: 97%|█████████▋| 4.82G/4.97G [00:05<00:00, 844MB/s] model-00002-of-00006.safetensors: 99%|█████████▉| 4.92G/4.97G [00:06<00:00, 612MB/s] model-00002-of-00006.safetensors: 100%|█████████▉| 4.97G/4.97G [00:07<00:00, 635MB/s]
khanhnto-khanhnto-v54-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<02:20, 34.9MB/s] model-00004-of-00006.safetensors: 1%| | 52.4M/4.93G [00:00<00:31, 157MB/s] model-00004-of-00006.safetensors: 2%|▏ | 94.4M/4.93G [00:00<00:23, 207MB/s] model-00004-of-00006.safetensors: 3%|▎ | 126M/4.93G [00:00<00:23, 205MB/s] model-00004-of-00006.safetensors: 4%|▍ | 189M/4.93G [00:00<00:15, 300MB/s] model-00004-of-00006.safetensors: 5%|▌ | 252M/4.93G [00:00<00:12, 384MB/s] model-00004-of-00006.safetensors: 6%|▌ | 304M/4.93G [00:01<00:11, 408MB/s] model-00004-of-00006.safetensors: 8%|▊ | 388M/4.93G [00:01<00:09, 469MB/s] model-00004-of-00006.safetensors: 9%|▉ | 440M/4.93G [00:01<00:10, 416MB/s] model-00004-of-00006.safetensors: 10%|▉ | 493M/4.93G [00:01<00:10, 407MB/s] model-00004-of-00006.safetensors: 11%|█ | 545M/4.93G [00:01<00:10, 414MB/s] model-00004-of-00006.safetensors: 12%|█▏ | 598M/4.93G [00:01<00:09, 439MB/s] model-00004-of-00006.safetensors: 14%|█▍ | 682M/4.93G [00:01<00:08, 520MB/s] model-00004-of-00006.safetensors: 16%|█▌ | 776M/4.93G [00:01<00:07, 594MB/s] model-00004-of-00006.safetensors: 17%|█▋ | 839M/4.93G [00:02<00:07, 569MB/s] model-00004-of-00006.safetensors: 18%|█▊ | 912M/4.93G [00:02<00:06, 578MB/s] model-00004-of-00006.safetensors: 20%|█▉ | 975M/4.93G [00:02<00:07, 513MB/s] model-00004-of-00006.safetensors: 22%|██▏ | 1.08G/4.93G [00:02<00:06, 633MB/s] model-00004-of-00006.safetensors: 23%|██▎ | 1.15G/4.93G [00:02<00:05, 637MB/s] model-00004-of-00006.safetensors: 25%|██▍ | 1.23G/4.93G [00:02<00:05, 643MB/s] model-00004-of-00006.safetensors: 27%|██▋ | 1.32G/4.93G [00:02<00:05, 714MB/s] model-00004-of-00006.safetensors: 28%|██▊ | 1.41G/4.93G [00:02<00:04, 747MB/s] model-00004-of-00006.safetensors: 31%|███ | 1.54G/4.93G [00:02<00:03, 914MB/s] model-00004-of-00006.safetensors: 33%|███▎ | 1.64G/4.93G [00:03<00:04, 758MB/s] model-00004-of-00006.safetensors: 35%|███▍ | 1.72G/4.93G [00:03<00:04, 649MB/s] model-00004-of-00006.safetensors: 36%|███▋ | 1.79G/4.93G [00:03<00:04, 658MB/s] model-00004-of-00006.safetensors: 38%|███▊ | 1.87G/4.93G [00:03<00:04, 619MB/s] model-00004-of-00006.safetensors: 39%|███▉ | 1.94G/4.93G [00:03<00:05, 581MB/s] model-00004-of-00006.safetensors: 41%|████▏ | 2.04G/4.93G [00:03<00:05, 564MB/s] model-00004-of-00006.safetensors: 43%|████▎ | 2.12G/4.93G [00:04<00:04, 584MB/s] model-00004-of-00006.safetensors: 44%|████▍ | 2.19G/4.93G [00:04<00:04, 580MB/s] model-00004-of-00006.safetensors: 47%|████▋ | 2.30G/4.93G [00:04<00:04, 648MB/s] model-00004-of-00006.safetensors: 48%|████▊ | 2.39G/4.93G [00:04<00:03, 674MB/s] model-00004-of-00006.safetensors: 50%|█████ | 2.47G/4.93G [00:04<00:03, 711MB/s] model-00004-of-00006.safetensors: 52%|█████▏ | 2.55G/4.93G [00:04<00:03, 687MB/s] model-00004-of-00006.safetensors: 54%|█████▍ | 2.65G/4.93G [00:04<00:02, 774MB/s] model-00004-of-00006.safetensors: 56%|█████▌ | 2.75G/4.93G [00:04<00:02, 791MB/s] model-00004-of-00006.safetensors: 59%|█████▉ | 2.93G/4.93G [00:04<00:01, 1.05GB/s] model-00004-of-00006.safetensors: 62%|██████▏ | 3.04G/4.93G [00:05<00:01, 1.07GB/s] model-00004-of-00006.safetensors: 66%|██████▌ | 3.25G/4.93G [00:05<00:01, 1.35GB/s] model-00004-of-00006.safetensors: 69%|██████▉ | 3.40G/4.93G [00:05<00:01, 1.35GB/s] model-00004-of-00006.safetensors: 72%|███████▏ | 3.54G/4.93G [00:05<00:01, 1.32GB/s] model-00004-of-00006.safetensors: 75%|███████▌ | 3.71G/4.93G [00:05<00:00, 1.42GB/s] model-00004-of-00006.safetensors: 81%|████████ | 4.01G/4.93G [00:05<00:00, 1.81GB/s] model-00004-of-00006.safetensors: 86%|████████▋ | 4.26G/4.93G [00:05<00:00, 2.00GB/s] model-00004-of-00006.safetensors: 90%|█████████ | 4.46G/4.93G [00:05<00:00, 1.94GB/s] model-00004-of-00006.safetensors: 94%|█████████▍| 4.66G/4.93G [00:06<00:00, 1.43GB/s] model-00004-of-00006.safetensors: 98%|█████████▊| 4.83G/4.93G [00:06<00:00, 1.28GB/s] model-00004-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:07<00:00, 640MB/s]
khanhnto-khanhnto-v54-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<03:00, 27.3MB/s] model-00005-of-00006.safetensors: 0%| | 21.0M/4.93G [00:00<01:43, 47.5MB/s] model-00005-of-00006.safetensors: 1%| | 52.4M/4.93G [00:00<00:42, 115MB/s] model-00005-of-00006.safetensors: 1%|▏ | 73.4M/4.93G [00:00<00:37, 131MB/s] model-00005-of-00006.safetensors: 2%|▏ | 105M/4.93G [00:00<00:27, 174MB/s] model-00005-of-00006.safetensors: 3%|▎ | 136M/4.93G [00:00<00:23, 204MB/s] model-00005-of-00006.safetensors: 4%|▍ | 189M/4.93G [00:01<00:17, 271MB/s] model-00005-of-00006.safetensors: 5%|▌ | 252M/4.93G [00:01<00:15, 305MB/s] model-00005-of-00006.safetensors: 6%|▋ | 315M/4.93G [00:01<00:12, 380MB/s] model-00005-of-00006.safetensors: 8%|▊ | 388M/4.93G [00:01<00:10, 445MB/s] model-00005-of-00006.safetensors: 9%|▉ | 440M/4.93G [00:01<00:11, 385MB/s] model-00005-of-00006.safetensors: 11%|█ | 535M/4.93G [00:01<00:08, 509MB/s] model-00005-of-00006.safetensors: 13%|█▎ | 619M/4.93G [00:01<00:07, 582MB/s] model-00005-of-00006.safetensors: 15%|█▍ | 724M/4.93G [00:01<00:06, 681MB/s] model-00005-of-00006.safetensors: 16%|█▌ | 797M/4.93G [00:02<00:07, 557MB/s] model-00005-of-00006.safetensors: 17%|█▋ | 860M/4.93G [00:02<00:07, 570MB/s] model-00005-of-00006.safetensors: 20%|█▉ | 965M/4.93G [00:02<00:06, 614MB/s] model-00005-of-00006.safetensors: 21%|██ | 1.04G/4.93G [00:02<00:06, 572MB/s] model-00005-of-00006.safetensors: 23%|██▎ | 1.13G/4.93G [00:02<00:05, 659MB/s] model-00005-of-00006.safetensors: 26%|██▌ | 1.28G/4.93G [00:02<00:04, 795MB/s] model-00005-of-00006.safetensors: 28%|██▊ | 1.36G/4.93G [00:02<00:05, 697MB/s] model-00005-of-00006.safetensors: 29%|██▉ | 1.44G/4.93G [00:03<00:05, 693MB/s] model-00005-of-00006.safetensors: 32%|███▏ | 1.58G/4.93G [00:03<00:03, 880MB/s] model-00005-of-00006.safetensors: 34%|███▍ | 1.68G/4.93G [00:03<00:04, 795MB/s] model-00005-of-00006.safetensors: 36%|███▌ | 1.77G/4.93G [00:03<00:03, 829MB/s] model-00005-of-00006.safetensors: 39%|███▉ | 1.92G/4.93G [00:03<00:03, 960MB/s] model-00005-of-00006.safetensors: 41%|████▏ | 2.04G/4.93G [00:03<00:02, 1.04GB/s] model-00005-of-00006.safetensors: 46%|████▋ | 2.29G/4.93G [00:03<00:01, 1.41GB/s] model-00005-of-00006.safetensors: 51%|█████ | 2.53G/4.93G [00:03<00:01, 1.64GB/s] model-00005-of-00006.safetensors: 57%|█████▋ | 2.79G/4.93G [00:03<00:01, 1.91GB/s] model-00005-of-00006.safetensors: 61%|██████ | 2.99G/4.93G [00:04<00:01, 1.60GB/s] model-00005-of-00006.safetensors: 64%|██████▍ | 3.17G/4.93G [00:04<00:01, 1.47GB/s] model-00005-of-00006.safetensors: 67%|██████▋ | 3.32G/4.93G [00:04<00:01, 1.13GB/s] model-00005-of-00006.safetensors: 70%|███████ | 3.46G/4.93G [00:04<00:01, 1.10GB/s] model-00005-of-00006.safetensors: 73%|███████▎ | 3.59G/4.93G [00:04<00:01, 933MB/s] model-00005-of-00006.safetensors: 75%|███████▍ | 3.69G/4.93G [00:04<00:01, 937MB/s] model-00005-of-00006.safetensors: 77%|███████▋ | 3.81G/4.93G [00:05<00:01, 981MB/s] model-00005-of-00006.safetensors: 79%|███████▉ | 3.91G/4.93G [00:05<00:01, 969MB/s] model-00005-of-00006.safetensors: 82%|████████▏ | 4.02G/4.93G [00:05<00:00, 969MB/s] model-00005-of-00006.safetensors: 84%|████████▎ | 4.13G/4.93G [00:05<00:00, 901MB/s] model-00005-of-00006.safetensors: 86%|████████▌ | 4.22G/4.93G [00:05<00:01, 639MB/s] model-00005-of-00006.safetensors: 87%|████████▋ | 4.30G/4.93G [00:05<00:01, 512MB/s] model-00005-of-00006.safetensors: 89%|████████▊ | 4.38G/4.93G [00:06<00:01, 540MB/s] model-00005-of-00006.safetensors: 92%|█████████▏| 4.52G/4.93G [00:06<00:00, 715MB/s] model-00005-of-00006.safetensors: 95%|█████████▌| 4.69G/4.93G [00:06<00:00, 917MB/s] model-00005-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:10<00:00, 111MB/s] model-00005-of-00006.safetensors: 100%|█████████▉| 4.93G/4.93G [00:10<00:00, 455MB/s]
khanhnto-khanhnto-v54-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<00:35, 35.1MB/s] model-00006-of-00006.safetensors: 3%|▎ | 41.9M/1.25G [00:00<00:10, 120MB/s] model-00006-of-00006.safetensors: 7%|▋ | 83.9M/1.25G [00:00<00:06, 184MB/s] model-00006-of-00006.safetensors: 9%|▉ | 115M/1.25G [00:00<00:05, 211MB/s] model-00006-of-00006.safetensors: 15%|█▌ | 189M/1.25G [00:00<00:03, 311MB/s] model-00006-of-00006.safetensors: 24%|██▎ | 294M/1.25G [00:00<00:01, 485MB/s] model-00006-of-00006.safetensors: 30%|███ | 375M/1.25G [00:01<00:01, 562MB/s] model-00006-of-00006.safetensors: 36%|███▌ | 448M/1.25G [00:01<00:01, 607MB/s] model-00006-of-00006.safetensors: 45%|████▌ | 564M/1.25G [00:01<00:01, 680MB/s] model-00006-of-00006.safetensors: 54%|█████▎ | 669M/1.25G [00:01<00:00, 764MB/s] model-00006-of-00006.safetensors: 64%|██████▍ | 794M/1.25G [00:01<00:00, 886MB/s] model-00006-of-00006.safetensors: 73%|███████▎ | 910M/1.25G [00:01<00:00, 951MB/s] model-00006-of-00006.safetensors: 82%|████████▏ | 1.03G/1.25G [00:01<00:00, 1.00GB/s] model-00006-of-00006.safetensors: 91%|█████████ | 1.13G/1.25G [00:01<00:00, 1.00GB/s] model-00006-of-00006.safetensors: 99%|█████████▉| 1.23G/1.25G [00:02<00:00, 404MB/s] model-00006-of-00006.safetensors: 100%|█████████▉| 1.25G/1.25G [00:03<00:00, 322MB/s]
khanhnto-khanhnto-v54-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, 129MB/s]
khanhnto-khanhnto-v54-mkmlizer: special_tokens_map.json: 0%| | 0.00/548 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 548/548 [00:00<00:00, 8.98MB/s]
khanhnto-khanhnto-v54-mkmlizer: tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.4MB/s] tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 15.4MB/s]
khanhnto-khanhnto-v54-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 60.7MB/s]
khanhnto-khanhnto-v54-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, 10.9MB/s]
khanhnto-khanhnto-v54-mkmlizer: Downloaded to shared memory in 49.536s
khanhnto-khanhnto-v54-mkmlizer: quantizing model to /dev/shm/model_cache
khanhnto-khanhnto-v54-mkmlizer: Saving mkml model at /dev/shm/model_cache
khanhnto-khanhnto-v54-mkmlizer: Reading /tmp/tmpecyarw9q/model.safetensors.index.json
khanhnto-khanhnto-v54-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:02<14:02, 2.33s/it] Profiling: 2%|▏ | 9/363 [00:02<01:10, 5.03it/s] Profiling: 5%|▍ | 17/363 [00:02<00:32, 10.73it/s] Profiling: 7%|▋ | 25/363 [00:02<00:19, 17.51it/s] Profiling: 9%|▉ | 33/363 [00:02<00:13, 25.17it/s] Profiling: 11%|█▏ | 41/363 [00:02<00:09, 32.99it/s] Profiling: 14%|█▍ | 50/363 [00:02<00:07, 42.17it/s] Profiling: 16%|█▋ | 59/363 [00:03<00:06, 50.65it/s] Profiling: 19%|█▉ | 69/363 [00:03<00:07, 39.57it/s] Profiling: 21%|██ | 76/363 [00:03<00:06, 44.46it/s] Profiling: 23%|██▎ | 84/363 [00:03<00:05, 51.09it/s] Profiling: 25%|██▌ | 92/363 [00:03<00:04, 56.98it/s] Profiling: 28%|██▊ | 100/363 [00:03<00:04, 61.82it/s] Profiling: 30%|██▉ | 108/363 [00:03<00:03, 65.79it/s] Profiling: 33%|███▎ | 118/363 [00:04<00:03, 74.33it/s] Profiling: 35%|███▍ | 127/363 [00:04<00:03, 74.87it/s] Profiling: 37%|███▋ | 135/363 [00:04<00:02, 76.08it/s] Profiling: 39%|███▉ | 143/363 [00:04<00:05, 43.55it/s] Profiling: 42%|████▏ | 152/363 [00:04<00:04, 51.35it/s] Profiling: 44%|████▍ | 161/363 [00:04<00:03, 58.33it/s] Profiling: 47%|████▋ | 169/363 [00:04<00:03, 63.12it/s] Profiling: 49%|████▉ | 177/363 [00:05<00:02, 67.18it/s] Profiling: 51%|█████ | 185/363 [00:05<00:02, 69.59it/s] Profiling: 53%|█████▎ | 194/363 [00:05<00:02, 73.28it/s] Profiling: 56%|█████▌ | 203/363 [00:05<00:02, 76.21it/s] Profiling: 58%|█████▊ | 211/363 [00:05<00:03, 48.59it/s] Profiling: 61%|██████ | 220/363 [00:05<00:02, 55.69it/s] Profiling: 63%|██████▎ | 229/363 [00:05<00:02, 62.06it/s] Profiling: 66%|██████▌ | 238/363 [00:06<00:01, 66.97it/s] Profiling: 68%|██████▊ | 247/363 [00:06<00:01, 71.16it/s] Profiling: 71%|███████ | 256/363 [00:06<00:01, 74.57it/s] Profiling: 73%|███████▎ | 265/363 [00:06<00:01, 76.74it/s] Profiling: 75%|███████▌ | 274/363 [00:06<00:01, 75.86it/s] Profiling: 78%|███████▊ | 282/363 [00:06<00:01, 51.35it/s] Profiling: 80%|████████ | 291/363 [00:06<00:01, 57.94it/s] Profiling: 83%|████████▎ | 300/363 [00:06<00:00, 63.56it/s] Profiling: 85%|████████▌ | 309/363 [00:07<00:00, 68.39it/s] Profiling: 88%|████████▊ | 318/363 [00:07<00:00, 72.50it/s] Profiling: 90%|█████████ | 327/363 [00:07<00:00, 74.69it/s] Profiling: 93%|█████████▎| 336/363 [00:07<00:00, 76.64it/s] Profiling: 95%|█████████▍| 344/363 [00:07<00:00, 75.65it/s] Profiling: 97%|█████████▋| 352/363 [00:09<00:00, 12.87it/s] Profiling: 100%|█████████▉| 362/363 [00:09<00:00, 18.15it/s] Profiling: 100%|██████████| 363/363 [00:09<00:00, 37.84it/s]
khanhnto-khanhnto-v54-mkmlizer: quantized model in 28.580s
khanhnto-khanhnto-v54-mkmlizer: Processed model khanhnto/khanhnto in 79.888s
khanhnto-khanhnto-v54-mkmlizer: creating bucket guanaco-mkml-models
khanhnto-khanhnto-v54-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
khanhnto-khanhnto-v54-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/khanhnto-khanhnto-v54
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/khanhnto-khanhnto-v54/added_tokens.json
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/khanhnto-khanhnto-v54/tokenizer.json
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v54/tokenizer_config.json
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/khanhnto-khanhnto-v54/tokenizer.model
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/khanhnto-khanhnto-v54/config.json
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/khanhnto-khanhnto-v54/special_tokens_map.json
khanhnto-khanhnto-v54-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/khanhnto-khanhnto-v54/mkml_model.tensors
khanhnto-khanhnto-v54-mkmlizer: loading reward model from rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99
khanhnto-khanhnto-v54-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-v54-mkmlizer: warnings.warn(
khanhnto-khanhnto-v54-mkmlizer: config.json: 0%| | 0.00/983 [00:00<?, ?B/s] config.json: 100%|██████████| 983/983 [00:00<00:00, 6.68MB/s]
khanhnto-khanhnto-v54-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-v54-mkmlizer: warnings.warn(
khanhnto-khanhnto-v54-mkmlizer: tokenizer_config.json: 0%| | 0.00/445 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 445/445 [00:00<00:00, 5.49MB/s]
khanhnto-khanhnto-v54-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 8.38MB/s]
khanhnto-khanhnto-v54-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 6.96MB/s]
khanhnto-khanhnto-v54-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 14.5MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 14.5MB/s]
khanhnto-khanhnto-v54-mkmlizer: special_tokens_map.json: 0%| | 0.00/441 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 441/441 [00:00<00:00, 3.32MB/s]
khanhnto-khanhnto-v54-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-v54-mkmlizer: warnings.warn(
khanhnto-khanhnto-v54-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, 65.2MB/s]
khanhnto-khanhnto-v54-mkmlizer: Downloading shards: 0%| | 0/1 [00:00<?, ?it/s]
khanhnto-khanhnto-v54-mkmlizer: model-00001-of-00001.safetensors: 0%| | 0.00/249M [00:00<?, ?B/s]
khanhnto-khanhnto-v54-mkmlizer: model-00001-of-00001.safetensors: 4%|▍ | 10.5M/249M [00:00<00:04, 53.3MB/s]
khanhnto-khanhnto-v54-mkmlizer: model-00001-of-00001.safetensors: 67%|██████▋ | 168M/249M [00:00<00:00, 654MB/s]  model-00001-of-00001.safetensors: 100%|█████████▉| 249M/249M [00:00<00:00, 517MB/s]
khanhnto-khanhnto-v54-mkmlizer: Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 1.05it/s] Downloading shards: 100%|██████████| 1/1 [00:00<00:00, 1.05it/s]
khanhnto-khanhnto-v54-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
khanhnto-khanhnto-v54-mkmlizer: Saving duration: 0.124s
khanhnto-khanhnto-v54-mkmlizer: Processed model rirv938/gpt2_ties_merge_preference_plus_classic_e2_density_99 in 3.465s
khanhnto-khanhnto-v54-mkmlizer: creating bucket guanaco-reward-models
khanhnto-khanhnto-v54-mkmlizer: Bucket 's3://guanaco-reward-models/' created
khanhnto-khanhnto-v54-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/config.json
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/special_tokens_map.json
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/tokenizer_config.json
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/merges.txt
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/vocab.json
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/tokenizer.json
khanhnto-khanhnto-v54-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/khanhnto-khanhnto-v54_reward/reward.tensors
Job khanhnto-khanhnto-v54-mkmlizer completed after 116.84s with status: succeeded
Stopping job with name khanhnto-khanhnto-v54-mkmlizer
Pipeline stage MKMLizer completed in 122.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service khanhnto-khanhnto-v54
Waiting for inference service khanhnto-khanhnto-v54 to be ready
Inference service khanhnto-khanhnto-v54 ready after 50.29734206199646s
Pipeline stage ISVCDeployer completed in 58.69s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7558236122131348s
Received healthy response to inference request in 1.7068984508514404s
Received healthy response to inference request in 1.453341007232666s
Received healthy response to inference request in 1.5200917720794678s
Received healthy response to inference request in 1.7603085041046143s
5 requests
0 failed requests
5th percentile: 1.4666911602020263
10th percentile: 1.4800413131713868
20th percentile: 1.5067416191101075
30th percentile: 1.5574531078338623
40th percentile: 1.6321757793426515
50th percentile: 1.7068984508514404
60th percentile: 1.7264685153961181
70th percentile: 1.7460385799407958
80th percentile: 1.7567205905914307
90th percentile: 1.7585145473480224
95th percentile: 1.7594115257263183
99th percentile: 1.760129108428955
mean time: 1.6392926692962646
Pipeline stage StressChecker completed in 9.12s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
AUTO_DEACTIVATION: submission %s deactivated %s
a100-khanhnto-khanhnto_v54 status is now inactive due to auto deactivation removed underperforming models
a100-khanhnto-khanhnto_v54 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics