submission_id: anhnv125-pawn_v3
developer_uid: vietanh
status: torndown
model_repo: anhnv125/pawn
reward_repo: anhnv125/reward-model-vj
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 30, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '</s>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "### Instruction:\nAs the assistant, your task is to fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}\n\n", 'prompt_template': '### Input:\n# Example conversation:\n{prompt}\n# Actual conversation:\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-02-03T14:21:58+00:00
model_name: anhnv125-pawn_v3
model_eval_status: success
model_group: anhnv125/pawn
num_battles: 18649
num_wins: 9017
celo_rating: 1138.32
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: None
model_num_parameters: 13015874560.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: anhnv125-pawn_v3
ineligible_reason: propriety_total_count < 800
language_model: anhnv125/pawn
model_size: 13B
reward_model: anhnv125/reward-model-vj
us_pacific_date: 2024-02-03
win_ratio: 0.4835111802241407
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name anhnv125-pawn-v3-mkmlizer
Waiting for job on anhnv125-pawn-v3-mkmlizer to finish
anhnv125-pawn-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
anhnv125-pawn-v3-mkmlizer: ║ _____ __ __ ║
anhnv125-pawn-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
anhnv125-pawn-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
anhnv125-pawn-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
anhnv125-pawn-v3-mkmlizer: ║ /___/ ║
anhnv125-pawn-v3-mkmlizer: ║ ║
anhnv125-pawn-v3-mkmlizer: ║ Version: 0.6.11 ║
anhnv125-pawn-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
anhnv125-pawn-v3-mkmlizer: ║ ║
anhnv125-pawn-v3-mkmlizer: ║ The license key for the current software has been verified as ║
anhnv125-pawn-v3-mkmlizer: ║ belonging to: ║
anhnv125-pawn-v3-mkmlizer: ║ ║
anhnv125-pawn-v3-mkmlizer: ║ Chai Research Corp. ║
anhnv125-pawn-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
anhnv125-pawn-v3-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
anhnv125-pawn-v3-mkmlizer: ║ ║
anhnv125-pawn-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
anhnv125-pawn-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.3MB/s]
anhnv125-pawn-v3-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, 266kB/s]
anhnv125-pawn-v3-mkmlizer: config.json: 0%| | 0.00/660 [00:00<?, ?B/s] config.json: 100%|██████████| 660/660 [00:00<00:00, 8.76MB/s]
anhnv125-pawn-v3-mkmlizer: generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 2.08MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model-00001-of-00006.bin: 0%| | 0.00/4.98G [00:00<?, ?B/s] pytorch_model-00001-of-00006.bin: 0%| | 10.5M/4.98G [00:00<04:15, 19.5MB/s] pytorch_model-00001-of-00006.bin: 0%| | 21.0M/4.98G [00:00<03:49, 21.6MB/s] pytorch_model-00001-of-00006.bin: 1%| | 31.5M/4.98G [00:01<03:29, 23.6MB/s] pytorch_model-00001-of-00006.bin: 1%|▏ | 62.9M/4.98G [00:01<01:26, 57.1MB/s] pytorch_model-00001-of-00006.bin: 3%|▎ | 126M/4.98G [00:01<00:34, 140MB/s] pytorch_model-00001-of-00006.bin: 3%|▎ | 157M/4.98G [00:01<00:33, 142MB/s] pytorch_model-00001-of-00006.bin: 4%|▍ | 220M/4.98G [00:02<00:23, 203MB/s] pytorch_model-00001-of-00006.bin: 5%|▌ | 262M/4.98G [00:02<00:21, 224MB/s] pytorch_model-00001-of-00006.bin: 6%|▋ | 315M/4.98G [00:02<00:17, 273MB/s] pytorch_model-00001-of-00006.bin: 7%|▋ | 357M/4.98G [00:02<00:16, 283MB/s] pytorch_model-00001-of-00006.bin: 8%|▊ | 419M/4.98G [00:02<00:12, 356MB/s] pytorch_model-00001-of-00006.bin: 11%|█ | 535M/4.98G [00:02<00:10, 424MB/s] pytorch_model-00001-of-00006.bin: 12%|█▏ | 587M/4.98G [00:02<00:09, 440MB/s] pytorch_model-00001-of-00006.bin: 13%|█▎ | 661M/4.98G [00:02<00:08, 504MB/s] pytorch_model-00001-of-00006.bin: 19%|█▊ | 923M/4.98G [00:03<00:03, 1.02GB/s] pytorch_model-00001-of-00006.bin: 31%|███▏ | 1.56G/4.98G [00:03<00:01, 2.13GB/s] pytorch_model-00001-of-00006.bin: 36%|███▌ | 1.77G/4.98G [00:04<00:04, 690MB/s] pytorch_model-00001-of-00006.bin: 39%|███▉ | 1.93G/4.98G [00:04<00:04, 750MB/s] pytorch_model-00001-of-00006.bin: 42%|████▏ | 2.08G/4.98G [00:04<00:03, 837MB/s] pytorch_model-00001-of-00006.bin: 45%|████▍ | 2.22G/4.98G [00:04<00:03, 803MB/s] pytorch_model-00001-of-00006.bin: 55%|█████▌ | 2.76G/4.98G [00:04<00:01, 1.47GB/s] pytorch_model-00001-of-00006.bin: 60%|█████▉ | 2.98G/4.98G [00:05<00:02, 986MB/s] pytorch_model-00001-of-00006.bin: 63%|██████▎ | 3.16G/4.98G [00:05<00:02, 611MB/s] pytorch_model-00001-of-00006.bin: 66%|██████▌ | 3.29G/4.98G [00:06<00:02, 625MB/s] pytorch_model-00001-of-00006.bin: 68%|██████▊ | 3.41G/4.98G [00:06<00:02, 679MB/s] pytorch_model-00001-of-00006.bin: 73%|███████▎ | 3.63G/4.98G [00:06<00:01, 882MB/s] pytorch_model-00001-of-00006.bin: 81%|████████ | 4.02G/4.98G [00:06<00:00, 1.36GB/s] pytorch_model-00001-of-00006.bin: 85%|████████▍ | 4.23G/4.98G [00:06<00:00, 1.23GB/s] pytorch_model-00001-of-00006.bin: 88%|████████▊ | 4.40G/4.98G [00:06<00:00, 836MB/s] pytorch_model-00001-of-00006.bin: 92%|█████████▏| 4.56G/4.98G [00:07<00:00, 931MB/s] pytorch_model-00001-of-00006.bin: 95%|█████████▍| 4.71G/4.98G [00:07<00:00, 1.00GB/s] pytorch_model-00001-of-00006.bin: 100%|█████████▉| 4.98G/4.98G [00:07<00:00, 1.30GB/s] pytorch_model-00001-of-00006.bin: 100%|█████████▉| 4.98G/4.98G [00:07<00:00, 676MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model-00002-of-00006.bin: 0%| | 0.00/4.97G [00:00<?, ?B/s] pytorch_model-00002-of-00006.bin: 0%| | 10.5M/4.97G [00:02<17:06, 4.83MB/s] pytorch_model-00002-of-00006.bin: 1%| | 31.5M/4.97G [00:02<04:51, 17.0MB/s] pytorch_model-00002-of-00006.bin: 1%| | 41.9M/4.97G [00:02<03:43, 22.0MB/s] pytorch_model-00002-of-00006.bin: 1%| | 52.4M/4.97G [00:02<02:49, 29.1MB/s] pytorch_model-00002-of-00006.bin: 2%|▏ | 83.9M/4.97G [00:02<01:23, 58.3MB/s] pytorch_model-00002-of-00006.bin: 5%|▍ | 231M/4.97G [00:02<00:19, 245MB/s] pytorch_model-00002-of-00006.bin: 7%|▋ | 367M/4.97G [00:03<00:10, 422MB/s] pytorch_model-00002-of-00006.bin: 9%|▉ | 451M/4.97G [00:03<00:10, 429MB/s] pytorch_model-00002-of-00006.bin: 18%|█▊ | 891M/4.97G [00:03<00:03, 1.16GB/s] pytorch_model-00002-of-00006.bin: 23%|██▎ | 1.16G/4.97G [00:03<00:02, 1.43GB/s] pytorch_model-00002-of-00006.bin: 27%|██▋ | 1.36G/4.97G [00:03<00:04, 830MB/s] pytorch_model-00002-of-00006.bin: 31%|███ | 1.52G/4.97G [00:04<00:04, 701MB/s] pytorch_model-00002-of-00006.bin: 34%|███▎ | 1.67G/4.97G [00:04<00:04, 800MB/s] pytorch_model-00002-of-00006.bin: 38%|███▊ | 1.87G/4.97G [00:04<00:03, 953MB/s] pytorch_model-00002-of-00006.bin: 40%|████ | 2.00G/4.97G [00:04<00:03, 982MB/s] pytorch_model-00002-of-00006.bin: 43%|████▎ | 2.14G/4.97G [00:04<00:02, 1.03GB/s] pytorch_model-00002-of-00006.bin: 49%|████▉ | 2.45G/4.97G [00:04<00:01, 1.45GB/s] pytorch_model-00002-of-00006.bin: 53%|█████▎ | 2.63G/4.97G [00:05<00:03, 761MB/s] pytorch_model-00002-of-00006.bin: 56%|█████▌ | 2.77G/4.97G [00:05<00:02, 735MB/s] pytorch_model-00002-of-00006.bin: 58%|█████▊ | 2.88G/4.97G [00:05<00:02, 754MB/s] pytorch_model-00002-of-00006.bin: 60%|██████ | 2.99G/4.97G [00:05<00:02, 759MB/s] pytorch_model-00002-of-00006.bin: 62%|██████▏ | 3.09G/4.97G [00:05<00:02, 798MB/s] pytorch_model-00002-of-00006.bin: 65%|██████▍ | 3.22G/4.97G [00:06<00:01, 883MB/s] pytorch_model-00002-of-00006.bin: 68%|██████▊ | 3.39G/4.97G [00:06<00:01, 1.05GB/s] pytorch_model-00002-of-00006.bin: 72%|███████▏ | 3.55G/4.97G [00:06<00:01, 1.18GB/s] pytorch_model-00002-of-00006.bin: 74%|███████▍ | 3.69G/4.97G [00:06<00:01, 760MB/s] pytorch_model-00002-of-00006.bin: 76%|███████▋ | 3.80G/4.97G [00:06<00:01, 697MB/s] pytorch_model-00002-of-00006.bin: 79%|███████▉ | 3.92G/4.97G [00:06<00:01, 740MB/s] pytorch_model-00002-of-00006.bin: 81%|████████ | 4.04G/4.97G [00:07<00:01, 741MB/s] pytorch_model-00002-of-00006.bin: 83%|████████▎ | 4.13G/4.97G [00:07<00:01, 710MB/s] pytorch_model-00002-of-00006.bin: 87%|████████▋ | 4.31G/4.97G [00:07<00:00, 927MB/s] pytorch_model-00002-of-00006.bin: 90%|█████████ | 4.48G/4.97G [00:07<00:00, 1.08GB/s] pytorch_model-00002-of-00006.bin: 95%|█████████▍| 4.71G/4.97G [00:07<00:00, 1.36GB/s] pytorch_model-00002-of-00006.bin: 99%|█████████▉| 4.92G/4.97G [00:07<00:00, 1.53GB/s] pytorch_model-00002-of-00006.bin: 100%|█████████▉| 4.97G/4.97G [00:07<00:00, 641MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model-00003-of-00006.bin: 0%| | 0.00/4.97G [00:00<?, ?B/s] pytorch_model-00003-of-00006.bin: 0%| | 10.5M/4.97G [00:01<10:30, 7.86MB/s] pytorch_model-00003-of-00006.bin: 0%| | 21.0M/4.97G [00:02<09:08, 9.02MB/s] pytorch_model-00003-of-00006.bin: 1%| | 31.5M/4.97G [00:02<05:52, 14.0MB/s] pytorch_model-00003-of-00006.bin: 1%| | 41.9M/4.97G [00:02<03:58, 20.6MB/s] pytorch_model-00003-of-00006.bin: 1%|▏ | 62.9M/4.97G [00:02<02:11, 37.4MB/s] pytorch_model-00003-of-00006.bin: 2%|▏ | 94.4M/4.97G [00:03<01:12, 67.0MB/s] pytorch_model-00003-of-00006.bin: 6%|▌ | 283M/4.97G [00:03<00:15, 312MB/s] pytorch_model-00003-of-00006.bin: 7%|▋ | 357M/4.97G [00:03<00:13, 348MB/s] pytorch_model-00003-of-00006.bin: 9%|▉ | 440M/4.97G [00:03<00:10, 430MB/s] pytorch_model-00003-of-00006.bin: 16%|█▌ | 797M/4.97G [00:03<00:03, 1.05GB/s] pytorch_model-00003-of-00006.bin: 23%|██▎ | 1.13G/4.97G [00:03<00:02, 1.40GB/s] pytorch_model-00003-of-00006.bin: 26%|██▋ | 1.31G/4.97G [00:04<00:06, 595MB/s] pytorch_model-00003-of-00006.bin: 29%|██▉ | 1.45G/4.97G [00:04<00:05, 654MB/s] pytorch_model-00003-of-00006.bin: 32%|███▏ | 1.59G/4.97G [00:04<00:04, 761MB/s] pytorch_model-00003-of-00006.bin: 35%|███▌ | 1.76G/4.97G [00:04<00:03, 901MB/s] pytorch_model-00003-of-00006.bin: 38%|███▊ | 1.91G/4.97G [00:05<00:04, 733MB/s] pytorch_model-00003-of-00006.bin: 41%|████ | 2.02G/4.97G [00:05<00:03, 800MB/s] pytorch_model-00003-of-00006.bin: 43%|████▎ | 2.14G/4.97G [00:05<00:04, 689MB/s] pytorch_model-00003-of-00006.bin: 48%|████▊ | 2.40G/4.97G [00:05<00:02, 1.02GB/s] pytorch_model-00003-of-00006.bin: 53%|█████▎ | 2.62G/4.97G [00:05<00:01, 1.25GB/s] pytorch_model-00003-of-00006.bin: 62%|██████▏ | 3.07G/4.97G [00:05<00:00, 1.96GB/s] pytorch_model-00003-of-00006.bin: 67%|██████▋ | 3.32G/4.97G [00:06<00:02, 721MB/s] pytorch_model-00003-of-00006.bin: 71%|███████ | 3.51G/4.97G [00:06<00:01, 788MB/s] pytorch_model-00003-of-00006.bin: 74%|███████▍ | 3.68G/4.97G [00:06<00:01, 860MB/s] pytorch_model-00003-of-00006.bin: 77%|███████▋ | 3.84G/4.97G [00:07<00:01, 883MB/s] pytorch_model-00003-of-00006.bin: 85%|████████▌ | 4.23G/4.97G [00:07<00:00, 1.30GB/s] pytorch_model-00003-of-00006.bin: 89%|████████▉ | 4.41G/4.97G [00:07<00:00, 985MB/s] pytorch_model-00003-of-00006.bin: 92%|█████████▏| 4.57G/4.97G [00:07<00:00, 1.07GB/s] pytorch_model-00003-of-00006.bin: 96%|█████████▌| 4.78G/4.97G [00:07<00:00, 1.23GB/s] pytorch_model-00003-of-00006.bin: 100%|█████████▉| 4.97G/4.97G [00:07<00:00, 627MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model-00004-of-00006.bin: 0%| | 0.00/4.93G [00:00<?, ?B/s] pytorch_model-00004-of-00006.bin: 0%| | 10.5M/4.93G [00:00<02:50, 28.9MB/s] pytorch_model-00004-of-00006.bin: 0%| | 21.0M/4.93G [00:01<07:30, 10.9MB/s] pytorch_model-00004-of-00006.bin: 1%| | 31.5M/4.93G [00:02<06:30, 12.6MB/s] pytorch_model-00004-of-00006.bin: 1%| | 52.4M/4.93G [00:02<03:02, 26.7MB/s] pytorch_model-00004-of-00006.bin: 1%|▏ | 62.9M/4.93G [00:02<02:28, 32.8MB/s] pytorch_model-00004-of-00006.bin: 1%|▏ | 73.4M/4.93G [00:02<02:06, 38.4MB/s] pytorch_model-00004-of-00006.bin: 3%|▎ | 147M/4.93G [00:02<00:37, 129MB/s] pytorch_model-00004-of-00006.bin: 6%|▌ | 304M/4.93G [00:03<00:13, 349MB/s] pytorch_model-00004-of-00006.bin: 7%|▋ | 367M/4.93G [00:03<00:13, 341MB/s] pytorch_model-00004-of-00006.bin: 12%|█▏ | 577M/4.93G [00:03<00:06, 654MB/s] pytorch_model-00004-of-00006.bin: 24%|██▍ | 1.17G/4.93G [00:03<00:02, 1.73GB/s] pytorch_model-00004-of-00006.bin: 29%|██▉ | 1.43G/4.93G [00:04<00:05, 647MB/s] pytorch_model-00004-of-00006.bin: 33%|███▎ | 1.61G/4.93G [00:04<00:05, 659MB/s] pytorch_model-00004-of-00006.bin: 37%|███▋ | 1.85G/4.93G [00:04<00:03, 835MB/s] pytorch_model-00004-of-00006.bin: 41%|████ | 2.02G/4.93G [00:05<00:03, 805MB/s] pytorch_model-00004-of-00006.bin: 44%|████▍ | 2.19G/4.93G [00:05<00:02, 920MB/s] pytorch_model-00004-of-00006.bin: 52%|█████▏ | 2.57G/4.93G [00:05<00:01, 1.37GB/s] pytorch_model-00004-of-00006.bin: 56%|█████▋ | 2.78G/4.93G [00:05<00:01, 1.16GB/s] pytorch_model-00004-of-00006.bin: 60%|█████▉ | 2.96G/4.93G [00:05<00:02, 940MB/s] pytorch_model-00004-of-00006.bin: 63%|██████▎ | 3.09G/4.93G [00:06<00:02, 698MB/s] pytorch_model-00004-of-00006.bin: 65%|██████▌ | 3.21G/4.93G [00:06<00:02, 702MB/s] pytorch_model-00004-of-00006.bin: 67%|██████▋ | 3.31G/4.93G [00:06<00:02, 753MB/s] pytorch_model-00004-of-00006.bin: 73%|███████▎ | 3.62G/4.93G [00:06<00:01, 1.15GB/s] pytorch_model-00004-of-00006.bin: 78%|███████▊ | 3.83G/4.93G [00:06<00:00, 1.32GB/s] pytorch_model-00004-of-00006.bin: 81%|████████ | 4.01G/4.93G [00:06<00:00, 1.34GB/s] pytorch_model-00004-of-00006.bin: 85%|████████▍ | 4.17G/4.93G [00:07<00:00, 834MB/s] pytorch_model-00004-of-00006.bin: 87%|████████▋ | 4.30G/4.93G [00:07<00:00, 862MB/s] pytorch_model-00004-of-00006.bin: 90%|████████▉ | 4.43G/4.93G [00:07<00:00, 884MB/s] pytorch_model-00004-of-00006.bin: 93%|█████████▎| 4.61G/4.93G [00:07<00:00, 993MB/s] pytorch_model-00004-of-00006.bin: 96%|█████████▌| 4.73G/4.93G [00:07<00:00, 975MB/s] pytorch_model-00004-of-00006.bin: 100%|█████████▉| 4.93G/4.93G [00:07<00:00, 626MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model-00005-of-00006.bin: 0%| | 0.00/4.93G [00:00<?, ?B/s] pytorch_model-00005-of-00006.bin: 0%| | 10.5M/4.93G [00:02<16:32, 4.96MB/s] pytorch_model-00005-of-00006.bin: 0%| | 21.0M/4.93G [00:02<07:33, 10.8MB/s] pytorch_model-00005-of-00006.bin: 1%| | 31.5M/4.93G [00:02<04:30, 18.1MB/s] pytorch_model-00005-of-00006.bin: 1%| | 52.4M/4.93G [00:02<02:16, 35.7MB/s] pytorch_model-00005-of-00006.bin: 2%|▏ | 115M/4.93G [00:02<00:44, 107MB/s] pytorch_model-00005-of-00006.bin: 4%|▎ | 178M/4.93G [00:02<00:25, 184MB/s] pytorch_model-00005-of-00006.bin: 7%|▋ | 325M/4.93G [00:02<00:11, 406MB/s] pytorch_model-00005-of-00006.bin: 10%|▉ | 482M/4.93G [00:02<00:07, 636MB/s] pytorch_model-00005-of-00006.bin: 12%|█▏ | 587M/4.93G [00:03<00:06, 656MB/s] pytorch_model-00005-of-00006.bin: 22%|██▏ | 1.10G/4.93G [00:03<00:02, 1.40GB/s] pytorch_model-00005-of-00006.bin: 26%|██▌ | 1.26G/4.93G [00:04<00:05, 620MB/s] pytorch_model-00005-of-00006.bin: 28%|██▊ | 1.37G/4.93G [00:04<00:05, 656MB/s] pytorch_model-00005-of-00006.bin: 30%|██▉ | 1.48G/4.93G [00:04<00:05, 609MB/s] pytorch_model-00005-of-00006.bin: 32%|███▏ | 1.57G/4.93G [00:04<00:05, 595MB/s] pytorch_model-00005-of-00006.bin: 34%|███▎ | 1.66G/4.93G [00:04<00:05, 621MB/s] pytorch_model-00005-of-00006.bin: 35%|███▌ | 1.75G/4.93G [00:04<00:04, 659MB/s] pytorch_model-00005-of-00006.bin: 38%|███▊ | 1.90G/4.93G [00:04<00:03, 811MB/s] pytorch_model-00005-of-00006.bin: 41%|████ | 2.00G/4.93G [00:05<00:03, 795MB/s] pytorch_model-00005-of-00006.bin: 43%|████▎ | 2.10G/4.93G [00:05<00:03, 812MB/s] pytorch_model-00005-of-00006.bin: 45%|████▌ | 2.22G/4.93G [00:05<00:03, 851MB/s] pytorch_model-00005-of-00006.bin: 47%|████▋ | 2.32G/4.93G [00:05<00:03, 663MB/s] pytorch_model-00005-of-00006.bin: 54%|█████▍ | 2.68G/4.93G [00:05<00:01, 1.28GB/s] pytorch_model-00005-of-00006.bin: 65%|██████▌ | 3.23G/4.93G [00:05<00:00, 2.18GB/s] pytorch_model-00005-of-00006.bin: 71%|███████ | 3.49G/4.93G [00:06<00:01, 756MB/s] pytorch_model-00005-of-00006.bin: 75%|███████▍ | 3.69G/4.93G [00:06<00:01, 862MB/s] pytorch_model-00005-of-00006.bin: 79%|███████▊ | 3.88G/4.93G [00:06<00:01, 860MB/s] pytorch_model-00005-of-00006.bin: 88%|████████▊ | 4.34G/4.93G [00:07<00:00, 1.36GB/s] pytorch_model-00005-of-00006.bin: 93%|█████████▎| 4.59G/4.93G [00:07<00:00, 1.37GB/s] pytorch_model-00005-of-00006.bin: 98%|█████████▊| 4.81G/4.93G [00:07<00:00, 1.45GB/s] pytorch_model-00005-of-00006.bin: 100%|█████████▉| 4.93G/4.93G [00:08<00:00, 607MB/s]
anhnv125-pawn-v3-mkmlizer: pytorch_model.bin.index.json: 0%| | 0.00/29.9k [00:00<?, ?B/s] pytorch_model.bin.index.json: 100%|██████████| 29.9k/29.9k [00:00<00:00, 167MB/s]
anhnv125-pawn-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/549 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 549/549 [00:00<00:00, 7.29MB/s]
anhnv125-pawn-v3-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 15.5MB/s]
anhnv125-pawn-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/1.15k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 1.15k/1.15k [00:00<00:00, 15.2MB/s]
anhnv125-pawn-v3-mkmlizer: Downloaded to shared memory in 45.544s
anhnv125-pawn-v3-mkmlizer: quantizing model to /dev/shm/model_cache
anhnv125-pawn-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
anhnv125-pawn-v3-mkmlizer: Reading /tmp/tmpwvfzwsnf/pytorch_model.bin.index.json
anhnv125-pawn-v3-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:02<17:50, 2.96s/it] Profiling: 19%|█▉ | 69/363 [00:03<00:12, 23.88it/s] Profiling: 38%|███▊ | 139/363 [00:04<00:05, 42.37it/s] Profiling: 58%|█████▊ | 209/363 [00:05<00:02, 56.09it/s] Profiling: 77%|███████▋ | 278/363 [00:06<00:01, 66.56it/s] Profiling: 96%|█████████▌| 349/363 [00:06<00:00, 91.87it/s] Profiling: 100%|██████████| 363/363 [00:07<00:00, 46.67it/s]
anhnv125-pawn-v3-mkmlizer: quantized model in 25.527s
anhnv125-pawn-v3-mkmlizer: Processed model anhnv125/pawn in 72.744s
anhnv125-pawn-v3-mkmlizer: creating bucket guanaco-mkml-models
anhnv125-pawn-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
anhnv125-pawn-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/anhnv125-pawn-v3
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/anhnv125-pawn-v3/config.json
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/anhnv125-pawn-v3/special_tokens_map.json
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/anhnv125-pawn-v3/tokenizer_config.json
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/anhnv125-pawn-v3/added_tokens.json
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/anhnv125-pawn-v3/tokenizer.model
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/anhnv125-pawn-v3/tokenizer.json
anhnv125-pawn-v3-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/anhnv125-pawn-v3/mkml_model.tensors
anhnv125-pawn-v3-mkmlizer: loading reward model from anhnv125/reward-model-vj
anhnv125-pawn-v3-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.
anhnv125-pawn-v3-mkmlizer: warnings.warn(
anhnv125-pawn-v3-mkmlizer: config.json: 0%| | 0.00/1.03k [00:00<?, ?B/s] config.json: 100%|██████████| 1.03k/1.03k [00:00<00:00, 11.7MB/s]
anhnv125-pawn-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
anhnv125-pawn-v3-mkmlizer: warnings.warn(
anhnv125-pawn-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/477 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 477/477 [00:00<00:00, 4.35MB/s]
anhnv125-pawn-v3-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 19.1MB/s]
anhnv125-pawn-v3-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 21.3MB/s]
anhnv125-pawn-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 27.0MB/s]
anhnv125-pawn-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/473 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 473/473 [00:00<00:00, 5.67MB/s]
anhnv125-pawn-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
anhnv125-pawn-v3-mkmlizer: warnings.warn(
anhnv125-pawn-v3-mkmlizer: model.safetensors: 0%| | 0.00/498M [00:00<?, ?B/s] model.safetensors: 2%|▏ | 10.5M/498M [00:00<00:13, 36.1MB/s] model.safetensors: 8%|▊ | 41.9M/498M [00:00<00:04, 112MB/s] model.safetensors: 12%|█▏ | 57.4M/498M [00:00<00:05, 75.9MB/s] model.safetensors: 14%|█▎ | 67.9M/498M [00:00<00:05, 77.8MB/s] model.safetensors: 16%|█▌ | 78.4M/498M [00:01<00:06, 61.8MB/s] model.safetensors: 18%|█▊ | 88.8M/498M [00:01<00:06, 66.9MB/s] model.safetensors: 30%|███ | 152M/498M [00:01<00:01, 179MB/s] model.safetensors: 100%|█████████▉| 498M/498M [00:01<00:00, 348MB/s]
anhnv125-pawn-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
anhnv125-pawn-v3-mkmlizer: Saving duration: 0.096s
anhnv125-pawn-v3-mkmlizer: Processed model anhnv125/reward-model-vj in 3.591s
anhnv125-pawn-v3-mkmlizer: creating bucket guanaco-reward-models
anhnv125-pawn-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
anhnv125-pawn-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/anhnv125-pawn-v3_reward
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/anhnv125-pawn-v3_reward/config.json
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/anhnv125-pawn-v3_reward/tokenizer_config.json
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/anhnv125-pawn-v3_reward/special_tokens_map.json
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/anhnv125-pawn-v3_reward/merges.txt
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/anhnv125-pawn-v3_reward/vocab.json
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/anhnv125-pawn-v3_reward/tokenizer.json
anhnv125-pawn-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/anhnv125-pawn-v3_reward/reward.tensors
Job anhnv125-pawn-v3-mkmlizer completed after 106.88s with status: succeeded
Stopping job with name anhnv125-pawn-v3-mkmlizer
Pipeline stage MKMLizer completed in 112.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service anhnv125-pawn-v3
Waiting for inference service anhnv125-pawn-v3 to be ready
Inference service anhnv125-pawn-v3 ready after 40.23964071273804s
Pipeline stage ISVCDeployer completed in 48.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.88179349899292s
Received healthy response to inference request in 1.8683805465698242s
Received healthy response to inference request in 1.9086248874664307s
Received healthy response to inference request in 1.8333280086517334s
Received healthy response to inference request in 1.883225917816162s
5 requests
0 failed requests
5th percentile: 1.8403385162353516
10th percentile: 1.8473490238189698
20th percentile: 1.861370038986206
30th percentile: 1.8713496208190918
40th percentile: 1.8772877693176269
50th percentile: 1.883225917816162
60th percentile: 1.8933855056762696
70th percentile: 1.903545093536377
80th percentile: 2.1032586097717285
90th percentile: 2.492526054382324
95th percentile: 2.687159776687622
99th percentile: 2.8428667545318604
mean time: 2.0750705718994142
Pipeline stage StressChecker completed in 11.36s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.06s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
anhnv125-pawn_v3 status is now deployed due to admin request
anhnv125-pawn_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of anhnv125-pawn_v3
Running pipeline stage ISVCDeleter
Checking if service anhnv125-pawn-v3 is running
Tearing down inference service anhnv125-pawn-v3
Toredown service anhnv125-pawn-v3
Pipeline stage ISVCDeleter completed in 5.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key anhnv125-pawn-v3/added_tokens.json from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/config.json from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key anhnv125-pawn-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key anhnv125-pawn-v3_reward/config.json from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key anhnv125-pawn-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.94s
anhnv125-pawn_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics