submission_id: katydeng-katy-new_v1
developer_uid: kathy196
status: inactive
model_repo: katydeng/katy_new
reward_repo: ChaiML/reward_models_100_170000000_cp_498032
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 20, '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.\nYour character: {bot_name}.\nContext: {memory}\n", 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:'}
timestamp: 2024-02-08T23:46:56+00:00
model_name: katydeng-katy-new_v1
model_eval_status: success
safety_score: 0.94
entertaining: 7.06
stay_in_character: 8.62
user_preference: 7.56
double_thumbs_up: 7379
thumbs_up: 11240
thumbs_down: 4558
num_battles: 360200
num_wins: 174096
win_ratio: 0.4833314825097168
celo_rating: 1145.52
Resubmit model
Running pipeline stage MKMLizer
Starting job with name katydeng-katy-new-v1-mkmlizer
Waiting for job on katydeng-katy-new-v1-mkmlizer to finish
Stopping job with name katydeng-katy-new-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name katydeng-katy-new-v1-mkmlizer
Waiting for job on katydeng-katy-new-v1-mkmlizer to finish
katydeng-katy-new-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
katydeng-katy-new-v1-mkmlizer: ║ _____ __ __ ║
katydeng-katy-new-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
katydeng-katy-new-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
katydeng-katy-new-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
katydeng-katy-new-v1-mkmlizer: ║ /___/ ║
katydeng-katy-new-v1-mkmlizer: ║ ║
katydeng-katy-new-v1-mkmlizer: ║ Version: 0.6.11 ║
katydeng-katy-new-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
katydeng-katy-new-v1-mkmlizer: ║ ║
katydeng-katy-new-v1-mkmlizer: ║ The license key for the current software has been verified as ║
katydeng-katy-new-v1-mkmlizer: ║ belonging to: ║
katydeng-katy-new-v1-mkmlizer: ║ ║
katydeng-katy-new-v1-mkmlizer: ║ Chai Research Corp. ║
katydeng-katy-new-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
katydeng-katy-new-v1-mkmlizer: ║ Expiration: 2024-04-15 23:59:59 ║
katydeng-katy-new-v1-mkmlizer: ║ ║
katydeng-katy-new-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
katydeng-katy-new-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 15.2MB/s]
katydeng-katy-new-v1-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, 170kB/s]
katydeng-katy-new-v1-mkmlizer: config.json: 0%| | 0.00/660 [00:00<?, ?B/s] config.json: 100%|██████████| 660/660 [00:00<00:00, 9.11MB/s]
katydeng-katy-new-v1-mkmlizer: generation_config.json: 0%| | 0.00/154 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 154/154 [00:00<00:00, 2.02MB/s]
katydeng-katy-new-v1-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 [00:01<09:27, 8.75MB/s] pytorch_model-00001-of-00006.bin: 1%| | 31.5M/4.98G [00:01<02:50, 29.0MB/s] pytorch_model-00001-of-00006.bin: 1%| | 41.9M/4.98G [00:01<02:23, 34.4MB/s] pytorch_model-00001-of-00006.bin: 2%|▏ | 83.9M/4.98G [00:01<00:55, 87.9MB/s] pytorch_model-00001-of-00006.bin: 4%|▍ | 199M/4.98G [00:01<00:18, 261MB/s] pytorch_model-00001-of-00006.bin: 7%|▋ | 346M/4.98G [00:01<00:10, 441MB/s] pytorch_model-00001-of-00006.bin: 8%|▊ | 419M/4.98G [00:02<00:09, 470MB/s] pytorch_model-00001-of-00006.bin: 10%|▉ | 482M/4.98G [00:02<00:09, 470MB/s] pytorch_model-00001-of-00006.bin: 12%|█▏ | 577M/4.98G [00:02<00:07, 570MB/s] pytorch_model-00001-of-00006.bin: 14%|█▎ | 682M/4.98G [00:02<00:06, 677MB/s] pytorch_model-00001-of-00006.bin: 16%|█▌ | 807M/4.98G [00:02<00:05, 807MB/s] pytorch_model-00001-of-00006.bin: 18%|█▊ | 902M/4.98G [00:02<00:06, 621MB/s] pytorch_model-00001-of-00006.bin: 20%|█▉ | 986M/4.98G [00:02<00:06, 585MB/s] pytorch_model-00001-of-00006.bin: 21%|██▏ | 1.07G/4.98G [00:03<00:06, 606MB/s] pytorch_model-00001-of-00006.bin: 28%|██▊ | 1.38G/4.98G [00:03<00:03, 1.16GB/s] pytorch_model-00001-of-00006.bin: 36%|███▌ | 1.78G/4.98G [00:03<00:01, 1.83GB/s] pytorch_model-00001-of-00006.bin: 40%|████ | 2.00G/4.98G [00:03<00:02, 1.41GB/s] pytorch_model-00001-of-00006.bin: 44%|████▍ | 2.18G/4.98G [00:04<00:04, 691MB/s] pytorch_model-00001-of-00006.bin: 47%|████▋ | 2.32G/4.98G [00:04<00:03, 731MB/s] pytorch_model-00001-of-00006.bin: 49%|████▉ | 2.44G/4.98G [00:04<00:03, 742MB/s] pytorch_model-00001-of-00006.bin: 51%|█████▏ | 2.56G/4.98G [00:04<00:03, 803MB/s] pytorch_model-00001-of-00006.bin: 54%|█████▎ | 2.67G/4.98G [00:04<00:02, 815MB/s] pytorch_model-00001-of-00006.bin: 57%|█████▋ | 2.83G/4.98G [00:04<00:02, 963MB/s] pytorch_model-00001-of-00006.bin: 65%|██████▌ | 3.25G/4.98G [00:04<00:01, 1.66GB/s] pytorch_model-00001-of-00006.bin: 70%|██████▉ | 3.46G/4.98G [00:04<00:00, 1.63GB/s] pytorch_model-00001-of-00006.bin: 74%|███████▎ | 3.66G/4.98G [00:05<00:01, 825MB/s] pytorch_model-00001-of-00006.bin: 76%|███████▋ | 3.81G/4.98G [00:05<00:01, 775MB/s] pytorch_model-00001-of-00006.bin: 79%|███████▉ | 3.93G/4.98G [00:05<00:01, 751MB/s] pytorch_model-00001-of-00006.bin: 81%|████████ | 4.04G/4.98G [00:06<00:01, 757MB/s] pytorch_model-00001-of-00006.bin: 83%|████████▎ | 4.14G/4.98G [00:06<00:01, 788MB/s] pytorch_model-00001-of-00006.bin: 88%|████████▊ | 4.36G/4.98G [00:06<00:00, 1.05GB/s] pytorch_model-00001-of-00006.bin: 92%|█████████▏| 4.56G/4.98G [00:06<00:00, 1.23GB/s] pytorch_model-00001-of-00006.bin: 98%|█████████▊| 4.90G/4.98G [00:06<00:00, 1.73GB/s] pytorch_model-00001-of-00006.bin: 100%|█████████▉| 4.98G/4.98G [00:06<00:00, 740MB/s]
katydeng-katy-new-v1-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 [00:00<05:07, 16.1MB/s] pytorch_model-00002-of-00006.bin: 0%| | 21.0M/4.97G [00:00<03:27, 23.8MB/s] pytorch_model-00002-of-00006.bin: 1%| | 31.5M/4.97G [00:01<02:25, 34.0MB/s] pytorch_model-00002-of-00006.bin: 1%| | 52.4M/4.97G [00:01<01:27, 56.3MB/s] pytorch_model-00002-of-00006.bin: 1%|▏ | 62.9M/4.97G [00:01<01:28, 55.6MB/s] pytorch_model-00002-of-00006.bin: 2%|▏ | 105M/4.97G [00:01<00:40, 120MB/s] pytorch_model-00002-of-00006.bin: 3%|▎ | 157M/4.97G [00:01<00:25, 187MB/s] pytorch_model-00002-of-00006.bin: 4%|▍ | 189M/4.97G [00:01<00:26, 184MB/s] pytorch_model-00002-of-00006.bin: 5%|▍ | 231M/4.97G [00:02<00:21, 217MB/s] pytorch_model-00002-of-00006.bin: 5%|▌ | 273M/4.97G [00:02<00:19, 242MB/s] pytorch_model-00002-of-00006.bin: 7%|▋ | 325M/4.97G [00:02<00:16, 276MB/s] pytorch_model-00002-of-00006.bin: 7%|▋ | 367M/4.97G [00:02<00:15, 305MB/s] pytorch_model-00002-of-00006.bin: 8%|▊ | 409M/4.97G [00:02<00:15, 297MB/s] pytorch_model-00002-of-00006.bin: 9%|▉ | 472M/4.97G [00:02<00:12, 372MB/s] pytorch_model-00002-of-00006.bin: 11%|█ | 524M/4.97G [00:02<00:11, 381MB/s] pytorch_model-00002-of-00006.bin: 11%|█▏ | 566M/4.97G [00:02<00:12, 341MB/s] pytorch_model-00002-of-00006.bin: 13%|█▎ | 640M/4.97G [00:03<00:10, 427MB/s] pytorch_model-00002-of-00006.bin: 19%|█▉ | 933M/4.97G [00:03<00:03, 1.04GB/s] pytorch_model-00002-of-00006.bin: 31%|███ | 1.55G/4.97G [00:03<00:01, 2.02GB/s] pytorch_model-00002-of-00006.bin: 35%|███▌ | 1.75G/4.97G [00:04<00:05, 593MB/s] pytorch_model-00002-of-00006.bin: 38%|███▊ | 1.90G/4.97G [00:04<00:04, 660MB/s] pytorch_model-00002-of-00006.bin: 41%|████ | 2.03G/4.97G [00:04<00:04, 627MB/s] pytorch_model-00002-of-00006.bin: 43%|████▎ | 2.15G/4.97G [00:04<00:04, 642MB/s] pytorch_model-00002-of-00006.bin: 45%|████▌ | 2.25G/4.97G [00:05<00:04, 647MB/s] pytorch_model-00002-of-00006.bin: 47%|████▋ | 2.35G/4.97G [00:05<00:03, 677MB/s] pytorch_model-00002-of-00006.bin: 50%|████▉ | 2.47G/4.97G [00:05<00:03, 711MB/s] pytorch_model-00002-of-00006.bin: 53%|█████▎ | 2.63G/4.97G [00:05<00:02, 827MB/s] pytorch_model-00002-of-00006.bin: 55%|█████▌ | 2.74G/4.97G [00:05<00:02, 818MB/s] pytorch_model-00002-of-00006.bin: 57%|█████▋ | 2.83G/4.97G [00:05<00:02, 812MB/s] pytorch_model-00002-of-00006.bin: 67%|██████▋ | 3.32G/4.97G [00:05<00:00, 1.71GB/s] pytorch_model-00002-of-00006.bin: 71%|███████ | 3.52G/4.97G [00:06<00:01, 1.39GB/s] pytorch_model-00002-of-00006.bin: 74%|███████▍ | 3.69G/4.97G [00:06<00:01, 1.10GB/s] pytorch_model-00002-of-00006.bin: 77%|███████▋ | 3.83G/4.97G [00:06<00:01, 840MB/s] pytorch_model-00002-of-00006.bin: 79%|███████▉ | 3.94G/4.97G [00:07<00:01, 604MB/s] pytorch_model-00002-of-00006.bin: 82%|████████▏ | 4.06G/4.97G [00:07<00:01, 675MB/s] pytorch_model-00002-of-00006.bin: 85%|████████▌ | 4.23G/4.97G [00:07<00:00, 817MB/s] pytorch_model-00002-of-00006.bin: 88%|████████▊ | 4.36G/4.97G [00:07<00:00, 916MB/s] pytorch_model-00002-of-00006.bin: 91%|█████████ | 4.53G/4.97G [00:07<00:00, 1.05GB/s] pytorch_model-00002-of-00006.bin: 99%|█████████▊| 4.91G/4.97G [00:07<00:00, 1.65GB/s] pytorch_model-00002-of-00006.bin: 100%|█████████▉| 4.97G/4.97G [00:07<00:00, 639MB/s]
katydeng-katy-new-v1-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<09:15, 8.93MB/s] pytorch_model-00003-of-00006.bin: 0%| | 21.0M/4.97G [00:01<04:16, 19.3MB/s] pytorch_model-00003-of-00006.bin: 1%| | 52.4M/4.97G [00:01<01:24, 58.3MB/s] pytorch_model-00003-of-00006.bin: 2%|▏ | 105M/4.97G [00:01<00:39, 123MB/s] pytorch_model-00003-of-00006.bin: 4%|▎ | 178M/4.97G [00:01<00:22, 214MB/s] pytorch_model-00003-of-00006.bin: 5%|▍ | 231M/4.97G [00:01<00:20, 232MB/s] pytorch_model-00003-of-00006.bin: 6%|▌ | 283M/4.97G [00:01<00:16, 285MB/s] pytorch_model-00003-of-00006.bin: 7%|▋ | 336M/4.97G [00:02<00:14, 313MB/s] pytorch_model-00003-of-00006.bin: 8%|▊ | 388M/4.97G [00:02<00:13, 333MB/s] pytorch_model-00003-of-00006.bin: 9%|▉ | 440M/4.97G [00:02<00:12, 362MB/s] pytorch_model-00003-of-00006.bin: 10%|▉ | 493M/4.97G [00:02<00:11, 398MB/s] pytorch_model-00003-of-00006.bin: 11%|█ | 545M/4.97G [00:02<00:12, 351MB/s] pytorch_model-00003-of-00006.bin: 12%|█▏ | 598M/4.97G [00:02<00:11, 389MB/s] pytorch_model-00003-of-00006.bin: 14%|█▍ | 692M/4.97G [00:02<00:08, 497MB/s] pytorch_model-00003-of-00006.bin: 16%|█▌ | 797M/4.97G [00:02<00:06, 606MB/s] pytorch_model-00003-of-00006.bin: 18%|█▊ | 902M/4.97G [00:03<00:06, 633MB/s] pytorch_model-00003-of-00006.bin: 20%|█▉ | 975M/4.97G [00:03<00:07, 529MB/s] pytorch_model-00003-of-00006.bin: 21%|██▏ | 1.06G/4.97G [00:03<00:06, 590MB/s] pytorch_model-00003-of-00006.bin: 30%|███ | 1.50G/4.97G [00:03<00:02, 1.49GB/s] pytorch_model-00003-of-00006.bin: 35%|███▌ | 1.76G/4.97G [00:03<00:02, 1.39GB/s] pytorch_model-00003-of-00006.bin: 39%|███▉ | 1.93G/4.97G [00:04<00:03, 949MB/s] pytorch_model-00003-of-00006.bin: 42%|████▏ | 2.07G/4.97G [00:04<00:04, 722MB/s] pytorch_model-00003-of-00006.bin: 44%|████▎ | 2.17G/4.97G [00:04<00:04, 684MB/s] pytorch_model-00003-of-00006.bin: 46%|████▌ | 2.30G/4.97G [00:04<00:03, 767MB/s] pytorch_model-00003-of-00006.bin: 49%|████▊ | 2.42G/4.97G [00:04<00:03, 848MB/s] pytorch_model-00003-of-00006.bin: 51%|█████ | 2.53G/4.97G [00:04<00:02, 888MB/s] pytorch_model-00003-of-00006.bin: 53%|█████▎ | 2.63G/4.97G [00:05<00:02, 852MB/s] pytorch_model-00003-of-00006.bin: 56%|█████▌ | 2.78G/4.97G [00:05<00:02, 936MB/s] pytorch_model-00003-of-00006.bin: 58%|█████▊ | 2.88G/4.97G [00:05<00:02, 820MB/s] pytorch_model-00003-of-00006.bin: 67%|██████▋ | 3.32G/4.97G [00:05<00:01, 1.61GB/s] pytorch_model-00003-of-00006.bin: 71%|███████ | 3.52G/4.97G [00:05<00:01, 1.44GB/s] pytorch_model-00003-of-00006.bin: 74%|███████▍ | 3.70G/4.97G [00:05<00:01, 1.11GB/s] pytorch_model-00003-of-00006.bin: 77%|███████▋ | 3.85G/4.97G [00:06<00:01, 899MB/s] pytorch_model-00003-of-00006.bin: 80%|███████▉ | 3.96G/4.97G [00:06<00:01, 681MB/s] pytorch_model-00003-of-00006.bin: 82%|████████▏ | 4.09G/4.97G [00:06<00:01, 758MB/s] pytorch_model-00003-of-00006.bin: 85%|████████▌ | 4.25G/4.97G [00:06<00:00, 897MB/s] pytorch_model-00003-of-00006.bin: 89%|████████▊ | 4.40G/4.97G [00:06<00:00, 1.02GB/s] pytorch_model-00003-of-00006.bin: 91%|█████████ | 4.53G/4.97G [00:06<00:00, 1.03GB/s] pytorch_model-00003-of-00006.bin: 95%|█████████▌| 4.74G/4.97G [00:07<00:00, 1.28GB/s] pytorch_model-00003-of-00006.bin: 100%|█████████▉| 4.97G/4.97G [00:07<00:00, 699MB/s]
katydeng-katy-new-v1-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<06:21, 12.9MB/s] pytorch_model-00004-of-00006.bin: 0%| | 21.0M/4.93G [00:00<03:26, 23.8MB/s] pytorch_model-00004-of-00006.bin: 1%| | 41.9M/4.93G [00:01<01:35, 51.2MB/s] pytorch_model-00004-of-00006.bin: 2%|▏ | 94.4M/4.93G [00:01<00:37, 130MB/s] pytorch_model-00004-of-00006.bin: 3%|▎ | 168M/4.93G [00:01<00:19, 249MB/s] pytorch_model-00004-of-00006.bin: 5%|▍ | 231M/4.93G [00:01<00:16, 284MB/s] pytorch_model-00004-of-00006.bin: 6%|▌ | 283M/4.93G [00:01<00:14, 326MB/s] pytorch_model-00004-of-00006.bin: 7%|▋ | 325M/4.93G [00:01<00:13, 337MB/s] pytorch_model-00004-of-00006.bin: 8%|▊ | 377M/4.93G [00:01<00:13, 335MB/s] pytorch_model-00004-of-00006.bin: 9%|▉ | 461M/4.93G [00:02<00:10, 435MB/s] pytorch_model-00004-of-00006.bin: 10%|█ | 514M/4.93G [00:02<00:11, 369MB/s] pytorch_model-00004-of-00006.bin: 12%|█▏ | 577M/4.93G [00:02<00:10, 401MB/s] pytorch_model-00004-of-00006.bin: 13%|█▎ | 629M/4.93G [00:02<00:10, 411MB/s] pytorch_model-00004-of-00006.bin: 14%|█▍ | 682M/4.93G [00:02<00:10, 424MB/s] pytorch_model-00004-of-00006.bin: 15%|█▍ | 734M/4.93G [00:02<00:10, 394MB/s] pytorch_model-00004-of-00006.bin: 18%|█▊ | 891M/4.93G [00:02<00:06, 646MB/s] pytorch_model-00004-of-00006.bin: 20%|█▉ | 965M/4.93G [00:03<00:06, 604MB/s] pytorch_model-00004-of-00006.bin: 21%|██ | 1.04G/4.93G [00:03<00:07, 545MB/s] pytorch_model-00004-of-00006.bin: 23%|██▎ | 1.14G/4.93G [00:03<00:05, 641MB/s] pytorch_model-00004-of-00006.bin: 30%|██▉ | 1.46G/4.93G [00:03<00:02, 1.24GB/s] pytorch_model-00004-of-00006.bin: 38%|███▊ | 1.88G/4.93G [00:03<00:01, 1.94GB/s] pytorch_model-00004-of-00006.bin: 43%|████▎ | 2.10G/4.93G [00:04<00:02, 959MB/s] pytorch_model-00004-of-00006.bin: 46%|████▌ | 2.26G/4.93G [00:04<00:03, 735MB/s] pytorch_model-00004-of-00006.bin: 49%|████▉ | 2.42G/4.93G [00:04<00:03, 834MB/s] pytorch_model-00004-of-00006.bin: 54%|█████▍ | 2.67G/4.93G [00:04<00:02, 944MB/s] pytorch_model-00004-of-00006.bin: 57%|█████▋ | 2.81G/4.93G [00:04<00:02, 892MB/s] pytorch_model-00004-of-00006.bin: 59%|█████▉ | 2.93G/4.93G [00:05<00:02, 757MB/s] pytorch_model-00004-of-00006.bin: 62%|██████▏ | 3.05G/4.93G [00:05<00:02, 834MB/s] pytorch_model-00004-of-00006.bin: 69%|██████▉ | 3.43G/4.93G [00:05<00:01, 1.38GB/s] pytorch_model-00004-of-00006.bin: 74%|███████▍ | 3.66G/4.93G [00:05<00:00, 1.57GB/s] pytorch_model-00004-of-00006.bin: 79%|███████▊ | 3.88G/4.93G [00:05<00:00, 1.66GB/s] pytorch_model-00004-of-00006.bin: 83%|████████▎ | 4.08G/4.93G [00:06<00:00, 927MB/s] pytorch_model-00004-of-00006.bin: 86%|████████▌ | 4.24G/4.93G [00:06<00:00, 887MB/s] pytorch_model-00004-of-00006.bin: 89%|████████▊ | 4.37G/4.93G [00:06<00:00, 953MB/s] pytorch_model-00004-of-00006.bin: 91%|█████████▏| 4.50G/4.93G [00:06<00:00, 927MB/s] pytorch_model-00004-of-00006.bin: 98%|█████████▊| 4.85G/4.93G [00:06<00:00, 1.42GB/s] pytorch_model-00004-of-00006.bin: 100%|█████████▉| 4.93G/4.93G [00:06<00:00, 741MB/s]
katydeng-katy-new-v1-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 [00:00<05:25, 15.1MB/s] pytorch_model-00005-of-00006.bin: 0%| | 21.0M/4.93G [00:01<04:26, 18.5MB/s] pytorch_model-00005-of-00006.bin: 1%| | 31.5M/4.93G [00:01<03:16, 25.0MB/s] pytorch_model-00005-of-00006.bin: 1%|▏ | 62.9M/4.93G [00:01<01:16, 63.3MB/s] pytorch_model-00005-of-00006.bin: 2%|▏ | 83.9M/4.93G [00:01<00:58, 82.6MB/s] pytorch_model-00005-of-00006.bin: 3%|▎ | 136M/4.93G [00:01<00:32, 147MB/s] pytorch_model-00005-of-00006.bin: 5%|▌ | 262M/4.93G [00:01<00:13, 349MB/s] pytorch_model-00005-of-00006.bin: 7%|▋ | 325M/4.93G [00:02<00:12, 384MB/s] pytorch_model-00005-of-00006.bin: 8%|▊ | 377M/4.93G [00:02<00:12, 363MB/s] pytorch_model-00005-of-00006.bin: 9%|▉ | 451M/4.93G [00:02<00:10, 426MB/s] pytorch_model-00005-of-00006.bin: 11%|█ | 545M/4.93G [00:02<00:08, 525MB/s] pytorch_model-00005-of-00006.bin: 13%|█▎ | 619M/4.93G [00:02<00:08, 512MB/s] pytorch_model-00005-of-00006.bin: 15%|█▍ | 734M/4.93G [00:02<00:06, 634MB/s] pytorch_model-00005-of-00006.bin: 16%|█▋ | 807M/4.93G [00:02<00:08, 476MB/s] pytorch_model-00005-of-00006.bin: 19%|█▊ | 923M/4.93G [00:03<00:06, 607MB/s] pytorch_model-00005-of-00006.bin: 23%|██▎ | 1.15G/4.93G [00:03<00:03, 977MB/s] pytorch_model-00005-of-00006.bin: 31%|███ | 1.53G/4.93G [00:03<00:02, 1.65GB/s] pytorch_model-00005-of-00006.bin: 37%|███▋ | 1.80G/4.93G [00:03<00:01, 1.89GB/s] pytorch_model-00005-of-00006.bin: 41%|████ | 2.02G/4.93G [00:04<00:05, 550MB/s] pytorch_model-00005-of-00006.bin: 44%|████▍ | 2.18G/4.93G [00:04<00:05, 519MB/s] pytorch_model-00005-of-00006.bin: 47%|████▋ | 2.31G/4.93G [00:04<00:04, 588MB/s] pytorch_model-00005-of-00006.bin: 49%|████▉ | 2.43G/4.93G [00:05<00:04, 617MB/s] pytorch_model-00005-of-00006.bin: 57%|█████▋ | 2.79G/4.93G [00:05<00:02, 1.02GB/s] pytorch_model-00005-of-00006.bin: 60%|██████ | 2.98G/4.93G [00:05<00:01, 1.14GB/s] pytorch_model-00005-of-00006.bin: 64%|██████▍ | 3.16G/4.93G [00:05<00:02, 730MB/s] pytorch_model-00005-of-00006.bin: 67%|██████▋ | 3.29G/4.93G [00:06<00:02, 726MB/s] pytorch_model-00005-of-00006.bin: 69%|██████▉ | 3.41G/4.93G [00:06<00:02, 686MB/s] pytorch_model-00005-of-00006.bin: 71%|███████ | 3.51G/4.93G [00:06<00:01, 720MB/s] pytorch_model-00005-of-00006.bin: 74%|███████▍ | 3.65G/4.93G [00:06<00:01, 826MB/s] pytorch_model-00005-of-00006.bin: 76%|███████▋ | 3.76G/4.93G [00:06<00:01, 828MB/s] pytorch_model-00005-of-00006.bin: 83%|████████▎ | 4.11G/4.93G [00:06<00:00, 1.34GB/s] pytorch_model-00005-of-00006.bin: 87%|████████▋ | 4.28G/4.93G [00:06<00:00, 989MB/s] pytorch_model-00005-of-00006.bin: 89%|████████▉ | 4.41G/4.93G [00:07<00:00, 945MB/s] pytorch_model-00005-of-00006.bin: 92%|█████████▏| 4.56G/4.93G [00:07<00:00, 1.03GB/s] pytorch_model-00005-of-00006.bin: 95%|█████████▌| 4.70G/4.93G [00:07<00:00, 1.12GB/s] pytorch_model-00005-of-00006.bin: 98%|█████████▊| 4.84G/4.93G [00:07<00:00, 1.12GB/s] pytorch_model-00005-of-00006.bin: 100%|█████████▉| 4.93G/4.93G [00:08<00:00, 599MB/s]
katydeng-katy-new-v1-mkmlizer: pytorch_model-00006-of-00006.bin: 0%| | 0.00/1.25G [00:00<?, ?B/s] pytorch_model-00006-of-00006.bin: 1%| | 10.5M/1.25G [00:01<02:28, 8.29MB/s] pytorch_model-00006-of-00006.bin: 3%|▎ | 31.5M/1.25G [00:01<00:42, 28.7MB/s] pytorch_model-00006-of-00006.bin: 13%|█▎ | 157M/1.25G [00:01<00:07, 144MB/s] pytorch_model-00006-of-00006.bin: 17%|█▋ | 210M/1.25G [00:01<00:05, 182MB/s] pytorch_model-00006-of-00006.bin: 21%|██ | 262M/1.25G [00:01<00:04, 220MB/s] pytorch_model-00006-of-00006.bin: 27%|██▋ | 333M/1.25G [00:02<00:03, 286MB/s] pytorch_model-00006-of-00006.bin: 30%|███ | 375M/1.25G [00:02<00:04, 181MB/s] pytorch_model-00006-of-00006.bin: 33%|███▎ | 406M/1.25G [00:02<00:05, 156MB/s] pytorch_model-00006-of-00006.bin: 39%|███▊ | 480M/1.25G [00:02<00:03, 230MB/s] pytorch_model-00006-of-00006.bin: 48%|████▊ | 595M/1.25G [00:03<00:01, 372MB/s] pytorch_model-00006-of-00006.bin: 53%|█████▎ | 658M/1.25G [00:03<00:01, 386MB/s] pytorch_model-00006-of-00006.bin: 64%|██████▍ | 794M/1.25G [00:03<00:00, 568MB/s] pytorch_model-00006-of-00006.bin: 100%|█████████▉| 1.25G/1.25G [00:03<00:00, 358MB/s]
katydeng-katy-new-v1-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, 24.9MB/s]
katydeng-katy-new-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/549 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 549/549 [00:00<00:00, 7.53MB/s]
katydeng-katy-new-v1-mkmlizer: tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 60.8MB/s]
katydeng-katy-new-v1-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, 15.5MB/s]
katydeng-katy-new-v1-mkmlizer: Downloaded to shared memory in 43.573s
katydeng-katy-new-v1-mkmlizer: quantizing model to /dev/shm/model_cache
katydeng-katy-new-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
katydeng-katy-new-v1-mkmlizer: Reading /tmp/tmpgg0hzi58/pytorch_model.bin.index.json
katydeng-katy-new-v1-mkmlizer: Profiling: 0%| | 0/363 [00:00<?, ?it/s] Profiling: 0%| | 1/363 [00:03<18:33, 3.08s/it] Profiling: 19%|█▉ | 69/363 [00:04<00:13, 22.06it/s] Profiling: 38%|███▊ | 139/363 [00:04<00:05, 38.40it/s] Profiling: 58%|█████▊ | 209/363 [00:05<00:03, 50.23it/s] Profiling: 77%|███████▋ | 278/363 [00:06<00:01, 59.14it/s] Profiling: 96%|█████████▌| 349/363 [00:06<00:00, 82.75it/s] Profiling: 100%|██████████| 363/363 [00:08<00:00, 48.29it/s] Profiling: 100%|██████████| 363/363 [00:08<00:00, 43.26it/s]
katydeng-katy-new-v1-mkmlizer: quantized model in 30.062s
katydeng-katy-new-v1-mkmlizer: Processed model katydeng/katy_new in 75.322s
katydeng-katy-new-v1-mkmlizer: creating bucket guanaco-mkml-models
katydeng-katy-new-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
katydeng-katy-new-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/katydeng-katy-new-v1
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/katydeng-katy-new-v1/config.json
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/katydeng-katy-new-v1/added_tokens.json
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/katydeng-katy-new-v1/tokenizer_config.json
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/katydeng-katy-new-v1/tokenizer.model
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/katydeng-katy-new-v1/special_tokens_map.json
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/katydeng-katy-new-v1/tokenizer.json
katydeng-katy-new-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/katydeng-katy-new-v1/mkml_model.tensors
katydeng-katy-new-v1-mkmlizer: loading reward model from ChaiML/reward_models_100_170000000_cp_498032
katydeng-katy-new-v1-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.
katydeng-katy-new-v1-mkmlizer: warnings.warn(
katydeng-katy-new-v1-mkmlizer: config.json: 0%| | 0.00/1.03k [00:00<?, ?B/s] config.json: 100%|██████████| 1.03k/1.03k [00:00<00:00, 10.5MB/s]
katydeng-katy-new-v1-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.
katydeng-katy-new-v1-mkmlizer: warnings.warn(
katydeng-katy-new-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.12MB/s]
katydeng-katy-new-v1-mkmlizer: vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s] vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 19.8MB/s]
katydeng-katy-new-v1-mkmlizer: merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s] merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 9.74MB/s]
katydeng-katy-new-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 44.3MB/s]
katydeng-katy-new-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/99.0 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 99.0/99.0 [00:00<00:00, 800kB/s]
katydeng-katy-new-v1-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.
katydeng-katy-new-v1-mkmlizer: warnings.warn(
katydeng-katy-new-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/510M [00:00<?, ?B/s] pytorch_model.bin: 3%|▎ | 17.6M/510M [00:00<00:04, 119MB/s] pytorch_model.bin: 16%|█▌ | 80.5M/510M [00:00<00:01, 352MB/s] pytorch_model.bin: 40%|████ | 206M/510M [00:00<00:00, 706MB/s] pytorch_model.bin: 94%|█████████▍| 479M/510M [00:00<00:00, 908MB/s] pytorch_model.bin: 100%|█████████▉| 510M/510M [00:01<00:00, 285MB/s]
katydeng-katy-new-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
katydeng-katy-new-v1-mkmlizer: Saving duration: 0.113s
katydeng-katy-new-v1-mkmlizer: Processed model ChaiML/reward_models_100_170000000_cp_498032 in 4.189s
katydeng-katy-new-v1-mkmlizer: creating bucket guanaco-reward-models
Job katydeng-katy-new-v1-mkmlizer completed after 106.25s with status: succeeded
Stopping job with name katydeng-katy-new-v1-mkmlizer
Pipeline stage MKMLizer completed in 112.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service katydeng-katy-new-v1
Waiting for inference service katydeng-katy-new-v1 to be ready
Inference service katydeng-katy-new-v1 ready after 50.39243841171265s
Pipeline stage ISVCDeployer completed in 58.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.801969289779663s
Received healthy response to inference request in 1.8713810443878174s
Received healthy response to inference request in 1.900587558746338s
Received healthy response to inference request in 1.8669185638427734s
Received healthy response to inference request in 1.8685271739959717s
5 requests
0 failed requests
5th percentile: 1.8672402858734132
10th percentile: 1.8675620079040527
20th percentile: 1.868205451965332
30th percentile: 1.8690979480743408
40th percentile: 1.870239496231079
50th percentile: 1.8713810443878174
60th percentile: 1.8830636501312257
70th percentile: 1.8947462558746337
80th percentile: 2.080863904953003
90th percentile: 2.441416597366333
95th percentile: 2.621692943572998
99th percentile: 2.76591402053833
mean time: 2.061876726150513
Pipeline stage StressChecker completed in 11.51s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
katydeng-katy-new_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics