submission_id: saishf-kuno-lake-7b_v2
developer_uid: chai_backend_admin
status: inactive
model_repo: saishf/Kuno-Lake-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-04-02T16:31:37+00:00
model_name: auto_submit_ricum_rohegekuco
model_eval_status: success
safety_score: 0.99
entertaining: 6.8
stay_in_character: 8.42
user_preference: 7.36
double_thumbs_up: 250
thumbs_up: 394
thumbs_down: 240
num_battles: 24176
num_wins: 10533
win_ratio: 0.43568001323626737
celo_rating: 1108.72
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-kuno-lake-7b-v2-mkmlizer
Waiting for job on saishf-kuno-lake-7b-v2-mkmlizer to finish
saishf-kuno-lake-7b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-kuno-lake-7b-v2-mkmlizer: ║ _____ __ __ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ /___/ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ Version: 0.6.11 ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ belonging to: ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ Chai Research Corp. ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-kuno-lake-7b-v2-mkmlizer: ║ ║
saishf-kuno-lake-7b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-kuno-lake-7b-v2-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 11.7MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: README.md: 0%| | 0.00/4.48k [00:00<?, ?B/s] README.md: 100%|██████████| 4.48k/4.48k [00:00<00:00, 41.0MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: config.json: 0%| | 0.00/642 [00:00<?, ?B/s] config.json: 100%|██████████| 642/642 [00:00<00:00, 8.63MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: mergekit_config.yml: 0%| | 0.00/387 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 387/387 [00:00<00:00, 3.38MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<04:08, 7.80MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.95G [00:01<02:39, 12.1MB/s] model-00001-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:01<00:49, 38.4MB/s] model-00001-of-00008.safetensors: 4%|▍ | 73.4M/1.95G [00:02<00:36, 50.8MB/s] model-00001-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:02<00:33, 55.3MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:02<00:25, 71.8MB/s] model-00001-of-00008.safetensors: 7%|▋ | 136M/1.95G [00:02<00:20, 88.7MB/s] model-00001-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:02<00:17, 104MB/s] model-00001-of-00008.safetensors: 9%|▉ | 178M/1.95G [00:03<00:16, 108MB/s] model-00001-of-00008.safetensors: 10%|█ | 199M/1.95G [00:03<00:14, 119MB/s] model-00001-of-00008.safetensors: 12%|█▏ | 241M/1.95G [00:03<00:09, 172MB/s] model-00001-of-00008.safetensors: 17%|█▋ | 336M/1.95G [00:03<00:04, 339MB/s] model-00001-of-00008.safetensors: 25%|██▌ | 493M/1.95G [00:03<00:02, 591MB/s] model-00001-of-00008.safetensors: 30%|███ | 587M/1.95G [00:03<00:02, 639MB/s] model-00001-of-00008.safetensors: 36%|███▌ | 703M/1.95G [00:03<00:01, 761MB/s] model-00001-of-00008.safetensors: 61%|██████▏ | 1.20G/1.95G [00:04<00:00, 1.37GB/s] model-00001-of-00008.safetensors: 68%|██████▊ | 1.33G/1.95G [00:04<00:00, 745MB/s] model-00001-of-00008.safetensors: 73%|███████▎ | 1.42G/1.95G [00:04<00:01, 509MB/s] model-00001-of-00008.safetensors: 77%|███████▋ | 1.50G/1.95G [00:05<00:00, 491MB/s] model-00001-of-00008.safetensors: 81%|████████ | 1.58G/1.95G [00:05<00:00, 530MB/s] model-00001-of-00008.safetensors: 85%|████████▍ | 1.65G/1.95G [00:05<00:00, 558MB/s] model-00001-of-00008.safetensors: 91%|█████████▏| 1.78G/1.95G [00:05<00:00, 671MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:05<00:00, 352MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<05:10, 6.23MB/s] model-00002-of-00008.safetensors: 1%| | 21.0M/1.95G [00:02<02:49, 11.4MB/s] model-00002-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:02<02:12, 14.4MB/s] model-00002-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:02<01:03, 29.8MB/s] model-00002-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:02<00:51, 36.6MB/s] model-00002-of-00008.safetensors: 4%|▍ | 73.4M/1.95G [00:02<00:45, 41.6MB/s] model-00002-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:03<00:19, 93.8MB/s] model-00002-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:03<00:09, 192MB/s] model-00002-of-00008.safetensors: 19%|█▉ | 367M/1.95G [00:03<00:03, 481MB/s] model-00002-of-00008.safetensors: 23%|██▎ | 440M/1.95G [00:03<00:03, 448MB/s] model-00002-of-00008.safetensors: 34%|███▍ | 661M/1.95G [00:03<00:01, 797MB/s] model-00002-of-00008.safetensors: 54%|█████▍ | 1.06G/1.95G [00:03<00:00, 994MB/s] model-00002-of-00008.safetensors: 60%|██████ | 1.17G/1.95G [00:04<00:01, 667MB/s] model-00002-of-00008.safetensors: 65%|██████▌ | 1.27G/1.95G [00:04<00:01, 507MB/s] model-00002-of-00008.safetensors: 69%|██████▉ | 1.34G/1.95G [00:04<00:01, 480MB/s] model-00002-of-00008.safetensors: 73%|███████▎ | 1.41G/1.95G [00:05<00:01, 428MB/s] model-00002-of-00008.safetensors: 76%|███████▋ | 1.48G/1.95G [00:05<00:01, 460MB/s] model-00002-of-00008.safetensors: 80%|████████ | 1.56G/1.95G [00:05<00:00, 492MB/s] model-00002-of-00008.safetensors: 85%|████████▌ | 1.66G/1.95G [00:05<00:00, 586MB/s] model-00002-of-00008.safetensors: 91%|█████████▏| 1.78G/1.95G [00:05<00:00, 702MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:05<00:00, 342MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<01:01, 30.3MB/s] model-00003-of-00008.safetensors: 2%|▏ | 31.5M/1.89G [00:00<00:44, 41.4MB/s] model-00003-of-00008.safetensors: 2%|▏ | 41.9M/1.89G [00:01<01:35, 19.4MB/s] model-00003-of-00008.safetensors: 3%|▎ | 52.4M/1.89G [00:02<01:52, 16.3MB/s] model-00003-of-00008.safetensors: 4%|▍ | 83.9M/1.89G [00:02<00:49, 36.4MB/s] model-00003-of-00008.safetensors: 7%|▋ | 136M/1.89G [00:02<00:22, 78.7MB/s] model-00003-of-00008.safetensors: 14%|█▍ | 262M/1.89G [00:03<00:07, 205MB/s] model-00003-of-00008.safetensors: 24%|██▍ | 461M/1.89G [00:03<00:03, 439MB/s] model-00003-of-00008.safetensors: 31%|███ | 577M/1.89G [00:03<00:02, 541MB/s] model-00003-of-00008.safetensors: 41%|████ | 776M/1.89G [00:03<00:01, 796MB/s] model-00003-of-00008.safetensors: 58%|█████▊ | 1.10G/1.89G [00:03<00:00, 1.24GB/s] model-00003-of-00008.safetensors: 67%|██████▋ | 1.27G/1.89G [00:04<00:01, 410MB/s] model-00003-of-00008.safetensors: 74%|███████▍ | 1.40G/1.89G [00:05<00:01, 384MB/s] model-00003-of-00008.safetensors: 79%|███████▉ | 1.49G/1.89G [00:05<00:00, 399MB/s] model-00003-of-00008.safetensors: 88%|████████▊ | 1.66G/1.89G [00:05<00:00, 531MB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:05<00:00, 342MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.95G [00:01<05:04, 6.36MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.95G [00:02<03:42, 8.64MB/s] model-00004-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:02<01:38, 19.4MB/s] model-00004-of-00008.safetensors: 4%|▍ | 73.4M/1.95G [00:02<00:44, 41.9MB/s] model-00004-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:03<00:27, 67.7MB/s] model-00004-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:03<00:10, 161MB/s] model-00004-of-00008.safetensors: 17%|█▋ | 325M/1.95G [00:03<00:04, 332MB/s] model-00004-of-00008.safetensors: 22%|██▏ | 419M/1.95G [00:03<00:03, 436MB/s] model-00004-of-00008.safetensors: 32%|███▏ | 619M/1.95G [00:03<00:01, 741MB/s] model-00004-of-00008.safetensors: 54%|█████▍ | 1.06G/1.95G [00:03<00:00, 914MB/s] model-00004-of-00008.safetensors: 60%|██████ | 1.17G/1.95G [00:04<00:01, 454MB/s] model-00004-of-00008.safetensors: 65%|██████▍ | 1.26G/1.95G [00:05<00:01, 357MB/s] model-00004-of-00008.safetensors: 68%|██████▊ | 1.33G/1.95G [00:05<00:01, 358MB/s] model-00004-of-00008.safetensors: 71%|███████▏ | 1.39G/1.95G [00:05<00:01, 355MB/s] model-00004-of-00008.safetensors: 75%|███████▍ | 1.45G/1.95G [00:05<00:01, 373MB/s] model-00004-of-00008.safetensors: 80%|███████▉ | 1.55G/1.95G [00:05<00:00, 444MB/s] model-00004-of-00008.safetensors: 83%|████████▎ | 1.61G/1.95G [00:05<00:00, 439MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:06<00:00, 320MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.98G [00:01<03:21, 9.75MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.98G [00:02<03:59, 8.18MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:02<02:23, 13.6MB/s] model-00005-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:02<01:14, 25.9MB/s] model-00005-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:03<00:48, 39.1MB/s] model-00005-of-00008.safetensors: 9%|▉ | 178M/1.98G [00:03<00:12, 146MB/s] model-00005-of-00008.safetensors: 16%|█▋ | 325M/1.98G [00:03<00:05, 299MB/s] model-00005-of-00008.safetensors: 20%|█▉ | 388M/1.98G [00:03<00:04, 334MB/s] model-00005-of-00008.safetensors: 33%|███▎ | 661M/1.98G [00:03<00:01, 740MB/s] model-00005-of-00008.safetensors: 56%|█████▌ | 1.10G/1.98G [00:03<00:00, 1.35GB/s] model-00005-of-00008.safetensors: 65%|██████▌ | 1.29G/1.98G [00:04<00:01, 507MB/s] model-00005-of-00008.safetensors: 72%|███████▏ | 1.42G/1.98G [00:05<00:01, 448MB/s] model-00005-of-00008.safetensors: 77%|███████▋ | 1.53G/1.98G [00:05<00:01, 420MB/s] model-00005-of-00008.safetensors: 83%|████████▎ | 1.63G/1.98G [00:05<00:00, 478MB/s] model-00005-of-00008.safetensors: 87%|████████▋ | 1.73G/1.98G [00:05<00:00, 533MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 342MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<02:40, 12.2MB/s] model-00007-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<02:03, 15.8MB/s] model-00007-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:19, 24.6MB/s] model-00007-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:01<00:30, 62.1MB/s] model-00007-of-00008.safetensors: 5%|▍ | 94.4M/1.98G [00:01<00:24, 75.8MB/s] model-00007-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:02<00:19, 93.6MB/s] model-00007-of-00008.safetensors: 7%|▋ | 136M/1.98G [00:02<00:17, 106MB/s] model-00007-of-00008.safetensors: 8%|▊ | 168M/1.98G [00:02<00:14, 127MB/s] model-00007-of-00008.safetensors: 10%|█ | 199M/1.98G [00:02<00:11, 155MB/s] model-00007-of-00008.safetensors: 13%|█▎ | 262M/1.98G [00:02<00:06, 248MB/s] model-00007-of-00008.safetensors: 16%|█▋ | 325M/1.98G [00:02<00:05, 310MB/s] model-00007-of-00008.safetensors: 21%|██ | 419M/1.98G [00:02<00:03, 442MB/s] model-00007-of-00008.safetensors: 29%|██▉ | 577M/1.98G [00:02<00:01, 712MB/s] model-00007-of-00008.safetensors: 38%|███▊ | 744M/1.98G [00:03<00:01, 958MB/s] model-00007-of-00008.safetensors: 43%|████▎ | 860M/1.98G [00:03<00:01, 816MB/s] model-00007-of-00008.safetensors: 66%|██████▌ | 1.31G/1.98G [00:03<00:00, 1.49GB/s] model-00007-of-00008.safetensors: 74%|███████▍ | 1.47G/1.98G [00:03<00:00, 709MB/s] model-00007-of-00008.safetensors: 80%|███████▉ | 1.58G/1.98G [00:04<00:00, 677MB/s] model-00007-of-00008.safetensors: 85%|████████▌ | 1.69G/1.98G [00:04<00:00, 663MB/s] model-00007-of-00008.safetensors: 94%|█████████▍| 1.86G/1.98G [00:04<00:00, 830MB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 433MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/906M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/906M [00:00<01:16, 11.7MB/s] model-00008-of-00008.safetensors: 4%|▍ | 35.7M/906M [00:01<00:23, 36.8MB/s] model-00008-of-00008.safetensors: 9%|▊ | 77.6M/906M [00:01<00:09, 87.0MB/s] model-00008-of-00008.safetensors: 11%|█ | 98.6M/906M [00:01<00:11, 70.8MB/s] model-00008-of-00008.safetensors: 13%|█▎ | 120M/906M [00:01<00:10, 76.7MB/s] model-00008-of-00008.safetensors: 16%|█▌ | 141M/906M [00:02<00:09, 80.3MB/s] model-00008-of-00008.safetensors: 19%|█▉ | 172M/906M [00:02<00:06, 112MB/s] model-00008-of-00008.safetensors: 27%|██▋ | 245M/906M [00:02<00:03, 216MB/s] model-00008-of-00008.safetensors: 44%|████▍ | 403M/906M [00:02<00:01, 477MB/s] model-00008-of-00008.safetensors: 56%|█████▌ | 508M/906M [00:02<00:00, 592MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 906M/906M [00:02<00:00, 333MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: model.safetensors.index.json: 0%| | 0.00/22.8k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 83.6MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.35MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 74.9MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 57.6MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 7.83MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: Downloaded to shared memory in 47.329s
saishf-kuno-lake-7b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-kuno-lake-7b-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
saishf-kuno-lake-7b-v2-mkmlizer: Reading /tmp/tmpylew201t/model.safetensors.index.json
saishf-kuno-lake-7b-v2-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:34, 8.46it/s] Profiling: 4%|▍ | 11/291 [00:00<00:04, 58.07it/s] Profiling: 7%|▋ | 21/291 [00:00<00:03, 76.00it/s] Profiling: 11%|█▏ | 33/291 [00:00<00:02, 86.97it/s] Profiling: 14%|█▍ | 42/291 [00:00<00:03, 71.59it/s] Profiling: 18%|█▊ | 52/291 [00:00<00:03, 79.44it/s] Profiling: 22%|██▏ | 63/291 [00:00<00:02, 87.72it/s] Profiling: 25%|██▌ | 74/291 [00:00<00:02, 92.06it/s] Profiling: 29%|██▉ | 84/291 [00:02<00:10, 19.49it/s] Profiling: 33%|███▎ | 95/291 [00:02<00:07, 26.50it/s] Profiling: 35%|███▌ | 103/291 [00:02<00:05, 31.60it/s] Profiling: 41%|████ | 118/291 [00:02<00:04, 41.82it/s] Profiling: 44%|████▍ | 129/291 [00:02<00:03, 50.87it/s] Profiling: 49%|████▉ | 142/291 [00:02<00:02, 63.12it/s] Profiling: 52%|█████▏ | 152/291 [00:03<00:02, 67.89it/s] Profiling: 56%|█████▌ | 162/291 [00:03<00:02, 60.89it/s] Profiling: 60%|█████▉ | 174/291 [00:03<00:01, 72.12it/s] Profiling: 64%|██████▍ | 187/291 [00:03<00:01, 81.78it/s] Profiling: 68%|██████▊ | 197/291 [00:03<00:01, 85.15it/s] Profiling: 71%|███████ | 207/291 [00:05<00:04, 19.39it/s] Profiling: 76%|███████▌ | 220/291 [00:05<00:02, 27.19it/s] Profiling: 79%|███████▉ | 231/291 [00:05<00:01, 34.43it/s] Profiling: 82%|████████▏ | 240/291 [00:05<00:01, 38.60it/s] Profiling: 88%|████████▊ | 255/291 [00:05<00:00, 52.51it/s] Profiling: 91%|█████████▏| 266/291 [00:05<00:00, 60.47it/s] Profiling: 95%|█████████▍| 276/291 [00:05<00:00, 60.40it/s] Profiling: 98%|█████████▊| 285/291 [00:06<00:00, 61.69it/s] Profiling: 100%|██████████| 291/291 [00:06<00:00, 47.38it/s]
saishf-kuno-lake-7b-v2-mkmlizer: quantized model in 17.003s
saishf-kuno-lake-7b-v2-mkmlizer: Processed model saishf/Kuno-Lake-7B in 65.257s
saishf-kuno-lake-7b-v2-mkmlizer: creating bucket guanaco-mkml-models
saishf-kuno-lake-7b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-kuno-lake-7b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2
saishf-kuno-lake-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2/tokenizer_config.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2/config.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2/tokenizer.model
saishf-kuno-lake-7b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2/special_tokens_map.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-kuno-lake-7b-v2/tokenizer.json
saishf-kuno-lake-7b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-kuno-lake-7b-v2-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.
saishf-kuno-lake-7b-v2-mkmlizer: warnings.warn(
saishf-kuno-lake-7b-v2-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 10.4MB/s]
saishf-kuno-lake-7b-v2-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.
saishf-kuno-lake-7b-v2-mkmlizer: warnings.warn(
saishf-kuno-lake-7b-v2-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.52MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 37.3MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 67.3MB/s]
saishf-kuno-lake-7b-v2-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.
saishf-kuno-lake-7b-v2-mkmlizer: warnings.warn(
saishf-kuno-lake-7b-v2-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:13, 103MB/s] pytorch_model.bin: 5%|▌ | 73.4M/1.44G [00:00<00:04, 287MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:02, 440MB/s] pytorch_model.bin: 15%|█▌ | 220M/1.44G [00:00<00:02, 408MB/s] pytorch_model.bin: 20%|██ | 294M/1.44G [00:00<00:02, 480MB/s] pytorch_model.bin: 27%|██▋ | 388M/1.44G [00:00<00:02, 512MB/s] pytorch_model.bin: 32%|███▏ | 469M/1.44G [00:00<00:01, 586MB/s] pytorch_model.bin: 40%|████ | 585M/1.44G [00:01<00:01, 694MB/s] pytorch_model.bin: 51%|█████▏ | 742M/1.44G [00:01<00:00, 891MB/s] pytorch_model.bin: 64%|██████▎ | 920M/1.44G [00:01<00:00, 1.12GB/s] pytorch_model.bin: 75%|███████▍ | 1.08G/1.44G [00:01<00:00, 1.22GB/s] pytorch_model.bin: 85%|████████▌ | 1.23G/1.44G [00:01<00:00, 1.30GB/s] pytorch_model.bin: 95%|█████████▍| 1.37G/1.44G [00:01<00:00, 1.22GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 482MB/s]
saishf-kuno-lake-7b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-kuno-lake-7b-v2-mkmlizer: Saving duration: 0.264s
saishf-kuno-lake-7b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.729s
saishf-kuno-lake-7b-v2-mkmlizer: creating bucket guanaco-reward-models
saishf-kuno-lake-7b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-kuno-lake-7b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/config.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/special_tokens_map.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/tokenizer_config.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/merges.txt
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/vocab.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/tokenizer.json
saishf-kuno-lake-7b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-kuno-lake-7b-v2_reward/reward.tensors
Job saishf-kuno-lake-7b-v2-mkmlizer completed after 95.86s with status: succeeded
Stopping job with name saishf-kuno-lake-7b-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service saishf-kuno-lake-7b-v2
Waiting for inference service saishf-kuno-lake-7b-v2 to be ready
Inference service saishf-kuno-lake-7b-v2 ready after 60.38724970817566s
Pipeline stage ISVCDeployer completed in 66.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3110029697418213s
Received healthy response to inference request in 0.5467023849487305s
Received healthy response to inference request in 0.5870575904846191s
Received healthy response to inference request in 0.8802318572998047s
Received healthy response to inference request in 0.7501189708709717s
5 requests
0 failed requests
5th percentile: 0.5547734260559082
10th percentile: 0.5628444671630859
20th percentile: 0.5789865493774414
30th percentile: 0.6196698665618896
40th percentile: 0.6848944187164306
50th percentile: 0.7501189708709717
60th percentile: 0.8021641254425049
70th percentile: 0.8542092800140381
80th percentile: 0.9663860797882081
90th percentile: 1.1386945247650146
95th percentile: 1.224848747253418
99th percentile: 1.2937721252441405
mean time: 0.8150227546691895
Pipeline stage StressChecker completed in 5.03s
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
saishf-kuno-lake-7b_v2 status is now deployed due to DeploymentManager action
saishf-kuno-lake-7b_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics