submission_id: saishf-kuro-lotus-10-7b_v1
developer_uid: saishf
status: torndown
model_repo: saishf/Kuro-Lotus-10.7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, '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}:', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-03-26T12:28:23+00:00
model_name: saishf-kuro-lotus-10-7b_v1
model_eval_status: success
model_group: saishf/Kuro-Lotus-10.7B
num_battles: 67697
num_wins: 32333
celo_rating: 1141.86
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 10731524096.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: saishf-kuro-lotus-10-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: saishf/Kuro-Lotus-10.7B
model_size: 11B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-26
win_ratio: 0.47761348361079514
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-kuro-lotus-10-7b-v1-mkmlizer
Waiting for job on saishf-kuro-lotus-10-7b-v1-mkmlizer to finish
saishf-kuro-lotus-10-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ _____ __ __ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ /___/ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ Version: 0.6.11 ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ belonging to: ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ Chai Research Corp. ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-kuro-lotus-10-7b-v1-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.7MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: README.md: 0%| | 0.00/4.30k [00:00<?, ?B/s] README.md: 100%|██████████| 4.30k/4.30k [00:00<00:00, 29.6MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: config.json: 0%| | 0.00/704 [00:00<?, ?B/s] config.json: 100%|██████████| 704/704 [00:00<00:00, 9.17MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: mergekit_config.yml: 0%| | 0.00/384 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 384/384 [00:00<00:00, 6.19MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00001-of-00011.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00001-of-00011.safetensors: 1%| | 10.5M/1.89G [00:01<02:59, 10.5MB/s] model-00001-of-00011.safetensors: 1%| | 21.0M/1.89G [00:02<03:31, 8.85MB/s] model-00001-of-00011.safetensors: 2%|▏ | 31.5M/1.89G [00:02<02:02, 15.1MB/s] model-00001-of-00011.safetensors: 6%|▌ | 115M/1.89G [00:02<00:20, 85.4MB/s] model-00001-of-00011.safetensors: 11%|█ | 199M/1.89G [00:02<00:10, 167MB/s] model-00001-of-00011.safetensors: 16%|█▌ | 304M/1.89G [00:02<00:05, 285MB/s] model-00001-of-00011.safetensors: 24%|██▍ | 461M/1.89G [00:02<00:03, 431MB/s] model-00001-of-00011.safetensors: 29%|██▉ | 545M/1.89G [00:03<00:02, 488MB/s] model-00001-of-00011.safetensors: 62%|██████▏ | 1.16G/1.89G [00:03<00:00, 1.57GB/s] model-00001-of-00011.safetensors: 74%|███████▍ | 1.41G/1.89G [00:03<00:00, 772MB/s] model-00001-of-00011.safetensors: 84%|████████▍ | 1.60G/1.89G [00:03<00:00, 893MB/s] model-00001-of-00011.safetensors: 94%|█████████▍| 1.77G/1.89G [00:04<00:00, 938MB/s] model-00001-of-00011.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 457MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00002-of-00011.safetensors: 0%| | 0.00/1.99G [00:00<?, ?B/s] model-00002-of-00011.safetensors: 1%| | 10.5M/1.99G [00:02<07:55, 4.16MB/s] model-00002-of-00011.safetensors: 4%|▍ | 83.9M/1.99G [00:02<00:45, 41.7MB/s] model-00002-of-00011.safetensors: 6%|▋ | 126M/1.99G [00:02<00:31, 59.6MB/s] model-00002-of-00011.safetensors: 15%|█▌ | 304M/1.99G [00:03<00:08, 194MB/s] model-00002-of-00011.safetensors: 51%|█████ | 1.01G/1.99G [00:03<00:01, 883MB/s] model-00002-of-00011.safetensors: 66%|██████▌ | 1.31G/1.99G [00:03<00:00, 689MB/s] model-00002-of-00011.safetensors: 77%|███████▋ | 1.53G/1.99G [00:04<00:00, 687MB/s] model-00002-of-00011.safetensors: 88%|████████▊ | 1.75G/1.99G [00:04<00:00, 843MB/s] model-00002-of-00011.safetensors: 100%|█████████▉| 1.99G/1.99G [00:04<00:00, 456MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00003-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00011.safetensors: 1%| | 10.5M/1.98G [00:02<07:34, 4.34MB/s] model-00003-of-00011.safetensors: 6%|▋ | 126M/1.98G [00:02<00:27, 66.7MB/s] model-00003-of-00011.safetensors: 10%|▉ | 189M/1.98G [00:02<00:17, 104MB/s] model-00003-of-00011.safetensors: 12%|█▏ | 241M/1.98G [00:03<00:14, 117MB/s] model-00003-of-00011.safetensors: 26%|██▌ | 514M/1.98G [00:03<00:03, 368MB/s] model-00003-of-00011.safetensors: 55%|█████▍ | 1.08G/1.98G [00:03<00:00, 908MB/s] model-00003-of-00011.safetensors: 64%|██████▍ | 1.27G/1.98G [00:03<00:01, 701MB/s] model-00003-of-00011.safetensors: 75%|███████▌ | 1.49G/1.98G [00:03<00:00, 833MB/s] model-00003-of-00011.safetensors: 83%|████████▎ | 1.63G/1.98G [00:04<00:00, 525MB/s] model-00003-of-00011.safetensors: 88%|████████▊ | 1.75G/1.98G [00:04<00:00, 586MB/s] model-00003-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 417MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00004-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00011.safetensors: 1%| | 10.5M/1.95G [00:02<07:27, 4.32MB/s] model-00004-of-00011.safetensors: 10%|▉ | 189M/1.95G [00:02<00:17, 100MB/s] model-00004-of-00011.safetensors: 15%|█▌ | 294M/1.95G [00:02<00:09, 165MB/s] model-00004-of-00011.safetensors: 19%|█▉ | 377M/1.95G [00:02<00:07, 205MB/s] model-00004-of-00011.safetensors: 26%|██▌ | 503M/1.95G [00:03<00:04, 313MB/s] model-00004-of-00011.safetensors: 60%|█████▉ | 1.16G/1.95G [00:03<00:00, 1.10GB/s] model-00004-of-00011.safetensors: 72%|███████▏ | 1.41G/1.95G [00:03<00:00, 743MB/s] model-00004-of-00011.safetensors: 82%|████████▏ | 1.59G/1.95G [00:03<00:00, 857MB/s] model-00004-of-00011.safetensors: 91%|█████████ | 1.77G/1.95G [00:04<00:00, 703MB/s] model-00004-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 453MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00005-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00005-of-00011.safetensors: 1%| | 10.5M/1.98G [00:01<05:10, 6.35MB/s] model-00005-of-00011.safetensors: 3%|▎ | 62.9M/1.98G [00:01<00:41, 45.7MB/s] model-00005-of-00011.safetensors: 4%|▍ | 83.9M/1.98G [00:02<00:35, 53.7MB/s] model-00005-of-00011.safetensors: 5%|▌ | 105M/1.98G [00:02<00:28, 66.2MB/s] model-00005-of-00011.safetensors: 6%|▋ | 126M/1.98G [00:02<00:25, 72.1MB/s] model-00005-of-00011.safetensors: 10%|▉ | 189M/1.98G [00:02<00:13, 129MB/s] model-00005-of-00011.safetensors: 11%|█ | 210M/1.98G [00:03<00:19, 92.6MB/s] model-00005-of-00011.safetensors: 17%|█▋ | 346M/1.98G [00:03<00:06, 244MB/s] model-00005-of-00011.safetensors: 33%|███▎ | 650M/1.98G [00:03<00:02, 650MB/s] model-00005-of-00011.safetensors: 65%|██████▌ | 1.29G/1.98G [00:03<00:00, 1.63GB/s] model-00005-of-00011.safetensors: 79%|███████▉ | 1.57G/1.98G [00:04<00:00, 697MB/s] model-00005-of-00011.safetensors: 90%|████████▉ | 1.78G/1.98G [00:04<00:00, 715MB/s] model-00005-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 421MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00006-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00006-of-00011.safetensors: 1%| | 10.5M/1.95G [00:00<03:00, 10.7MB/s] model-00006-of-00011.safetensors: 1%| | 21.0M/1.95G [00:01<01:26, 22.3MB/s] model-00006-of-00011.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:24, 22.6MB/s] model-00006-of-00011.safetensors: 3%|▎ | 62.9M/1.95G [00:01<00:32, 58.5MB/s] model-00006-of-00011.safetensors: 10%|█ | 199M/1.95G [00:01<00:07, 247MB/s] model-00006-of-00011.safetensors: 13%|█▎ | 252M/1.95G [00:02<00:07, 233MB/s] model-00006-of-00011.safetensors: 15%|█▌ | 294M/1.95G [00:02<00:06, 239MB/s] model-00006-of-00011.safetensors: 17%|█▋ | 336M/1.95G [00:02<00:07, 211MB/s] model-00006-of-00011.safetensors: 22%|██▏ | 419M/1.95G [00:02<00:04, 310MB/s] model-00006-of-00011.safetensors: 37%|███▋ | 724M/1.95G [00:02<00:01, 814MB/s] model-00006-of-00011.safetensors: 65%|██████▌ | 1.27G/1.95G [00:02<00:00, 1.78GB/s] model-00006-of-00011.safetensors: 78%|███████▊ | 1.52G/1.95G [00:02<00:00, 1.81GB/s] model-00006-of-00011.safetensors: 90%|█████████ | 1.76G/1.95G [00:03<00:00, 1.59GB/s] model-00006-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 617MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00007-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00007-of-00011.safetensors: 1%| | 10.5M/1.98G [00:01<05:55, 5.54MB/s] model-00007-of-00011.safetensors: 1%| | 21.0M/1.98G [00:02<03:17, 9.92MB/s] model-00007-of-00011.safetensors: 2%|▏ | 41.9M/1.98G [00:02<01:27, 22.2MB/s] model-00007-of-00011.safetensors: 7%|▋ | 136M/1.98G [00:02<00:18, 101MB/s] model-00007-of-00011.safetensors: 20%|██ | 398M/1.98G [00:02<00:04, 362MB/s] model-00007-of-00011.safetensors: 25%|██▍ | 493M/1.98G [00:03<00:03, 379MB/s] model-00007-of-00011.safetensors: 58%|█████▊ | 1.14G/1.98G [00:03<00:00, 1.22GB/s] model-00007-of-00011.safetensors: 70%|███████ | 1.39G/1.98G [00:03<00:00, 694MB/s] model-00007-of-00011.safetensors: 80%|███████▉ | 1.58G/1.98G [00:04<00:00, 721MB/s] model-00007-of-00011.safetensors: 88%|████████▊ | 1.74G/1.98G [00:04<00:00, 686MB/s] model-00007-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 441MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00008-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00008-of-00011.safetensors: 1%| | 10.5M/1.95G [00:01<03:43, 8.67MB/s] model-00008-of-00011.safetensors: 1%| | 21.0M/1.95G [00:01<01:51, 17.2MB/s] model-00008-of-00011.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:13, 26.1MB/s] model-00008-of-00011.safetensors: 2%|▏ | 41.9M/1.95G [00:01<00:53, 35.5MB/s] model-00008-of-00011.safetensors: 3%|▎ | 62.9M/1.95G [00:01<00:31, 60.4MB/s] model-00008-of-00011.safetensors: 6%|▌ | 115M/1.95G [00:01<00:12, 141MB/s] model-00008-of-00011.safetensors: 12%|█▏ | 231M/1.95G [00:02<00:05, 327MB/s] model-00008-of-00011.safetensors: 17%|█▋ | 325M/1.95G [00:02<00:05, 271MB/s] model-00008-of-00011.safetensors: 20%|█▉ | 388M/1.95G [00:02<00:04, 325MB/s] model-00008-of-00011.safetensors: 26%|██▋ | 514M/1.95G [00:02<00:02, 488MB/s] model-00008-of-00011.safetensors: 39%|███▉ | 755M/1.95G [00:02<00:01, 875MB/s] model-00008-of-00011.safetensors: 72%|███████▏ | 1.41G/1.95G [00:02<00:00, 2.13GB/s] model-00008-of-00011.safetensors: 87%|████████▋ | 1.69G/1.95G [00:03<00:00, 1.43GB/s] model-00008-of-00011.safetensors: 98%|█████████▊| 1.91G/1.95G [00:03<00:00, 1.49GB/s] model-00008-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 570MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00009-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00009-of-00011.safetensors: 1%| | 10.5M/1.98G [00:02<07:36, 4.31MB/s] model-00009-of-00011.safetensors: 1%| | 21.0M/1.98G [00:02<03:21, 9.71MB/s] model-00009-of-00011.safetensors: 3%|▎ | 52.4M/1.98G [00:02<01:01, 31.5MB/s] model-00009-of-00011.safetensors: 7%|▋ | 147M/1.98G [00:02<00:15, 115MB/s] model-00009-of-00011.safetensors: 13%|█▎ | 252M/1.98G [00:02<00:08, 208MB/s] model-00009-of-00011.safetensors: 18%|█▊ | 357M/1.98G [00:03<00:05, 319MB/s] model-00009-of-00011.safetensors: 25%|██▍ | 493M/1.98G [00:03<00:03, 475MB/s] model-00009-of-00011.safetensors: 58%|█████▊ | 1.14G/1.98G [00:03<00:00, 1.19GB/s] model-00009-of-00011.safetensors: 65%|██████▍ | 1.28G/1.98G [00:03<00:00, 947MB/s] model-00009-of-00011.safetensors: 71%|███████▏ | 1.41G/1.98G [00:03<00:00, 990MB/s] model-00009-of-00011.safetensors: 84%|████████▎ | 1.65G/1.98G [00:04<00:00, 1.06GB/s] model-00009-of-00011.safetensors: 89%|████████▉ | 1.77G/1.98G [00:04<00:00, 969MB/s] model-00009-of-00011.safetensors: 99%|█████████▉| 1.97G/1.98G [00:04<00:00, 1.16GB/s] model-00009-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 457MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model-00011-of-00011.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00011-of-00011.safetensors: 1%| | 10.5M/1.89G [00:02<07:21, 4.26MB/s] model-00011-of-00011.safetensors: 8%|▊ | 147M/1.89G [00:02<00:22, 77.8MB/s] model-00011-of-00011.safetensors: 12%|█▏ | 220M/1.89G [00:02<00:13, 124MB/s] model-00011-of-00011.safetensors: 22%|██▏ | 419M/1.89G [00:02<00:05, 293MB/s] model-00011-of-00011.safetensors: 28%|██▊ | 535M/1.89G [00:02<00:03, 363MB/s] model-00011-of-00011.safetensors: 62%|██████▏ | 1.17G/1.89G [00:03<00:00, 1.16GB/s] model-00011-of-00011.safetensors: 77%|███████▋ | 1.46G/1.89G [00:03<00:00, 936MB/s] model-00011-of-00011.safetensors: 88%|████████▊ | 1.67G/1.89G [00:03<00:00, 998MB/s] model-00011-of-00011.safetensors: 98%|█████████▊| 1.86G/1.89G [00:03<00:00, 991MB/s] model-00011-of-00011.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 482MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: model.safetensors.index.json: 0%| | 0.00/34.1k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 34.1k/34.1k [00:00<00:00, 177MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: special_tokens_map.json: 0%| | 0.00/551 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 551/551 [00:00<00:00, 5.64MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 10.2MB/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 10.1MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 19.1MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/984 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 984/984 [00:00<00:00, 8.88MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: Downloaded to shared memory in 48.445s
saishf-kuro-lotus-10-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-kuro-lotus-10-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
saishf-kuro-lotus-10-7b-v1-mkmlizer: Reading /tmp/tmpk5lfzmp2/model.safetensors.index.json
saishf-kuro-lotus-10-7b-v1-mkmlizer: Profiling: 0%| | 0/435 [00:00<?, ?it/s] Profiling: 0%| | 1/435 [00:01<09:26, 1.31s/it] Profiling: 3%|▎ | 13/435 [00:01<00:34, 12.36it/s] Profiling: 6%|▋ | 28/435 [00:01<00:14, 28.88it/s] Profiling: 9%|▊ | 38/435 [00:01<00:10, 37.24it/s] Profiling: 11%|█▏ | 49/435 [00:01<00:07, 48.44it/s] Profiling: 14%|█▍ | 62/435 [00:01<00:05, 63.62it/s] Profiling: 17%|█▋ | 76/435 [00:01<00:04, 77.05it/s] Profiling: 20%|██ | 87/435 [00:02<00:04, 71.95it/s] Profiling: 23%|██▎ | 99/435 [00:02<00:04, 80.15it/s] Profiling: 25%|██▌ | 110/435 [00:02<00:03, 84.70it/s] Profiling: 28%|██▊ | 120/435 [00:02<00:03, 82.01it/s] Profiling: 30%|███ | 131/435 [00:02<00:03, 86.38it/s] Profiling: 34%|███▍ | 147/435 [00:02<00:02, 102.93it/s] Profiling: 37%|███▋ | 159/435 [00:02<00:03, 88.90it/s] Profiling: 40%|███▉ | 173/435 [00:03<00:02, 100.25it/s] Profiling: 43%|████▎ | 186/435 [00:03<00:02, 105.59it/s] Profiling: 46%|████▌ | 198/435 [00:03<00:02, 87.81it/s] Profiling: 49%|████▊ | 211/435 [00:03<00:02, 94.30it/s] Profiling: 52%|█████▏ | 225/435 [00:03<00:02, 103.94it/s] Profiling: 55%|█████▌ | 240/435 [00:03<00:02, 87.12it/s] Profiling: 58%|█████▊ | 254/435 [00:03<00:01, 97.46it/s] Profiling: 61%|██████▏ | 267/435 [00:03<00:01, 103.82it/s] Profiling: 64%|██████▍ | 279/435 [00:04<00:01, 84.36it/s] Profiling: 67%|██████▋ | 293/435 [00:04<00:01, 93.12it/s] Profiling: 71%|███████▏ | 310/435 [00:04<00:01, 107.82it/s] Profiling: 74%|███████▍ | 322/435 [00:04<00:01, 89.29it/s] Profiling: 78%|███████▊ | 339/435 [00:04<00:00, 103.63it/s] Profiling: 82%|████████▏ | 356/435 [00:04<00:00, 115.90it/s] Profiling: 85%|████████▍ | 369/435 [00:05<00:00, 91.62it/s] Profiling: 88%|████████▊ | 383/435 [00:05<00:00, 98.76it/s] Profiling: 92%|█████████▏| 399/435 [00:06<00:01, 27.50it/s] Profiling: 95%|█████████▍| 413/435 [00:06<00:00, 35.73it/s] Profiling: 98%|█████████▊| 428/435 [00:06<00:00, 46.24it/s] Profiling: 100%|██████████| 435/435 [00:07<00:00, 61.87it/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: quantized model in 23.327s
saishf-kuro-lotus-10-7b-v1-mkmlizer: Processed model saishf/Kuro-Lotus-10.7B in 73.292s
saishf-kuro-lotus-10-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
saishf-kuro-lotus-10-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-kuro-lotus-10-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/special_tokens_map.json
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/config.json
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/tokenizer_config.json
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/tokenizer.model
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/tokenizer.json
saishf-kuro-lotus-10-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v1/mkml_model.tensors
saishf-kuro-lotus-10-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-kuro-lotus-10-7b-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.
saishf-kuro-lotus-10-7b-v1-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v1-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.6MB/s]
saishf-kuro-lotus-10-7b-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.
saishf-kuro-lotus-10-7b-v1-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v1-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.20MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.3MB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 3.21MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 3.20MB/s]
saishf-kuro-lotus-10-7b-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.
saishf-kuro-lotus-10-7b-v1-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v1-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:06, 205MB/s] pytorch_model.bin: 4%|▎ | 52.4M/1.44G [00:00<00:07, 185MB/s] pytorch_model.bin: 8%|▊ | 115M/1.44G [00:00<00:03, 346MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:03, 394MB/s] pytorch_model.bin: 20%|██ | 294M/1.44G [00:00<00:01, 620MB/s] pytorch_model.bin: 30%|██▉ | 430M/1.44G [00:00<00:01, 830MB/s] pytorch_model.bin: 39%|███▉ | 566M/1.44G [00:00<00:00, 976MB/s] pytorch_model.bin: 46%|████▋ | 671M/1.44G [00:00<00:00, 960MB/s] pytorch_model.bin: 56%|█████▌ | 805M/1.44G [00:01<00:00, 971MB/s] pytorch_model.bin: 76%|███████▌ | 1.10G/1.44G [00:01<00:00, 1.49GB/s] pytorch_model.bin: 99%|█████████▊| 1.42G/1.44G [00:01<00:00, 1.89GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.02GB/s]
saishf-kuro-lotus-10-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-kuro-lotus-10-7b-v1-mkmlizer: Saving duration: 0.259s
saishf-kuro-lotus-10-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.531s
saishf-kuro-lotus-10-7b-v1-mkmlizer: creating bucket guanaco-reward-models
Job saishf-kuro-lotus-10-7b-v1-mkmlizer completed after 158.35s with status: succeeded
Stopping job with name saishf-kuro-lotus-10-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 163.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.21s
Running pipeline stage ISVCDeployer
Creating inference service saishf-kuro-lotus-10-7b-v1
Waiting for inference service saishf-kuro-lotus-10-7b-v1 to be ready
Inference service saishf-kuro-lotus-10-7b-v1 ready after 50.275513648986816s
Pipeline stage ISVCDeployer completed in 58.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5211381912231445s
Received healthy response to inference request in 1.6620054244995117s
Received healthy response to inference request in 1.2658874988555908s
Received healthy response to inference request in 1.2014553546905518s
Received healthy response to inference request in 0.7993640899658203s
5 requests
0 failed requests
5th percentile: 0.8797823429107666
10th percentile: 0.9602005958557129
20th percentile: 1.1210371017456056
30th percentile: 1.2143417835235595
40th percentile: 1.2401146411895752
50th percentile: 1.2658874988555908
60th percentile: 1.3679877758026122
70th percentile: 1.4700880527496338
80th percentile: 1.549311637878418
90th percentile: 1.6056585311889648
95th percentile: 1.6338319778442383
99th percentile: 1.6563707351684571
mean time: 1.2899701118469238
Pipeline stage StressChecker completed in 7.95s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.10s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.09s
Running M-Eval for topic stay_in_character
saishf-kuro-lotus-10-7b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
saishf-kuro-lotus-10-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of saishf-kuro-lotus-10-7b_v1
Running pipeline stage ISVCDeleter
Checking if service saishf-kuro-lotus-10-7b-v1 is running
Tearing down inference service saishf-kuro-lotus-10-7b-v1
Toredown service saishf-kuro-lotus-10-7b-v1
Pipeline stage ISVCDeleter completed in 3.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key saishf-kuro-lotus-10-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key saishf-kuro-lotus-10-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key saishf-kuro-lotus-10-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key saishf-kuro-lotus-10-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key saishf-kuro-lotus-10-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key saishf-kuro-lotus-10-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key saishf-kuro-lotus-10-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key saishf-kuro-lotus-10-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.46s
saishf-kuro-lotus-10-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics