submission_id: saishf-fimbulvetr-kuro-l_8724_v3
developer_uid: saishf
status: inactive
model_repo: saishf/Fimbulvetr-Kuro-Lotus-10.7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, '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: 2024-03-26T12:48:40+00:00
model_name: saishf-fimbulvetr-kuro-l_8724_v3
model_eval_status: success
safety_score: 0.82
entertaining: 6.9
stay_in_character: 8.71
user_preference: 7.26
double_thumbs_up: 316
thumbs_up: 535
thumbs_down: 259
num_battles: 67771
num_wins: 33420
win_ratio: 0.4931312803411489
celo_rating: 1152.59
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer
Waiting for job on saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer to finish
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ _____ __ __ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ /___/ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ Version: 0.6.11 ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ belonging to: ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ Chai Research Corp. ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ║ ║
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.3MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: README.md: 0%| | 0.00/5.03k [00:00<?, ?B/s] README.md: 100%|██████████| 5.03k/5.03k [00:00<00:00, 31.1MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: config.json: 0%| | 0.00/707 [00:00<?, ?B/s] config.json: 100%|██████████| 707/707 [00:00<00:00, 6.30MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: mergekit_config.yml: 0%| | 0.00/382 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 382/382 [00:00<00:00, 3.99MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00001-of-00011.safetensors: 0%| | 0.00/1.90G [00:00<?, ?B/s] model-00001-of-00011.safetensors: 1%| | 10.5M/1.90G [00:02<06:05, 5.17MB/s] model-00001-of-00011.safetensors: 1%| | 21.0M/1.90G [00:02<02:51, 10.9MB/s] model-00001-of-00011.safetensors: 2%|▏ | 41.9M/1.90G [00:02<01:15, 24.6MB/s] model-00001-of-00011.safetensors: 3%|▎ | 62.9M/1.90G [00:02<00:47, 38.4MB/s] model-00001-of-00011.safetensors: 11%|█ | 210M/1.90G [00:02<00:09, 171MB/s] model-00001-of-00011.safetensors: 14%|█▍ | 262M/1.90G [00:03<00:07, 211MB/s] model-00001-of-00011.safetensors: 39%|███▉ | 744M/1.90G [00:03<00:01, 882MB/s] model-00001-of-00011.safetensors: 68%|██████▊ | 1.29G/1.90G [00:03<00:00, 1.54GB/s] model-00001-of-00011.safetensors: 81%|████████ | 1.53G/1.90G [00:03<00:00, 1.05GB/s] model-00001-of-00011.safetensors: 91%|█████████ | 1.72G/1.90G [00:03<00:00, 990MB/s] model-00001-of-00011.safetensors: 100%|█████████▉| 1.90G/1.90G [00:03<00:00, 480MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00002-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00002-of-00011.safetensors: 1%| | 10.5M/1.98G [00:02<06:58, 4.71MB/s] model-00002-of-00011.safetensors: 1%| | 21.0M/1.98G [00:02<03:29, 9.34MB/s] model-00002-of-00011.safetensors: 7%|▋ | 136M/1.98G [00:02<00:20, 88.5MB/s] model-00002-of-00011.safetensors: 11%|█ | 210M/1.98G [00:02<00:12, 145MB/s] model-00002-of-00011.safetensors: 53%|█████▎ | 1.06G/1.98G [00:02<00:00, 1.08GB/s] model-00002-of-00011.safetensors: 70%|███████ | 1.39G/1.98G [00:03<00:00, 878MB/s] model-00002-of-00011.safetensors: 83%|████████▎ | 1.64G/1.98G [00:03<00:00, 893MB/s] model-00002-of-00011.safetensors: 93%|█████████▎| 1.84G/1.98G [00:03<00:00, 931MB/s] model-00002-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 388MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00003-of-00011.safetensors: 0%| | 0.00/1.99G [00:00<?, ?B/s] model-00003-of-00011.safetensors: 1%| | 10.5M/1.99G [00:02<06:32, 5.03MB/s] model-00003-of-00011.safetensors: 1%| | 21.0M/1.99G [00:02<02:54, 11.3MB/s] model-00003-of-00011.safetensors: 3%|▎ | 62.9M/1.99G [00:02<00:42, 44.8MB/s] model-00003-of-00011.safetensors: 4%|▍ | 83.9M/1.99G [00:02<00:41, 45.9MB/s] model-00003-of-00011.safetensors: 14%|█▎ | 273M/1.99G [00:02<00:07, 228MB/s] model-00003-of-00011.safetensors: 45%|████▌ | 902M/1.99G [00:02<00:01, 981MB/s] model-00003-of-00011.safetensors: 60%|█████▉ | 1.18G/1.99G [00:03<00:00, 1.08GB/s] model-00003-of-00011.safetensors: 71%|███████ | 1.41G/1.99G [00:03<00:00, 591MB/s] model-00003-of-00011.safetensors: 79%|███████▉ | 1.58G/1.99G [00:04<00:00, 521MB/s] model-00003-of-00011.safetensors: 100%|█████████▉| 1.99G/1.99G [00:04<00:00, 432MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00004-of-00011.safetensors: 0%| | 0.00/1.94G [00:00<?, ?B/s] model-00004-of-00011.safetensors: 1%| | 10.5M/1.94G [00:02<06:49, 4.71MB/s] model-00004-of-00011.safetensors: 1%| | 21.0M/1.94G [00:02<03:10, 10.0MB/s] model-00004-of-00011.safetensors: 2%|▏ | 31.5M/1.94G [00:02<01:54, 16.6MB/s] model-00004-of-00011.safetensors: 28%|██▊ | 535M/1.94G [00:02<00:02, 476MB/s] model-00004-of-00011.safetensors: 36%|███▋ | 703M/1.94G [00:02<00:02, 582MB/s] model-00004-of-00011.safetensors: 44%|████▍ | 849M/1.94G [00:02<00:01, 672MB/s] model-00004-of-00011.safetensors: 51%|█████▏ | 996M/1.94G [00:03<00:01, 772MB/s] model-00004-of-00011.safetensors: 58%|█████▊ | 1.13G/1.94G [00:03<00:01, 485MB/s] model-00004-of-00011.safetensors: 64%|██████▎ | 1.24G/1.94G [00:04<00:02, 243MB/s] model-00004-of-00011.safetensors: 68%|██████▊ | 1.31G/1.94G [00:04<00:02, 272MB/s] model-00004-of-00011.safetensors: 100%|█████████▉| 1.94G/1.94G [00:05<00:00, 379MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00005-of-00011.safetensors: 0%| | 0.00/1.99G [00:00<?, ?B/s] model-00005-of-00011.safetensors: 1%| | 10.5M/1.99G [00:02<07:23, 4.46MB/s] model-00005-of-00011.safetensors: 1%| | 21.0M/1.99G [00:02<03:19, 9.87MB/s] model-00005-of-00011.safetensors: 3%|▎ | 52.4M/1.99G [00:02<01:14, 25.8MB/s] model-00005-of-00011.safetensors: 8%|▊ | 157M/1.99G [00:03<00:17, 104MB/s] model-00005-of-00011.safetensors: 10%|█ | 199M/1.99G [00:03<00:13, 134MB/s] model-00005-of-00011.safetensors: 34%|███▍ | 682M/1.99G [00:03<00:01, 707MB/s] model-00005-of-00011.safetensors: 63%|██████▎ | 1.25G/1.99G [00:03<00:00, 1.43GB/s] model-00005-of-00011.safetensors: 78%|███████▊ | 1.56G/1.99G [00:04<00:00, 619MB/s] model-00005-of-00011.safetensors: 89%|████████▉ | 1.78G/1.99G [00:04<00:00, 680MB/s] model-00005-of-00011.safetensors: 100%|█████████▉| 1.99G/1.99G [00:04<00:00, 414MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00006-of-00011.safetensors: 0%| | 0.00/1.94G [00:00<?, ?B/s] model-00006-of-00011.safetensors: 1%| | 10.5M/1.94G [00:02<07:03, 4.55MB/s] model-00006-of-00011.safetensors: 2%|▏ | 41.9M/1.94G [00:02<01:39, 19.0MB/s] model-00006-of-00011.safetensors: 15%|█▌ | 294M/1.94G [00:02<00:09, 182MB/s] model-00006-of-00011.safetensors: 57%|█████▋ | 1.11G/1.94G [00:02<00:00, 849MB/s] model-00006-of-00011.safetensors: 75%|███████▍ | 1.45G/1.94G [00:04<00:00, 527MB/s] model-00006-of-00011.safetensors: 86%|████████▋ | 1.68G/1.94G [00:04<00:00, 582MB/s] model-00006-of-00011.safetensors: 100%|█████████▉| 1.94G/1.94G [00:04<00:00, 434MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00007-of-00011.safetensors: 0%| | 0.00/1.99G [00:00<?, ?B/s] model-00007-of-00011.safetensors: 1%| | 10.5M/1.99G [00:02<07:56, 4.15MB/s] model-00007-of-00011.safetensors: 2%|▏ | 41.9M/1.99G [00:02<01:44, 18.5MB/s] model-00007-of-00011.safetensors: 7%|▋ | 147M/1.99G [00:02<00:22, 82.3MB/s] model-00007-of-00011.safetensors: 57%|█████▋ | 1.14G/1.99G [00:03<00:00, 890MB/s] model-00007-of-00011.safetensors: 78%|███████▊ | 1.56G/1.99G [00:04<00:00, 579MB/s] model-00007-of-00011.safetensors: 93%|█████████▎| 1.84G/1.99G [00:04<00:00, 682MB/s] model-00007-of-00011.safetensors: 100%|█████████▉| 1.99G/1.99G [00:04<00:00, 438MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00008-of-00011.safetensors: 0%| | 0.00/1.94G [00:00<?, ?B/s] model-00008-of-00011.safetensors: 1%| | 10.5M/1.94G [00:01<05:55, 5.42MB/s] model-00008-of-00011.safetensors: 1%| | 21.0M/1.94G [00:02<03:18, 9.66MB/s] model-00008-of-00011.safetensors: 4%|▍ | 73.4M/1.94G [00:02<00:43, 42.6MB/s] model-00008-of-00011.safetensors: 10%|█ | 199M/1.94G [00:02<00:11, 146MB/s] model-00008-of-00011.safetensors: 23%|██▎ | 440M/1.94G [00:02<00:03, 391MB/s] model-00008-of-00011.safetensors: 58%|█████▊ | 1.13G/1.94G [00:03<00:00, 1.13GB/s] model-00008-of-00011.safetensors: 69%|██████▉ | 1.34G/1.94G [00:03<00:00, 781MB/s] model-00008-of-00011.safetensors: 77%|███████▋ | 1.50G/1.94G [00:03<00:00, 840MB/s] model-00008-of-00011.safetensors: 85%|████████▍ | 1.64G/1.94G [00:04<00:00, 620MB/s] model-00008-of-00011.safetensors: 100%|█████████▉| 1.94G/1.94G [00:05<00:00, 380MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-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<06:44, 4.87MB/s] model-00009-of-00011.safetensors: 1%| | 21.0M/1.98G [00:02<03:34, 9.14MB/s] model-00009-of-00011.safetensors: 6%|▋ | 126M/1.98G [00:02<00:23, 79.8MB/s] model-00009-of-00011.safetensors: 49%|████▊ | 965M/1.98G [00:02<00:01, 815MB/s] model-00009-of-00011.safetensors: 67%|██████▋ | 1.33G/1.98G [00:03<00:01, 519MB/s] model-00009-of-00011.safetensors: 99%|█████████▉| 1.97G/1.98G [00:04<00:00, 921MB/s] model-00009-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 389MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: model-00010-of-00011.safetensors: 0%| | 0.00/1.94G [00:00<?, ?B/s] model-00010-of-00011.safetensors: 1%| | 10.5M/1.94G [00:02<06:54, 4.65MB/s] model-00010-of-00011.safetensors: 1%| | 21.0M/1.94G [00:02<03:44, 8.55MB/s] model-00010-of-00011.safetensors: 2%|▏ | 31.5M/1.94G [00:02<02:12, 14.4MB/s] model-00010-of-00011.safetensors: 3%|▎ | 52.4M/1.94G [00:03<01:04, 29.1MB/s] model-00010-of-00011.safetensors: 5%|▌ | 105M/1.94G [00:03<00:23, 78.0MB/s] model-00010-of-00011.safetensors: 28%|██▊ | 535M/1.94G [00:03<00:02, 603MB/s] model-00010-of-00011.safetensors: 57%|█████▋ | 1.11G/1.94G [00:03<00:00, 1.27GB/s] model-00010-of-00011.safetensors: 69%|██████▉ | 1.34G/1.94G [00:04<00:00, 677MB/s] model-00010-of-00011.safetensors: 78%|███████▊ | 1.51G/1.94G [00:04<00:00, 615MB/s] model-00010-of-00011.safetensors: 85%|████████▍ | 1.64G/1.94G [00:04<00:00, 625MB/s] model-00010-of-00011.safetensors: 100%|█████████▉| 1.94G/1.94G [00:04<00:00, 398MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-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<07:08, 4.38MB/s] model-00011-of-00011.safetensors: 3%|▎ | 52.4M/1.89G [00:02<01:06, 27.6MB/s] model-00011-of-00011.safetensors: 4%|▍ | 83.9M/1.89G [00:02<00:43, 41.6MB/s] model-00011-of-00011.safetensors: 7%|▋ | 136M/1.89G [00:02<00:21, 81.2MB/s] model-00011-of-00011.safetensors: 60%|██████ | 1.14G/1.89G [00:03<00:00, 1.06GB/s] model-00011-of-00011.safetensors: 73%|███████▎ | 1.39G/1.89G [00:04<00:00, 542MB/s] model-00011-of-00011.safetensors: 82%|████████▏ | 1.55G/1.89G [00:04<00:00, 581MB/s] model-00011-of-00011.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 418MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-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, 1.55MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/551 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 551/551 [00:00<00:00, 6.94MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 16.7MB/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 16.6MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 50.1MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/984 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 984/984 [00:00<00:00, 6.83MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Downloaded to shared memory in 60.442s
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Reading /tmp/tmpmbgloq97/model.safetensors.index.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Profiling: 0%| | 0/435 [00:00<?, ?it/s] Profiling: 0%| | 1/435 [00:01<09:47, 1.35s/it] Profiling: 3%|▎ | 13/435 [00:01<00:35, 11.89it/s] Profiling: 7%|▋ | 30/435 [00:01<00:13, 30.19it/s] Profiling: 9%|▉ | 41/435 [00:01<00:11, 35.28it/s] Profiling: 12%|█▏ | 54/435 [00:01<00:07, 49.03it/s] Profiling: 15%|█▌ | 66/435 [00:02<00:06, 58.51it/s] Profiling: 17%|█▋ | 76/435 [00:02<00:05, 64.38it/s] Profiling: 20%|█▉ | 86/435 [00:02<00:06, 53.86it/s] Profiling: 23%|██▎ | 98/435 [00:02<00:05, 65.32it/s] Profiling: 25%|██▌ | 110/435 [00:02<00:04, 75.11it/s] Profiling: 28%|██▊ | 120/435 [00:02<00:05, 60.35it/s] Profiling: 30%|███ | 132/435 [00:02<00:04, 70.19it/s] Profiling: 33%|███▎ | 144/435 [00:03<00:03, 80.67it/s] Profiling: 36%|███▋ | 158/435 [00:03<00:03, 90.89it/s] Profiling: 39%|███▉ | 169/435 [00:03<00:03, 71.36it/s] Profiling: 42%|████▏ | 183/435 [00:03<00:02, 85.36it/s] Profiling: 45%|████▍ | 194/435 [00:03<00:02, 90.56it/s] Profiling: 47%|████▋ | 205/435 [00:03<00:03, 66.18it/s] Profiling: 51%|█████ | 221/435 [00:04<00:02, 81.92it/s] Profiling: 53%|█████▎ | 232/435 [00:04<00:02, 84.39it/s] Profiling: 56%|█████▌ | 242/435 [00:04<00:02, 69.12it/s] Profiling: 59%|█████▉ | 257/435 [00:04<00:02, 82.43it/s] Profiling: 62%|██████▏ | 268/435 [00:04<00:01, 85.34it/s] Profiling: 64%|██████▍ | 280/435 [00:04<00:02, 73.41it/s] Profiling: 67%|██████▋ | 293/435 [00:04<00:01, 83.99it/s] Profiling: 70%|██████▉ | 303/435 [00:05<00:01, 87.42it/s] Profiling: 72%|███████▏ | 315/435 [00:05<00:01, 94.90it/s] Profiling: 75%|███████▍ | 326/435 [00:05<00:01, 77.49it/s] Profiling: 78%|███████▊ | 338/435 [00:05<00:01, 86.85it/s] Profiling: 80%|████████ | 349/435 [00:05<00:00, 88.59it/s] Profiling: 83%|████████▎ | 359/435 [00:05<00:01, 74.65it/s] Profiling: 86%|████████▌ | 372/435 [00:05<00:00, 84.29it/s] Profiling: 88%|████████▊ | 382/435 [00:05<00:00, 87.36it/s] Profiling: 90%|█████████ | 393/435 [00:06<00:00, 92.96it/s] Profiling: 93%|█████████▎| 403/435 [00:07<00:01, 19.02it/s] Profiling: 96%|█████████▌| 416/435 [00:07<00:00, 26.82it/s] Profiling: 98%|█████████▊| 427/435 [00:07<00:00, 34.29it/s] Profiling: 100%|██████████| 435/435 [00:08<00:00, 53.94it/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: quantized model in 25.794s
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Processed model saishf/Fimbulvetr-Kuro-Lotus-10.7B in 88.251s
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: creating bucket guanaco-mkml-models
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/special_tokens_map.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/config.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/tokenizer_config.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/tokenizer.model
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/tokenizer.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/saishf-fimbulvetr-kuro-l-8724-v3/mkml_model.tensors
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-fimbulvetr-kuro-l-8724-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.
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: warnings.warn(
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.14MB/s]
saishf-fimbulvetr-kuro-l-8724-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.
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: warnings.warn(
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.52MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 38.2MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 9.33MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 9.30MB/s]
saishf-fimbulvetr-kuro-l-8724-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.
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: warnings.warn(
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:07, 203MB/s] pytorch_model.bin: 7%|▋ | 94.4M/1.44G [00:00<00:02, 502MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:02, 605MB/s] pytorch_model.bin: 22%|██▏ | 315M/1.44G [00:00<00:01, 880MB/s] pytorch_model.bin: 28%|██▊ | 409M/1.44G [00:00<00:01, 687MB/s] pytorch_model.bin: 38%|███▊ | 543M/1.44G [00:00<00:01, 852MB/s] pytorch_model.bin: 45%|████▍ | 648M/1.44G [00:00<00:00, 818MB/s] pytorch_model.bin: 55%|█████▍ | 794M/1.44G [00:00<00:00, 984MB/s] pytorch_model.bin: 67%|██████▋ | 962M/1.44G [00:01<00:00, 1.15GB/s] pytorch_model.bin: 87%|████████▋ | 1.26G/1.44G [00:01<00:00, 1.63GB/s] pytorch_model.bin: 99%|█████████▉| 1.43G/1.44G [00:01<00:00, 881MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 281MB/s]
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Saving duration: 0.308s
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.021s
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: creating bucket guanaco-reward-models
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/config.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/special_tokens_map.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/tokenizer_config.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/merges.txt
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/vocab.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/tokenizer.json
saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-fimbulvetr-kuro-l-8724-v3_reward/reward.tensors
Job saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer completed after 117.12s with status: succeeded
Stopping job with name saishf-fimbulvetr-kuro-l-8724-v3-mkmlizer
Pipeline stage MKMLizer completed in 121.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service saishf-fimbulvetr-kuro-l-8724-v3
Waiting for inference service saishf-fimbulvetr-kuro-l-8724-v3 to be ready
Inference service saishf-fimbulvetr-kuro-l-8724-v3 ready after 50.293744802474976s
Pipeline stage ISVCDeployer completed in 57.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.157036542892456s
Received healthy response to inference request in 1.2994887828826904s
Received healthy response to inference request in 1.621077060699463s
Received healthy response to inference request in 1.4863274097442627s
Received healthy response to inference request in 1.4882967472076416s
5 requests
0 failed requests
5th percentile: 1.3368565082550048
10th percentile: 1.3742242336273194
20th percentile: 1.4489596843719483
30th percentile: 1.4867212772369385
40th percentile: 1.48750901222229
50th percentile: 1.4882967472076416
60th percentile: 1.5414088726043702
70th percentile: 1.5945209980010986
80th percentile: 1.7282689571380616
90th percentile: 1.9426527500152588
95th percentile: 2.0498446464538573
99th percentile: 2.1355981636047363
mean time: 1.6104453086853028
Pipeline stage StressChecker completed in 9.15s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
Running M-Eval for topic stay_in_character
saishf-fimbulvetr-kuro-l_8724_v3 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
saishf-fimbulvetr-kuro-l_8724_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics