submission_id: grimjim-kukulemon-7b_v4
developer_uid: chai_backend_admin
status: inactive
model_repo: grimjim/kukulemon-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: 2024-04-01T21:17:54+00:00
model_name: auto_submit_wehay_tawigite
model_eval_status: success
safety_score: 0.98
entertaining: 6.82
stay_in_character: 8.54
user_preference: 7.44
double_thumbs_up: 67
thumbs_up: 101
thumbs_down: 44
num_battles: 5485
num_wins: 2499
win_ratio: 0.45560619872379216
celo_rating: 1130.91
Resubmit model
Running pipeline stage MKMLizer
Starting job with name grimjim-kukulemon-7b-v4-mkmlizer
Waiting for job on grimjim-kukulemon-7b-v4-mkmlizer to finish
grimjim-kukulemon-7b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-kukulemon-7b-v4-mkmlizer: ║ _____ __ __ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ /___/ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ Version: 0.6.11 ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ belonging to: ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ Chai Research Corp. ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
grimjim-kukulemon-7b-v4-mkmlizer: ║ ║
grimjim-kukulemon-7b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-kukulemon-7b-v4-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.9MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: README.md: 0%| | 0.00/1.93k [00:00<?, ?B/s] README.md: 100%|██████████| 1.93k/1.93k [00:00<00:00, 16.5MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: config.json: 0%| | 0.00/645 [00:00<?, ?B/s] config.json: 100%|██████████| 645/645 [00:00<00:00, 9.87MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: mergekit_config.yml: 0%| | 0.00/481 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 481/481 [00:00<00:00, 6.77MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: model-00001-of-00002.safetensors: 0%| | 0.00/9.86G [00:00<?, ?B/s] model-00001-of-00002.safetensors: 0%| | 10.5M/9.86G [00:00<08:24, 19.5MB/s] model-00001-of-00002.safetensors: 0%| | 31.5M/9.86G [00:01<06:00, 27.3MB/s] model-00001-of-00002.safetensors: 0%| | 41.9M/9.86G [00:01<05:50, 28.0MB/s] model-00001-of-00002.safetensors: 1%| | 73.4M/9.86G [00:01<02:40, 60.8MB/s] model-00001-of-00002.safetensors: 1%|▏ | 136M/9.86G [00:01<01:22, 118MB/s] model-00001-of-00002.safetensors: 2%|▏ | 157M/9.86G [00:02<01:27, 111MB/s] model-00001-of-00002.safetensors: 2%|▏ | 210M/9.86G [00:02<01:00, 160MB/s] model-00001-of-00002.safetensors: 2%|▏ | 241M/9.86G [00:02<00:56, 172MB/s] model-00001-of-00002.safetensors: 3%|▎ | 325M/9.86G [00:02<00:32, 290MB/s] model-00001-of-00002.safetensors: 4%|▎ | 367M/9.86G [00:02<00:32, 295MB/s] model-00001-of-00002.safetensors: 4%|▍ | 409M/9.86G [00:02<00:30, 309MB/s] model-00001-of-00002.safetensors: 5%|▌ | 514M/9.86G [00:02<00:20, 464MB/s] model-00001-of-00002.safetensors: 7%|▋ | 650M/9.86G [00:03<00:13, 659MB/s] model-00001-of-00002.safetensors: 8%|▊ | 807M/9.86G [00:03<00:10, 832MB/s] model-00001-of-00002.safetensors: 10%|▉ | 954M/9.86G [00:03<00:09, 987MB/s] model-00001-of-00002.safetensors: 14%|█▎ | 1.35G/9.86G [00:03<00:05, 1.68GB/s] model-00001-of-00002.safetensors: 16%|█▌ | 1.53G/9.86G [00:04<00:12, 660MB/s] model-00001-of-00002.safetensors: 17%|█▋ | 1.69G/9.86G [00:04<00:10, 774MB/s] model-00001-of-00002.safetensors: 19%|█▊ | 1.84G/9.86G [00:04<00:11, 690MB/s] model-00001-of-00002.safetensors: 20%|█▉ | 1.95G/9.86G [00:04<00:11, 693MB/s] model-00001-of-00002.safetensors: 21%|██ | 2.08G/9.86G [00:04<00:10, 769MB/s] model-00001-of-00002.safetensors: 22%|██▏ | 2.21G/9.86G [00:04<00:08, 863MB/s] model-00001-of-00002.safetensors: 24%|██▍ | 2.39G/9.86G [00:04<00:07, 1.04GB/s] model-00001-of-00002.safetensors: 26%|██▌ | 2.53G/9.86G [00:05<00:07, 1.04GB/s] model-00001-of-00002.safetensors: 27%|██▋ | 2.65G/9.86G [00:05<00:06, 1.07GB/s] model-00001-of-00002.safetensors: 30%|██▉ | 2.94G/9.86G [00:05<00:04, 1.39GB/s] model-00001-of-00002.safetensors: 31%|███▏ | 3.09G/9.86G [00:05<00:05, 1.33GB/s] model-00001-of-00002.safetensors: 33%|███▎ | 3.24G/9.86G [00:05<00:07, 858MB/s] model-00001-of-00002.safetensors: 34%|███▍ | 3.36G/9.86G [00:05<00:08, 786MB/s] model-00001-of-00002.safetensors: 35%|███▌ | 3.46G/9.86G [00:06<00:09, 672MB/s] model-00001-of-00002.safetensors: 36%|███▌ | 3.54G/9.86G [00:06<00:09, 693MB/s] model-00001-of-00002.safetensors: 37%|███▋ | 3.64G/9.86G [00:06<00:08, 720MB/s] model-00001-of-00002.safetensors: 38%|███▊ | 3.73G/9.86G [00:06<00:08, 757MB/s] model-00001-of-00002.safetensors: 40%|████ | 3.95G/9.86G [00:06<00:05, 1.07GB/s] model-00001-of-00002.safetensors: 42%|████▏ | 4.10G/9.86G [00:06<00:04, 1.17GB/s] model-00001-of-00002.safetensors: 43%|████▎ | 4.24G/9.86G [00:06<00:05, 964MB/s] model-00001-of-00002.safetensors: 44%|████▍ | 4.35G/9.86G [00:07<00:07, 773MB/s] model-00001-of-00002.safetensors: 45%|████▌ | 4.45G/9.86G [00:07<00:08, 671MB/s] model-00001-of-00002.safetensors: 46%|████▌ | 4.53G/9.86G [00:07<00:07, 674MB/s] model-00001-of-00002.safetensors: 47%|████▋ | 4.61G/9.86G [00:07<00:07, 673MB/s] model-00001-of-00002.safetensors: 48%|████▊ | 4.69G/9.86G [00:07<00:07, 675MB/s] model-00001-of-00002.safetensors: 49%|████▊ | 4.79G/9.86G [00:07<00:07, 716MB/s] model-00001-of-00002.safetensors: 50%|████▉ | 4.93G/9.86G [00:07<00:05, 848MB/s] model-00001-of-00002.safetensors: 52%|█████▏ | 5.13G/9.86G [00:08<00:04, 1.13GB/s] model-00001-of-00002.safetensors: 53%|█████▎ | 5.25G/9.86G [00:08<00:04, 1.08GB/s] model-00001-of-00002.safetensors: 54%|█████▍ | 5.37G/9.86G [00:08<00:05, 793MB/s] model-00001-of-00002.safetensors: 55%|█████▌ | 5.46G/9.86G [00:08<00:06, 726MB/s] model-00001-of-00002.safetensors: 56%|█████▋ | 5.55G/9.86G [00:08<00:06, 658MB/s] model-00001-of-00002.safetensors: 57%|█████▋ | 5.63G/9.86G [00:08<00:06, 694MB/s] model-00001-of-00002.safetensors: 58%|█████▊ | 5.71G/9.86G [00:09<00:05, 708MB/s] model-00001-of-00002.safetensors: 59%|█████▉ | 5.82G/9.86G [00:09<00:05, 786MB/s] model-00001-of-00002.safetensors: 60%|█████▉ | 5.90G/9.86G [00:09<00:04, 793MB/s] model-00001-of-00002.safetensors: 61%|██████ | 5.99G/9.86G [00:09<00:04, 791MB/s] model-00001-of-00002.safetensors: 63%|██████▎ | 6.22G/9.86G [00:09<00:03, 1.18GB/s] model-00001-of-00002.safetensors: 64%|██████▍ | 6.34G/9.86G [00:09<00:03, 1.10GB/s] model-00001-of-00002.safetensors: 66%|██████▌ | 6.46G/9.86G [00:09<00:03, 964MB/s] model-00001-of-00002.safetensors: 67%|██████▋ | 6.56G/9.86G [00:10<00:05, 631MB/s] model-00001-of-00002.safetensors: 67%|██████▋ | 6.65G/9.86G [00:10<00:05, 605MB/s] model-00001-of-00002.safetensors: 68%|██████▊ | 6.74G/9.86G [00:10<00:04, 669MB/s] model-00001-of-00002.safetensors: 69%|██████▉ | 6.85G/9.86G [00:10<00:04, 739MB/s] model-00001-of-00002.safetensors: 70%|███████ | 6.94G/9.86G [00:10<00:03, 785MB/s] model-00001-of-00002.safetensors: 71%|███████▏ | 7.04G/9.86G [00:10<00:03, 717MB/s] model-00001-of-00002.safetensors: 73%|███████▎ | 7.20G/9.86G [00:10<00:02, 934MB/s] model-00001-of-00002.safetensors: 74%|███████▍ | 7.34G/9.86G [00:10<00:02, 1.00GB/s] model-00001-of-00002.safetensors: 76%|███████▌ | 7.48G/9.86G [00:11<00:02, 1.06GB/s] model-00001-of-00002.safetensors: 77%|███████▋ | 7.60G/9.86G [00:11<00:02, 949MB/s] model-00001-of-00002.safetensors: 78%|███████▊ | 7.71G/9.86G [00:11<00:02, 818MB/s] model-00001-of-00002.safetensors: 79%|███████▉ | 7.80G/9.86G [00:11<00:02, 752MB/s] model-00001-of-00002.safetensors: 80%|███████▉ | 7.89G/9.86G [00:11<00:02, 667MB/s] model-00001-of-00002.safetensors: 81%|████████ | 7.97G/9.86G [00:11<00:02, 633MB/s] model-00001-of-00002.safetensors: 82%|████████▏ | 8.04G/9.86G [00:11<00:03, 578MB/s] model-00001-of-00002.safetensors: 82%|████████▏ | 8.11G/9.86G [00:12<00:02, 588MB/s] model-00001-of-00002.safetensors: 83%|████████▎ | 8.20G/9.86G [00:12<00:02, 670MB/s] model-00001-of-00002.safetensors: 85%|████████▌ | 8.40G/9.86G [00:12<00:01, 996MB/s] model-00001-of-00002.safetensors: 86%|████████▋ | 8.52G/9.86G [00:12<00:01, 1.06GB/s] model-00001-of-00002.safetensors: 88%|████████▊ | 8.68G/9.86G [00:12<00:01, 1.17GB/s] model-00001-of-00002.safetensors: 89%|████████▉ | 8.81G/9.86G [00:12<00:01, 862MB/s] model-00001-of-00002.safetensors: 90%|█████████ | 8.91G/9.86G [00:12<00:01, 902MB/s] model-00001-of-00002.safetensors: 91%|█████████▏| 9.02G/9.86G [00:12<00:01, 834MB/s] model-00001-of-00002.safetensors: 92%|█████████▏| 9.11G/9.86G [00:13<00:01, 726MB/s] model-00001-of-00002.safetensors: 93%|█████████▎| 9.20G/9.86G [00:13<00:00, 728MB/s] model-00001-of-00002.safetensors: 95%|█████████▌| 9.39G/9.86G [00:13<00:00, 964MB/s] model-00001-of-00002.safetensors: 97%|█████████▋| 9.60G/9.86G [00:13<00:00, 1.23GB/s] model-00001-of-00002.safetensors: 100%|█████████▉| 9.86G/9.86G [00:13<00:00, 723MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: model-00002-of-00002.safetensors: 0%| | 0.00/4.62G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 0%| | 10.5M/4.62G [00:00<06:24, 12.0MB/s] model-00002-of-00002.safetensors: 0%| | 21.0M/4.62G [00:01<03:49, 20.1MB/s] model-00002-of-00002.safetensors: 1%| | 31.5M/4.62G [00:01<03:01, 25.3MB/s] model-00002-of-00002.safetensors: 1%|▏ | 62.9M/4.62G [00:01<01:11, 63.8MB/s] model-00002-of-00002.safetensors: 2%|▏ | 115M/4.62G [00:01<00:34, 131MB/s] model-00002-of-00002.safetensors: 3%|▎ | 147M/4.62G [00:01<00:34, 129MB/s] model-00002-of-00002.safetensors: 4%|▍ | 178M/4.62G [00:02<00:28, 157MB/s] model-00002-of-00002.safetensors: 5%|▍ | 210M/4.62G [00:02<00:25, 170MB/s] model-00002-of-00002.safetensors: 6%|▌ | 262M/4.62G [00:02<00:18, 234MB/s] model-00002-of-00002.safetensors: 6%|▋ | 294M/4.62G [00:02<00:19, 227MB/s] model-00002-of-00002.safetensors: 7%|▋ | 336M/4.62G [00:02<00:16, 266MB/s] model-00002-of-00002.safetensors: 8%|▊ | 377M/4.62G [00:02<00:14, 294MB/s] model-00002-of-00002.safetensors: 10%|▉ | 451M/4.62G [00:02<00:10, 389MB/s] model-00002-of-00002.safetensors: 13%|█▎ | 608M/4.62G [00:02<00:05, 678MB/s] model-00002-of-00002.safetensors: 17%|█▋ | 776M/4.62G [00:03<00:04, 889MB/s] model-00002-of-00002.safetensors: 19%|█▉ | 870M/4.62G [00:03<00:04, 863MB/s] model-00002-of-00002.safetensors: 29%|██▉ | 1.36G/4.62G [00:03<00:01, 1.91GB/s] model-00002-of-00002.safetensors: 34%|███▍ | 1.57G/4.62G [00:04<00:04, 648MB/s] model-00002-of-00002.safetensors: 37%|███▋ | 1.73G/4.62G [00:04<00:03, 740MB/s] model-00002-of-00002.safetensors: 41%|████ | 1.88G/4.62G [00:04<00:04, 641MB/s] model-00002-of-00002.safetensors: 43%|████▎ | 2.00G/4.62G [00:04<00:04, 624MB/s] model-00002-of-00002.safetensors: 46%|████▌ | 2.11G/4.62G [00:04<00:03, 662MB/s] model-00002-of-00002.safetensors: 48%|████▊ | 2.21G/4.62G [00:05<00:03, 620MB/s] model-00002-of-00002.safetensors: 50%|█████ | 2.32G/4.62G [00:05<00:03, 691MB/s] model-00002-of-00002.safetensors: 54%|█████▍ | 2.52G/4.62G [00:05<00:02, 917MB/s] model-00002-of-00002.safetensors: 57%|█████▋ | 2.63G/4.62G [00:05<00:02, 892MB/s] model-00002-of-00002.safetensors: 60%|█████▉ | 2.76G/4.62G [00:05<00:01, 956MB/s] model-00002-of-00002.safetensors: 67%|██████▋ | 3.11G/4.62G [00:05<00:00, 1.56GB/s] model-00002-of-00002.safetensors: 71%|███████▏ | 3.30G/4.62G [00:05<00:00, 1.61GB/s] model-00002-of-00002.safetensors: 76%|███████▌ | 3.49G/4.62G [00:05<00:00, 1.29GB/s] model-00002-of-00002.safetensors: 79%|███████▉ | 3.65G/4.62G [00:06<00:01, 808MB/s] model-00002-of-00002.safetensors: 82%|████████▏ | 3.78G/4.62G [00:06<00:01, 820MB/s] model-00002-of-00002.safetensors: 84%|████████▍ | 3.89G/4.62G [00:06<00:00, 789MB/s] model-00002-of-00002.safetensors: 88%|████████▊ | 4.08G/4.62G [00:06<00:00, 981MB/s] model-00002-of-00002.safetensors: 91%|█████████ | 4.22G/4.62G [00:06<00:00, 1.06GB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 4.60G/4.62G [00:06<00:00, 1.68GB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 4.62G/4.62G [00:07<00:00, 653MB/s]
grimjim-kukulemon-7b-v4-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, 24.6MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.50MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 27.9MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 56.2MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 8.14MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: Downloaded to shared memory in 24.502s
grimjim-kukulemon-7b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-kukulemon-7b-v4-mkmlizer: Saving mkml model at /dev/shm/model_cache
grimjim-kukulemon-7b-v4-mkmlizer: Reading /tmp/tmpbged1xyt/model.safetensors.index.json
grimjim-kukulemon-7b-v4-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:01<06:08, 1.27s/it] Profiling: 4%|▍ | 12/291 [00:01<00:23, 11.80it/s] Profiling: 8%|▊ | 23/291 [00:01<00:11, 23.92it/s] Profiling: 14%|█▎ | 40/291 [00:01<00:05, 44.77it/s] Profiling: 19%|█▉ | 55/291 [00:01<00:03, 62.93it/s] Profiling: 23%|██▎ | 68/291 [00:01<00:03, 73.29it/s] Profiling: 29%|██▉ | 85/291 [00:01<00:02, 90.73it/s] Profiling: 34%|███▍ | 100/291 [00:02<00:01, 104.24it/s] Profiling: 39%|███▉ | 114/291 [00:02<00:01, 105.74it/s] Profiling: 45%|████▍ | 130/291 [00:02<00:01, 114.69it/s] Profiling: 51%|█████ | 147/291 [00:02<00:01, 123.79it/s] Profiling: 55%|█████▌ | 161/291 [00:02<00:01, 123.26it/s] Profiling: 60%|██████ | 175/291 [00:02<00:00, 123.69it/s] Profiling: 65%|██████▍ | 189/291 [00:02<00:00, 127.55it/s] Profiling: 70%|██████▉ | 203/291 [00:04<00:03, 22.79it/s] Profiling: 75%|███████▍ | 218/291 [00:04<00:02, 30.90it/s] Profiling: 79%|███████▉ | 230/291 [00:04<00:01, 38.26it/s] Profiling: 84%|████████▍ | 244/291 [00:04<00:00, 48.97it/s] Profiling: 88%|████████▊ | 257/291 [00:04<00:00, 59.03it/s] Profiling: 93%|█████████▎| 271/291 [00:05<00:00, 71.45it/s] Profiling: 98%|█████████▊| 284/291 [00:05<00:00, 81.29it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 53.72it/s]
grimjim-kukulemon-7b-v4-mkmlizer: quantized model in 15.629s
grimjim-kukulemon-7b-v4-mkmlizer: creating bucket guanaco-mkml-models
grimjim-kukulemon-7b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-kukulemon-7b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/special_tokens_map.json
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/config.json
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/tokenizer.model
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/tokenizer.json
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/tokenizer_config.json
grimjim-kukulemon-7b-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/grimjim-kukulemon-7b-v4/mkml_model.tensors
grimjim-kukulemon-7b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
grimjim-kukulemon-7b-v4-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.
grimjim-kukulemon-7b-v4-mkmlizer: warnings.warn(
grimjim-kukulemon-7b-v4-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.7MB/s]
grimjim-kukulemon-7b-v4-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.
grimjim-kukulemon-7b-v4-mkmlizer: warnings.warn(
grimjim-kukulemon-7b-v4-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.96MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 3.01MB/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 3.01MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 21.8MB/s]
grimjim-kukulemon-7b-v4-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.
grimjim-kukulemon-7b-v4-mkmlizer: warnings.warn(
grimjim-kukulemon-7b-v4-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:08, 166MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:12, 115MB/s] pytorch_model.bin: 5%|▌ | 73.4M/1.44G [00:00<00:08, 168MB/s] pytorch_model.bin: 7%|▋ | 105M/1.44G [00:00<00:06, 200MB/s] pytorch_model.bin: 11%|█ | 157M/1.44G [00:00<00:04, 292MB/s] pytorch_model.bin: 14%|█▍ | 199M/1.44G [00:00<00:03, 315MB/s] pytorch_model.bin: 17%|█▋ | 252M/1.44G [00:00<00:03, 323MB/s] pytorch_model.bin: 20%|██ | 294M/1.44G [00:01<00:03, 289MB/s] pytorch_model.bin: 33%|███▎ | 482M/1.44G [00:01<00:01, 665MB/s] pytorch_model.bin: 65%|██████▍ | 933M/1.44G [00:01<00:00, 1.63GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 996MB/s]
grimjim-kukulemon-7b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-kukulemon-7b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-kukulemon-7b-v4_reward/reward.tensors
Job grimjim-kukulemon-7b-v4-mkmlizer completed after 66.7s with status: succeeded
Stopping job with name grimjim-kukulemon-7b-v4-mkmlizer
Pipeline stage MKMLizer completed in 72.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-kukulemon-7b-v4
Waiting for inference service grimjim-kukulemon-7b-v4 to be ready
%s
%s
Inference service grimjim-kukulemon-7b-v4 ready after 70.37678074836731s
Pipeline stage ISVCDeployer completed in 78.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.9667131900787354s
Received healthy response to inference request in 0.7804474830627441s
Received healthy response to inference request in 0.7550172805786133s
Received healthy response to inference request in 0.45158982276916504s
Received healthy response to inference request in 1.0058553218841553s
5 requests
0 failed requests
5th percentile: 0.5122753143310547
10th percentile: 0.5729608058929443
20th percentile: 0.6943317890167237
30th percentile: 0.7601033210754394
40th percentile: 0.7702754020690918
50th percentile: 0.7804474830627441
60th percentile: 0.8549537658691406
70th percentile: 0.9294600486755371
80th percentile: 0.9745416164398193
90th percentile: 0.9901984691619873
95th percentile: 0.9980268955230713
99th percentile: 1.0042896366119385
mean time: 0.7919246196746826
Pipeline stage StressChecker completed in 4.76s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
grimjim-kukulemon-7b_v4 status is now deployed due to DeploymentManager action
grimjim-kukulemon-7b_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics