submission_id: inv-konstanta-v4-alpha-7b_v8
developer_uid: chai_backend_admin
status: torndown
model_repo: Inv/Konstanta-V4-Alpha-7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, '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}:', '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: 2024-04-01T20:56:38+00:00
model_name: auto_submit_hihel_nicutogo
model_eval_status: success
model_group: Inv/Konstanta-V4-Alpha-7
num_battles: 5546
num_wins: 2501
celo_rating: 1127.36
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: auto_submit_hihel_nicutogo
ineligible_reason: propriety_total_count < 800
language_model: Inv/Konstanta-V4-Alpha-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-01
win_ratio: 0.45095564370717633
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-v4-alpha-7b-v8-mkmlizer
Waiting for job on inv-konstanta-v4-alpha-7b-v8-mkmlizer to finish
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ _____ __ __ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ /___/ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ Version: 0.6.11 ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ The license key for the current software has been verified as ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ belonging to: ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ Chai Research Corp. ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-konstanta-v4-alpha-7b-v8-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 14.9MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: README.md: 0%| | 0.00/1.31k [00:00<?, ?B/s] README.md: 100%|██████████| 1.31k/1.31k [00:00<00:00, 17.5MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: config.json: 0%| | 0.00/632 [00:00<?, ?B/s] config.json: 100%|██████████| 632/632 [00:00<00:00, 8.81MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: mergekit_config.yml: 0%| | 0.00/410 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 410/410 [00:00<00:00, 3.67MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<03:01, 10.8MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<01:28, 22.1MB/s] model-00001-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:12, 26.8MB/s] model-00001-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:01<00:55, 35.1MB/s] model-00001-of-00008.safetensors: 5%|▍ | 94.4M/1.98G [00:01<00:17, 109MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:01<00:17, 108MB/s] model-00001-of-00008.safetensors: 8%|▊ | 157M/1.98G [00:02<00:14, 127MB/s] model-00001-of-00008.safetensors: 11%|█ | 210M/1.98G [00:02<00:10, 174MB/s] model-00001-of-00008.safetensors: 13%|█▎ | 252M/1.98G [00:02<00:09, 184MB/s] model-00001-of-00008.safetensors: 16%|█▌ | 315M/1.98G [00:02<00:07, 234MB/s] model-00001-of-00008.safetensors: 18%|█▊ | 357M/1.98G [00:02<00:06, 267MB/s] model-00001-of-00008.safetensors: 21%|██ | 409M/1.98G [00:02<00:04, 318MB/s] model-00001-of-00008.safetensors: 28%|██▊ | 545M/1.98G [00:02<00:02, 550MB/s] model-00001-of-00008.safetensors: 31%|███ | 619M/1.98G [00:03<00:02, 515MB/s] model-00001-of-00008.safetensors: 34%|███▍ | 682M/1.98G [00:03<00:02, 529MB/s] model-00001-of-00008.safetensors: 42%|████▏ | 839M/1.98G [00:03<00:01, 779MB/s] model-00001-of-00008.safetensors: 72%|███████▏ | 1.42G/1.98G [00:03<00:00, 2.00GB/s] model-00001-of-00008.safetensors: 83%|████████▎ | 1.64G/1.98G [00:03<00:00, 1.34GB/s] model-00001-of-00008.safetensors: 92%|█████████▏| 1.81G/1.98G [00:03<00:00, 1.36GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 762MB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 448MB/s]
inv-konstanta-v4-alpha-7b-v8-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<04:18, 7.50MB/s] model-00002-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:01<00:41, 45.4MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:01<00:30, 61.8MB/s] model-00002-of-00008.safetensors: 6%|▋ | 126M/1.95G [00:02<00:19, 94.0MB/s] model-00002-of-00008.safetensors: 8%|▊ | 147M/1.95G [00:02<00:17, 105MB/s] model-00002-of-00008.safetensors: 9%|▊ | 168M/1.95G [00:02<00:14, 120MB/s] model-00002-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:02<00:14, 121MB/s] model-00002-of-00008.safetensors: 11%|█▏ | 220M/1.95G [00:02<00:11, 155MB/s] model-00002-of-00008.safetensors: 13%|█▎ | 262M/1.95G [00:02<00:10, 158MB/s] model-00002-of-00008.safetensors: 15%|█▍ | 283M/1.95G [00:02<00:10, 165MB/s] model-00002-of-00008.safetensors: 18%|█▊ | 346M/1.95G [00:02<00:06, 257MB/s] model-00002-of-00008.safetensors: 20%|██ | 398M/1.95G [00:03<00:05, 293MB/s] model-00002-of-00008.safetensors: 27%|██▋ | 524M/1.95G [00:03<00:02, 509MB/s] model-00002-of-00008.safetensors: 32%|███▏ | 619M/1.95G [00:03<00:02, 574MB/s] model-00002-of-00008.safetensors: 41%|████ | 797M/1.95G [00:03<00:01, 861MB/s] model-00002-of-00008.safetensors: 67%|██████▋ | 1.30G/1.95G [00:03<00:00, 1.83GB/s] model-00002-of-00008.safetensors: 77%|███████▋ | 1.50G/1.95G [00:04<00:00, 843MB/s] model-00002-of-00008.safetensors: 85%|████████▍ | 1.65G/1.95G [00:04<00:00, 680MB/s] model-00002-of-00008.safetensors: 91%|█████████ | 1.77G/1.95G [00:04<00:00, 728MB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 410MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:57, 16.7MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.98G [00:01<01:46, 18.4MB/s] model-00003-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:26, 22.5MB/s] model-00003-of-00008.safetensors: 3%|▎ | 52.4M/1.98G [00:01<00:48, 40.0MB/s] model-00003-of-00008.safetensors: 4%|▎ | 73.4M/1.98G [00:01<00:33, 57.6MB/s] model-00003-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:01<00:29, 63.2MB/s] model-00003-of-00008.safetensors: 5%|▌ | 105M/1.98G [00:02<00:23, 78.4MB/s] model-00003-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:02<00:25, 74.2MB/s] model-00003-of-00008.safetensors: 8%|▊ | 157M/1.98G [00:02<00:17, 103MB/s] model-00003-of-00008.safetensors: 9%|▉ | 178M/1.98G [00:02<00:16, 111MB/s] model-00003-of-00008.safetensors: 11%|█ | 210M/1.98G [00:02<00:12, 138MB/s] model-00003-of-00008.safetensors: 13%|█▎ | 252M/1.98G [00:03<00:10, 168MB/s] model-00003-of-00008.safetensors: 15%|█▍ | 294M/1.98G [00:03<00:07, 213MB/s] model-00003-of-00008.safetensors: 19%|█▉ | 377M/1.98G [00:03<00:04, 345MB/s] model-00003-of-00008.safetensors: 28%|██▊ | 556M/1.98G [00:03<00:02, 679MB/s] model-00003-of-00008.safetensors: 32%|███▏ | 640M/1.98G [00:03<00:02, 648MB/s] model-00003-of-00008.safetensors: 48%|████▊ | 954M/1.98G [00:03<00:00, 1.25GB/s] model-00003-of-00008.safetensors: 61%|██████▏ | 1.22G/1.98G [00:03<00:00, 1.10GB/s] model-00003-of-00008.safetensors: 68%|██████▊ | 1.35G/1.98G [00:04<00:00, 752MB/s] model-00003-of-00008.safetensors: 74%|███████▎ | 1.46G/1.98G [00:04<00:00, 543MB/s] model-00003-of-00008.safetensors: 78%|███████▊ | 1.54G/1.98G [00:04<00:00, 467MB/s] model-00003-of-00008.safetensors: 82%|████████▏ | 1.62G/1.98G [00:05<00:00, 512MB/s] model-00003-of-00008.safetensors: 89%|████████▉ | 1.77G/1.98G [00:05<00:00, 659MB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 373MB/s]
inv-konstanta-v4-alpha-7b-v8-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 [00:00<01:21, 23.6MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<01:32, 20.8MB/s] model-00004-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:31, 20.8MB/s] model-00004-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:01<00:46, 41.2MB/s] model-00004-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:01<00:27, 68.5MB/s] model-00004-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:02<00:26, 69.0MB/s] model-00004-of-00008.safetensors: 7%|▋ | 136M/1.95G [00:02<00:22, 80.9MB/s] model-00004-of-00008.safetensors: 9%|▉ | 178M/1.95G [00:02<00:13, 127MB/s] model-00004-of-00008.safetensors: 11%|█ | 210M/1.95G [00:02<00:11, 158MB/s] model-00004-of-00008.safetensors: 15%|█▍ | 283M/1.95G [00:02<00:06, 264MB/s] model-00004-of-00008.safetensors: 21%|██ | 409M/1.95G [00:02<00:03, 460MB/s] model-00004-of-00008.safetensors: 25%|██▌ | 493M/1.95G [00:02<00:02, 531MB/s] model-00004-of-00008.safetensors: 29%|██▉ | 566M/1.95G [00:03<00:02, 560MB/s] model-00004-of-00008.safetensors: 50%|████▉ | 965M/1.95G [00:03<00:00, 1.40GB/s] model-00004-of-00008.safetensors: 63%|██████▎ | 1.23G/1.95G [00:03<00:00, 1.42GB/s] model-00004-of-00008.safetensors: 71%|███████▏ | 1.39G/1.95G [00:03<00:00, 890MB/s] model-00004-of-00008.safetensors: 78%|███████▊ | 1.52G/1.95G [00:04<00:00, 654MB/s] model-00004-of-00008.safetensors: 83%|████████▎ | 1.62G/1.95G [00:04<00:00, 708MB/s] model-00004-of-00008.safetensors: 89%|████████▊ | 1.73G/1.95G [00:04<00:00, 703MB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 432MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<02:58, 10.5MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.89G [00:01<01:29, 20.9MB/s] model-00005-of-00008.safetensors: 2%|▏ | 31.5M/1.89G [00:01<01:11, 26.1MB/s] model-00005-of-00008.safetensors: 3%|▎ | 52.4M/1.89G [00:01<00:38, 47.6MB/s] model-00005-of-00008.safetensors: 4%|▍ | 83.9M/1.89G [00:01<00:25, 71.3MB/s] model-00005-of-00008.safetensors: 5%|▍ | 94.4M/1.89G [00:02<00:27, 66.3MB/s] model-00005-of-00008.safetensors: 6%|▌ | 115M/1.89G [00:02<00:25, 68.8MB/s] model-00005-of-00008.safetensors: 7%|▋ | 136M/1.89G [00:02<00:23, 76.1MB/s] model-00005-of-00008.safetensors: 9%|▉ | 178M/1.89G [00:02<00:13, 127MB/s] model-00005-of-00008.safetensors: 12%|█▏ | 231M/1.89G [00:02<00:09, 169MB/s] model-00005-of-00008.safetensors: 15%|█▍ | 283M/1.89G [00:02<00:06, 232MB/s] model-00005-of-00008.safetensors: 21%|██ | 388M/1.89G [00:03<00:03, 382MB/s] model-00005-of-00008.safetensors: 29%|██▉ | 545M/1.89G [00:03<00:02, 628MB/s] model-00005-of-00008.safetensors: 37%|███▋ | 692M/1.89G [00:03<00:01, 812MB/s] model-00005-of-00008.safetensors: 64%|██████▍ | 1.21G/1.89G [00:03<00:00, 1.24GB/s] model-00005-of-00008.safetensors: 70%|███████ | 1.33G/1.89G [00:03<00:00, 979MB/s] model-00005-of-00008.safetensors: 76%|███████▌ | 1.44G/1.89G [00:04<00:00, 567MB/s] model-00005-of-00008.safetensors: 81%|████████ | 1.52G/1.89G [00:04<00:00, 583MB/s] model-00005-of-00008.safetensors: 89%|████████▉ | 1.69G/1.89G [00:04<00:00, 737MB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 400MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.92G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.92G [00:01<03:25, 9.32MB/s] model-00006-of-00008.safetensors: 2%|▏ | 31.5M/1.92G [00:01<01:05, 29.0MB/s] model-00006-of-00008.safetensors: 4%|▍ | 73.4M/1.92G [00:01<00:26, 69.5MB/s] model-00006-of-00008.safetensors: 5%|▍ | 94.4M/1.92G [00:01<00:22, 80.0MB/s] model-00006-of-00008.safetensors: 7%|▋ | 136M/1.92G [00:01<00:13, 131MB/s] model-00006-of-00008.safetensors: 9%|▊ | 168M/1.92G [00:02<00:14, 123MB/s] model-00006-of-00008.safetensors: 12%|█▏ | 231M/1.92G [00:02<00:09, 172MB/s] model-00006-of-00008.safetensors: 14%|█▎ | 262M/1.92G [00:02<00:11, 140MB/s] model-00006-of-00008.safetensors: 16%|█▌ | 304M/1.92G [00:02<00:09, 170MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 336M/1.92G [00:03<00:09, 163MB/s] model-00006-of-00008.safetensors: 21%|██▏ | 409M/1.92G [00:03<00:06, 250MB/s] model-00006-of-00008.safetensors: 28%|██▊ | 535M/1.92G [00:03<00:03, 427MB/s] model-00006-of-00008.safetensors: 31%|███ | 598M/1.92G [00:03<00:02, 447MB/s] model-00006-of-00008.safetensors: 35%|███▌ | 682M/1.92G [00:03<00:02, 521MB/s] model-00006-of-00008.safetensors: 68%|██████▊ | 1.31G/1.92G [00:03<00:00, 1.83GB/s] model-00006-of-00008.safetensors: 80%|███████▉ | 1.53G/1.92G [00:04<00:00, 924MB/s] model-00006-of-00008.safetensors: 88%|████████▊ | 1.70G/1.92G [00:04<00:00, 862MB/s] model-00006-of-00008.safetensors: 96%|█████████▌| 1.84G/1.92G [00:04<00:00, 864MB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:05<00:00, 376MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:30, 21.5MB/s] model-00007-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:54, 35.4MB/s] model-00007-of-00008.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:07, 28.5MB/s] model-00007-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:01<00:56, 33.6MB/s] model-00007-of-00008.safetensors: 3%|▎ | 52.4M/1.95G [00:01<00:46, 40.4MB/s] model-00007-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:01<00:37, 50.0MB/s] model-00007-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:01<00:22, 81.7MB/s] model-00007-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:01<00:19, 94.8MB/s] model-00007-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:02<00:13, 131MB/s] model-00007-of-00008.safetensors: 10%|▉ | 189M/1.95G [00:02<00:11, 148MB/s] model-00007-of-00008.safetensors: 11%|█ | 210M/1.95G [00:02<00:11, 157MB/s] model-00007-of-00008.safetensors: 12%|█▏ | 241M/1.95G [00:02<00:09, 180MB/s] model-00007-of-00008.safetensors: 14%|█▍ | 273M/1.95G [00:02<00:08, 203MB/s] model-00007-of-00008.safetensors: 17%|█▋ | 325M/1.95G [00:02<00:06, 270MB/s] model-00007-of-00008.safetensors: 26%|██▋ | 514M/1.95G [00:02<00:02, 634MB/s] model-00007-of-00008.safetensors: 30%|███ | 587M/1.95G [00:03<00:02, 553MB/s] model-00007-of-00008.safetensors: 67%|██████▋ | 1.30G/1.95G [00:03<00:00, 1.84GB/s] model-00007-of-00008.safetensors: 77%|███████▋ | 1.49G/1.95G [00:03<00:00, 881MB/s] model-00007-of-00008.safetensors: 84%|████████▎ | 1.63G/1.95G [00:04<00:00, 754MB/s] model-00007-of-00008.safetensors: 89%|████████▉ | 1.74G/1.95G [00:04<00:00, 733MB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 437MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/872M [00:01<01:45, 8.18MB/s] model-00008-of-00008.safetensors: 3%|▎ | 23.1M/872M [00:01<00:46, 18.3MB/s] model-00008-of-00008.safetensors: 4%|▍ | 33.6M/872M [00:02<00:50, 16.5MB/s] model-00008-of-00008.safetensors: 9%|▊ | 75.5M/872M [00:02<00:16, 48.7MB/s] model-00008-of-00008.safetensors: 11%|█ | 96.5M/872M [00:02<00:11, 65.2MB/s] model-00008-of-00008.safetensors: 16%|█▌ | 138M/872M [00:02<00:06, 111MB/s] model-00008-of-00008.safetensors: 34%|███▍ | 296M/872M [00:02<00:01, 313MB/s] model-00008-of-00008.safetensors: 46%|████▌ | 401M/872M [00:02<00:01, 436MB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 298MB/s]
inv-konstanta-v4-alpha-7b-v8-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, 141MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 4.52MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 44.6MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 60.5MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 10.2MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Downloaded to shared memory in 44.073s
inv-konstanta-v4-alpha-7b-v8-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Reading /tmp/tmpcof4pzh0/model.safetensors.index.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<01:19, 3.66it/s] Profiling: 5%|▌ | 15/291 [00:00<00:05, 50.19it/s] Profiling: 10%|█ | 30/291 [00:00<00:03, 82.58it/s] Profiling: 14%|█▍ | 42/291 [00:00<00:03, 72.16it/s] Profiling: 20%|█▉ | 58/291 [00:00<00:02, 93.69it/s] Profiling: 27%|██▋ | 80/291 [00:00<00:02, 98.39it/s] Profiling: 32%|███▏ | 94/291 [00:01<00:01, 105.11it/s] Profiling: 38%|███▊ | 112/291 [00:01<00:01, 120.52it/s] Profiling: 43%|████▎ | 126/291 [00:01<00:01, 103.14it/s] Profiling: 49%|████▉ | 142/291 [00:01<00:01, 115.22it/s] Profiling: 55%|█████▍ | 160/291 [00:03<00:04, 29.09it/s] Profiling: 62%|██████▏ | 180/291 [00:03<00:02, 41.06it/s] Profiling: 68%|██████▊ | 197/291 [00:04<00:03, 25.01it/s] Profiling: 73%|███████▎ | 211/291 [00:04<00:02, 31.76it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 41.77it/s] Profiling: 86%|████████▌ | 250/291 [00:04<00:00, 55.37it/s] Profiling: 93%|█████████▎| 272/291 [00:04<00:00, 74.58it/s] Profiling: 99%|█████████▉| 288/291 [00:05<00:00, 77.22it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 56.04it/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: quantized model in 15.558s
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Processed model Inv/Konstanta-V4-Alpha-7B in 60.664s
inv-konstanta-v4-alpha-7b-v8-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-v4-alpha-7b-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/tokenizer.model
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/config.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/tokenizer.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v8/mkml_model.tensors
inv-konstanta-v4-alpha-7b-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-konstanta-v4-alpha-7b-v8-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.
inv-konstanta-v4-alpha-7b-v8-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v8-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 9.99MB/s]
inv-konstanta-v4-alpha-7b-v8-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.
inv-konstanta-v4-alpha-7b-v8-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v8-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.78MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 25.2MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 47.0MB/s]
inv-konstanta-v4-alpha-7b-v8-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.
inv-konstanta-v4-alpha-7b-v8-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v8-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:54, 26.5MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:19, 73.5MB/s] pytorch_model.bin: 12%|█▏ | 168M/1.44G [00:00<00:04, 316MB/s] pytorch_model.bin: 28%|██▊ | 409M/1.44G [00:00<00:01, 786MB/s] pytorch_model.bin: 47%|████▋ | 682M/1.44G [00:00<00:00, 1.19GB/s] pytorch_model.bin: 59%|█████▉ | 849M/1.44G [00:01<00:01, 408MB/s] pytorch_model.bin: 67%|██████▋ | 965M/1.44G [00:02<00:01, 419MB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:02<00:00, 617MB/s]
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Saving duration: 0.305s
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.473s
inv-konstanta-v4-alpha-7b-v8-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-v4-alpha-7b-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-v4-alpha-7b-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/config.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/merges.txt
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/vocab.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/tokenizer.json
inv-konstanta-v4-alpha-7b-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v8_reward/reward.tensors
Job inv-konstanta-v4-alpha-7b-v8-mkmlizer completed after 95.9s with status: succeeded
Stopping job with name inv-konstanta-v4-alpha-7b-v8-mkmlizer
Pipeline stage MKMLizer completed in 101.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-v4-alpha-7b-v8
Waiting for inference service inv-konstanta-v4-alpha-7b-v8 to be ready
Inference service inv-konstanta-v4-alpha-7b-v8 ready after 50.31156349182129s
Pipeline stage ISVCDeployer completed in 58.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.0209622383117676s
Received healthy response to inference request in 1.0725467205047607s
Received healthy response to inference request in 0.4235513210296631s
Received healthy response to inference request in 0.3906388282775879s
Received healthy response to inference request in 0.666602373123169s
5 requests
0 failed requests
5th percentile: 0.39722132682800293
10th percentile: 0.40380382537841797
20th percentile: 0.41696882247924805
30th percentile: 0.47216153144836426
40th percentile: 0.5693819522857666
50th percentile: 0.666602373123169
60th percentile: 0.8083463191986083
70th percentile: 0.9500902652740478
80th percentile: 1.0312791347503663
90th percentile: 1.0519129276275634
95th percentile: 1.062229824066162
99th percentile: 1.070483341217041
mean time: 0.7148602962493896
Pipeline stage StressChecker completed in 4.89s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.10s
inv-konstanta-v4-alpha-7b_v8 status is now deployed due to DeploymentManager action
inv-konstanta-v4-alpha-7b_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-konstanta-v4-alpha-7b_v8
Running pipeline stage ISVCDeleter
Checking if service inv-konstanta-v4-alpha-7b-v8 is running
Tearing down inference service inv-konstanta-v4-alpha-7b-v8
Toredown service inv-konstanta-v4-alpha-7b-v8
Pipeline stage ISVCDeleter completed in 3.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v8/config.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v8/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v8/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-konstanta-v4-alpha-7b-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-konstanta-v4-alpha-7b-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
inv-konstanta-v4-alpha-7b_v8 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics