submission_id: inv-kazbek-7b_v1
developer_uid: Inv
status: torndown
model_repo: Inv/Kazbek-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': 16, 'max_output_tokens': 64}
formatter: {'memory_template': 'This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}. Put actions in asterisks.', '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: 2024-03-26T18:13:26+00:00
model_name: inv-kazbek-7b_v1
model_eval_status: success
model_group: Inv/Kazbek-7B
num_battles: 67575
num_wins: 33807
celo_rating: 1157.57
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: inv-kazbek-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: Inv/Kazbek-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-26
win_ratio: 0.5002885682574917
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-kazbek-7b-v1-mkmlizer
Waiting for job on inv-kazbek-7b-v1-mkmlizer to finish
inv-kazbek-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-kazbek-7b-v1-mkmlizer: ║     _____            __           __                                ║
inv-kazbek-7b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
inv-kazbek-7b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
inv-kazbek-7b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
inv-kazbek-7b-v1-mkmlizer: ║       /___/                                                         ║
inv-kazbek-7b-v1-mkmlizer: ║                                                                     ║
inv-kazbek-7b-v1-mkmlizer: ║  Version: 0.6.11                                                    ║
inv-kazbek-7b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
inv-kazbek-7b-v1-mkmlizer: ║                                                                     ║
inv-kazbek-7b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
inv-kazbek-7b-v1-mkmlizer: ║  belonging to:                                                      ║
inv-kazbek-7b-v1-mkmlizer: ║                                                                     ║
inv-kazbek-7b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
inv-kazbek-7b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
inv-kazbek-7b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
inv-kazbek-7b-v1-mkmlizer: ║                                                                     ║
inv-kazbek-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-kazbek-7b-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 10.5MB/s]
inv-kazbek-7b-v1-mkmlizer: 
README.md:   0%|          | 0.00/967 [00:00<?, ?B/s]
README.md: 100%|██████████| 967/967 [00:00<00:00, 5.96MB/s]
inv-kazbek-7b-v1-mkmlizer: 
config.json:   0%|          | 0.00/628 [00:00<?, ?B/s]
config.json: 100%|██████████| 628/628 [00:00<00:00, 3.61MB/s]
inv-kazbek-7b-v1-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/378 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 378/378 [00:00<00:00, 1.99MB/s]
inv-kazbek-7b-v1-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<02:39, 12.3MB/s]
model-00001-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:01<02:49, 11.6MB/s]
model-00001-of-00008.safetensors:   2%|▏         | 31.5M/1.98G [00:01<01:45, 18.4MB/s]
model-00001-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:02<00:56, 34.1MB/s]
model-00001-of-00008.safetensors:   4%|▎         | 73.4M/1.98G [00:02<00:37, 51.3MB/s]
model-00001-of-00008.safetensors:   5%|▌         | 105M/1.98G [00:02<00:22, 83.1MB/s] 
model-00001-of-00008.safetensors:   8%|▊         | 157M/1.98G [00:02<00:12, 150MB/s] 
model-00001-of-00008.safetensors:  14%|█▍        | 283M/1.98G [00:02<00:04, 348MB/s]
model-00001-of-00008.safetensors:  17%|█▋        | 346M/1.98G [00:02<00:05, 282MB/s]
model-00001-of-00008.safetensors:  21%|██        | 409M/1.98G [00:03<00:04, 327MB/s]
model-00001-of-00008.safetensors:  25%|██▍       | 493M/1.98G [00:03<00:03, 420MB/s]
model-00001-of-00008.safetensors:  33%|███▎      | 661M/1.98G [00:03<00:01, 669MB/s]
model-00001-of-00008.safetensors:  55%|█████▍    | 1.08G/1.98G [00:03<00:00, 1.38GB/s]
model-00001-of-00008.safetensors:  63%|██████▎   | 1.25G/1.98G [00:03<00:00, 1.25GB/s]
model-00001-of-00008.safetensors:  74%|███████▎  | 1.46G/1.98G [00:03<00:00, 1.20GB/s]
model-00001-of-00008.safetensors:  81%|████████  | 1.59G/1.98G [00:04<00:00, 750MB/s] 
model-00001-of-00008.safetensors:  86%|████████▌ | 1.70G/1.98G [00:05<00:00, 337MB/s]
model-00001-of-00008.safetensors:  90%|█████████ | 1.78G/1.98G [00:07<00:01, 116MB/s]
model-00001-of-00008.safetensors:  93%|█████████▎| 1.84G/1.98G [00:10<00:01, 73.3MB/s]
model-00001-of-00008.safetensors:  95%|█████████▌| 1.89G/1.98G [00:11<00:01, 68.5MB/s]
model-00001-of-00008.safetensors:  97%|█████████▋| 1.92G/1.98G [00:11<00:00, 70.0MB/s]
model-00001-of-00008.safetensors:  98%|█████████▊| 1.95G/1.98G [00:11<00:00, 74.3MB/s]
model-00001-of-00008.safetensors:  99%|█████████▉| 1.97G/1.98G [00:12<00:00, 77.1MB/s]
model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:12<00:00, 158MB/s] 
inv-kazbek-7b-v1-mkmlizer: 
model-00002-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]
model-00002-of-00008.safetensors:   1%|          | 10.5M/1.98G [00:01<04:42, 6.96MB/s]
model-00002-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:01<02:23, 13.6MB/s]
model-00002-of-00008.safetensors:   2%|▏         | 31.5M/1.98G [00:02<02:01, 16.0MB/s]
model-00002-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:02<00:57, 33.3MB/s]
model-00002-of-00008.safetensors:   4%|▍         | 83.9M/1.98G [00:02<00:29, 64.6MB/s]
model-00002-of-00008.safetensors:   6%|▋         | 126M/1.98G [00:02<00:16, 113MB/s]  
model-00002-of-00008.safetensors:  11%|█         | 220M/1.98G [00:02<00:08, 213MB/s]
model-00002-of-00008.safetensors:  13%|█▎        | 262M/1.98G [00:02<00:07, 237MB/s]
model-00002-of-00008.safetensors:  16%|█▋        | 325M/1.98G [00:03<00:05, 308MB/s]
model-00002-of-00008.safetensors:  20%|██        | 398M/1.98G [00:03<00:04, 394MB/s]
model-00002-of-00008.safetensors:  34%|███▍      | 671M/1.98G [00:03<00:01, 927MB/s]
model-00002-of-00008.safetensors:  58%|█████▊    | 1.14G/1.98G [00:03<00:00, 1.86GB/s]
model-00002-of-00008.safetensors:  69%|██████▉   | 1.37G/1.98G [00:03<00:00, 826MB/s] 
model-00002-of-00008.safetensors:  78%|███████▊  | 1.55G/1.98G [00:04<00:00, 660MB/s]
model-00002-of-00008.safetensors:  98%|█████████▊| 1.95G/1.98G [00:04<00:00, 963MB/s]
model-00002-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:06<00:00, 318MB/s]
inv-kazbek-7b-v1-mkmlizer: 
model-00003-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00003-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:02<06:09, 5.24MB/s]
model-00003-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:02<01:48, 17.7MB/s]
model-00003-of-00008.safetensors:   3%|▎         | 52.4M/1.95G [00:02<01:08, 27.8MB/s]
model-00003-of-00008.safetensors:   8%|▊         | 157M/1.95G [00:02<00:16, 110MB/s]  
model-00003-of-00008.safetensors:  10%|▉         | 189M/1.95G [00:03<00:17, 100MB/s]
model-00003-of-00008.safetensors:  12%|█▏        | 241M/1.95G [00:03<00:12, 137MB/s]
model-00003-of-00008.safetensors:  17%|█▋        | 325M/1.95G [00:03<00:07, 218MB/s]
model-00003-of-00008.safetensors:  30%|███       | 587M/1.95G [00:03<00:02, 570MB/s]
model-00003-of-00008.safetensors:  62%|██████▏   | 1.21G/1.95G [00:03<00:00, 1.53GB/s]
model-00003-of-00008.safetensors:  76%|███████▌  | 1.47G/1.95G [00:04<00:00, 865MB/s] 
model-00003-of-00008.safetensors:  86%|████████▌ | 1.67G/1.95G [00:04<00:00, 868MB/s]
model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 1.06GB/s]
model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 416MB/s] 
inv-kazbek-7b-v1-mkmlizer: 
model-00004-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00004-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:01<04:59, 6.46MB/s]
model-00004-of-00008.safetensors:   1%|          | 21.0M/1.95G [00:01<02:38, 12.2MB/s]
model-00004-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:02<01:34, 20.3MB/s]
model-00004-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:02<01:10, 26.8MB/s]
model-00004-of-00008.safetensors:   4%|▍         | 73.4M/1.95G [00:02<00:30, 60.4MB/s]
model-00004-of-00008.safetensors:   5%|▌         | 105M/1.95G [00:02<00:18, 97.3MB/s] 
model-00004-of-00008.safetensors:   9%|▊         | 168M/1.95G [00:02<00:09, 187MB/s] 
model-00004-of-00008.safetensors:  13%|█▎        | 262M/1.95G [00:02<00:06, 265MB/s]
model-00004-of-00008.safetensors:  16%|█▌        | 304M/1.95G [00:03<00:06, 258MB/s]
model-00004-of-00008.safetensors:  18%|█▊        | 357M/1.95G [00:03<00:05, 307MB/s]
model-00004-of-00008.safetensors:  26%|██▌       | 503M/1.95G [00:03<00:02, 549MB/s]
model-00004-of-00008.safetensors:  54%|█████▍    | 1.06G/1.95G [00:03<00:00, 1.67GB/s]
model-00004-of-00008.safetensors:  67%|██████▋   | 1.30G/1.95G [00:03<00:00, 1.83GB/s]
model-00004-of-00008.safetensors:  78%|███████▊  | 1.52G/1.95G [00:03<00:00, 1.01GB/s]
model-00004-of-00008.safetensors:  87%|████████▋ | 1.68G/1.95G [00:03<00:00, 1.10GB/s]
model-00004-of-00008.safetensors:  95%|█████████▌| 1.85G/1.95G [00:04<00:00, 1.18GB/s]
model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 441MB/s] 
inv-kazbek-7b-v1-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 [00:01<03:14, 9.65MB/s]
model-00005-of-00008.safetensors:   1%|          | 21.0M/1.89G [00:01<02:48, 11.1MB/s]
model-00005-of-00008.safetensors:   2%|▏         | 31.5M/1.89G [00:02<01:43, 18.0MB/s]
model-00005-of-00008.safetensors:   2%|▏         | 41.9M/1.89G [00:02<01:16, 24.2MB/s]
model-00005-of-00008.safetensors:   3%|▎         | 62.9M/1.89G [00:02<00:40, 45.3MB/s]
model-00005-of-00008.safetensors:   7%|▋         | 136M/1.89G [00:02<00:12, 141MB/s]  
model-00005-of-00008.safetensors:  11%|█         | 199M/1.89G [00:02<00:07, 222MB/s]
model-00005-of-00008.safetensors:  14%|█▍        | 273M/1.89G [00:02<00:05, 278MB/s]
model-00005-of-00008.safetensors:  17%|█▋        | 315M/1.89G [00:02<00:06, 253MB/s]
model-00005-of-00008.safetensors:  19%|█▉        | 367M/1.89G [00:03<00:05, 292MB/s]
model-00005-of-00008.safetensors:  25%|██▍       | 472M/1.89G [00:03<00:03, 445MB/s]
model-00005-of-00008.safetensors:  51%|█████     | 965M/1.89G [00:03<00:00, 1.45GB/s]
model-00005-of-00008.safetensors:  67%|██████▋   | 1.27G/1.89G [00:03<00:00, 1.79GB/s]
model-00005-of-00008.safetensors:  79%|███████▉  | 1.49G/1.89G [00:03<00:00, 1.20GB/s]
model-00005-of-00008.safetensors:  88%|████████▊ | 1.67G/1.89G [00:03<00:00, 1.19GB/s]
model-00005-of-00008.safetensors:  99%|█████████▉| 1.88G/1.89G [00:04<00:00, 1.19GB/s]
model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 441MB/s] 
inv-kazbek-7b-v1-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 [00:00<01:07, 28.2MB/s]
model-00006-of-00008.safetensors:   1%|          | 21.0M/1.92G [00:01<02:39, 11.9MB/s]
model-00006-of-00008.safetensors:   2%|▏         | 31.5M/1.92G [00:02<02:34, 12.2MB/s]
model-00006-of-00008.safetensors:   2%|▏         | 41.9M/1.92G [00:02<01:40, 18.7MB/s]
model-00006-of-00008.safetensors:   4%|▍         | 83.9M/1.92G [00:02<00:38, 47.3MB/s]
model-00006-of-00008.safetensors:   6%|▌         | 115M/1.92G [00:02<00:25, 70.9MB/s] 
model-00006-of-00008.safetensors:   9%|▉         | 178M/1.92G [00:03<00:12, 138MB/s] 
model-00006-of-00008.safetensors:  13%|█▎        | 252M/1.92G [00:03<00:07, 224MB/s]
model-00006-of-00008.safetensors:  24%|██▍       | 461M/1.92G [00:03<00:02, 547MB/s]
model-00006-of-00008.safetensors:  60%|█████▉    | 1.15G/1.92G [00:03<00:00, 1.75GB/s]
model-00006-of-00008.safetensors:  73%|███████▎  | 1.41G/1.92G [00:04<00:00, 744MB/s] 
model-00006-of-00008.safetensors:  83%|████████▎ | 1.60G/1.92G [00:04<00:00, 633MB/s]
model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 396MB/s]
inv-kazbek-7b-v1-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 [00:01<04:24, 7.31MB/s]
model-00007-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:01<01:21, 23.4MB/s]
model-00007-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:01<01:06, 28.7MB/s]
model-00007-of-00008.safetensors:   3%|▎         | 62.9M/1.95G [00:02<00:47, 39.7MB/s]
model-00007-of-00008.safetensors:   5%|▍         | 94.4M/1.95G [00:02<00:25, 71.6MB/s]
model-00007-of-00008.safetensors:   6%|▌         | 115M/1.95G [00:02<00:21, 83.8MB/s] 
model-00007-of-00008.safetensors:  10%|█         | 199M/1.95G [00:02<00:08, 202MB/s] 
model-00007-of-00008.safetensors:  13%|█▎        | 252M/1.95G [00:02<00:06, 249MB/s]
model-00007-of-00008.safetensors:  16%|█▌        | 304M/1.95G [00:02<00:05, 280MB/s]
model-00007-of-00008.safetensors:  18%|█▊        | 346M/1.95G [00:02<00:06, 266MB/s]
model-00007-of-00008.safetensors:  20%|█▉        | 388M/1.95G [00:03<00:06, 253MB/s]
model-00007-of-00008.safetensors:  27%|██▋       | 524M/1.95G [00:03<00:03, 467MB/s]
model-00007-of-00008.safetensors:  52%|█████▏    | 1.02G/1.95G [00:03<00:00, 1.43GB/s]
model-00007-of-00008.safetensors:  70%|███████   | 1.36G/1.95G [00:03<00:00, 1.91GB/s]
model-00007-of-00008.safetensors:  82%|████████▏ | 1.60G/1.95G [00:03<00:00, 1.03GB/s]
model-00007-of-00008.safetensors:  92%|█████████▏| 1.79G/1.95G [00:04<00:00, 1.07GB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 450MB/s] 
inv-kazbek-7b-v1-mkmlizer: 
model-00008-of-00008.safetensors:   0%|          | 0.00/872M [00:00<?, ?B/s]
model-00008-of-00008.safetensors:   1%|          | 10.5M/872M [00:00<00:42, 20.4MB/s]
model-00008-of-00008.safetensors:   1%|▏         | 12.6M/872M [00:01<01:27, 9.81MB/s]
model-00008-of-00008.safetensors:   3%|▎         | 23.1M/872M [00:01<01:06, 12.8MB/s]
model-00008-of-00008.safetensors:   7%|▋         | 65.0M/872M [00:01<00:15, 50.8MB/s]
model-00008-of-00008.safetensors:  12%|█▏        | 107M/872M [00:02<00:08, 93.7MB/s] 
model-00008-of-00008.safetensors:  21%|██        | 180M/872M [00:02<00:03, 185MB/s] 
model-00008-of-00008.safetensors:  25%|██▌       | 222M/872M [00:02<00:03, 184MB/s]
model-00008-of-00008.safetensors:  33%|███▎      | 285M/872M [00:02<00:02, 251MB/s]
model-00008-of-00008.safetensors:  83%|████████▎ | 726M/872M [00:02<00:00, 1.03GB/s]
model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 329MB/s] 
inv-kazbek-7b-v1-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, 52.9MB/s]
inv-kazbek-7b-v1-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 2.60MB/s]
inv-kazbek-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, 22.3MB/s]
inv-kazbek-7b-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 47.3MB/s]
inv-kazbek-7b-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:00<00:40,  7.16it/s]
Profiling:   4%|▍         | 11/291 [00:00<00:05, 48.28it/s]
Profiling:   7%|▋         | 20/291 [00:00<00:04, 63.45it/s]
Profiling:  11%|█         | 31/291 [00:00<00:03, 75.39it/s]
Profiling:  13%|█▎        | 39/291 [00:00<00:04, 59.63it/s]
Profiling:  18%|█▊        | 51/291 [00:00<00:03, 73.85it/s]
Profiling:  21%|██        | 61/291 [00:00<00:03, 76.53it/s]
Profiling:  25%|██▌       | 74/291 [00:01<00:02, 89.11it/s]
Profiling:  29%|██▉       | 84/291 [00:01<00:02, 70.02it/s]
Profiling:  33%|███▎      | 97/291 [00:01<00:02, 79.42it/s]
Profiling:  37%|███▋      | 109/291 [00:01<00:02, 88.83it/s]
Profiling:  41%|████      | 119/291 [00:01<00:02, 72.77it/s]
Profiling:  46%|████▋     | 135/291 [00:01<00:01, 90.88it/s]
Profiling:  50%|█████     | 146/291 [00:01<00:01, 93.30it/s]
Profiling:  55%|█████▍    | 160/291 [00:03<00:06, 21.32it/s]
Profiling:  59%|█████▉    | 171/291 [00:03<00:04, 27.29it/s]
Profiling:  62%|██████▏   | 181/291 [00:03<00:03, 33.64it/s]
Profiling:  67%|██████▋   | 195/291 [00:03<00:02, 45.10it/s]
Profiling:  71%|███████   | 206/291 [00:05<00:04, 19.36it/s]
Profiling:  74%|███████▍  | 216/291 [00:05<00:03, 24.26it/s]
Profiling:  78%|███████▊  | 226/291 [00:05<00:02, 30.62it/s]
Profiling:  81%|████████  | 235/291 [00:05<00:01, 33.15it/s]
Profiling:  84%|████████▍ | 245/291 [00:05<00:01, 41.21it/s]
Profiling:  88%|████████▊ | 255/291 [00:05<00:00, 49.61it/s]
Profiling:  91%|█████████ | 265/291 [00:06<00:00, 57.95it/s]
Profiling:  94%|█████████▍| 274/291 [00:06<00:00, 57.21it/s]
Profiling:  98%|█████████▊| 284/291 [00:06<00:00, 63.01it/s]
Profiling: 100%|██████████| 291/291 [00:06<00:00, 45.45it/s]
inv-kazbek-7b-v1-mkmlizer: quantized model in 19.718s
inv-kazbek-7b-v1-mkmlizer: Processed model Inv/Kazbek-7B in 69.514s
inv-kazbek-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
inv-kazbek-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-kazbek-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-kazbek-7b-v1
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-kazbek-7b-v1/config.json
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-kazbek-7b-v1/tokenizer_config.json
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-kazbek-7b-v1/special_tokens_map.json
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-kazbek-7b-v1/tokenizer.model
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-kazbek-7b-v1/tokenizer.json
inv-kazbek-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-kazbek-7b-v1/mkml_model.tensors
inv-kazbek-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-kazbek-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.
inv-kazbek-7b-v1-mkmlizer:   warnings.warn(
inv-kazbek-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, 7.02MB/s]
inv-kazbek-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.
inv-kazbek-7b-v1-mkmlizer:   warnings.warn(
inv-kazbek-7b-v1-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]
inv-kazbek-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, 45.0MB/s]
inv-kazbek-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, 26.2MB/s]
inv-kazbek-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.
inv-kazbek-7b-v1-mkmlizer:   warnings.warn(
inv-kazbek-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-kazbek-7b-v1-mkmlizer: Saving duration: 0.319s
inv-kazbek-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.986s
inv-kazbek-7b-v1-mkmlizer: creating bucket guanaco-reward-models
inv-kazbek-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-kazbek-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-kazbek-7b-v1_reward
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/config.json
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/special_tokens_map.json
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/tokenizer_config.json
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/merges.txt
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/tokenizer.json
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/vocab.json
inv-kazbek-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-kazbek-7b-v1_reward/reward.tensors
Job inv-kazbek-7b-v1-mkmlizer completed after 95.31s with status: succeeded
Stopping job with name inv-kazbek-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service inv-kazbek-7b-v1
Waiting for inference service inv-kazbek-7b-v1 to be ready
Inference service inv-kazbek-7b-v1 ready after 40.37109303474426s
Pipeline stage ISVCDeployer completed in 47.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7224042415618896s
Received healthy response to inference request in 0.8461549282073975s
Received healthy response to inference request in 1.170755386352539s
Received healthy response to inference request in 1.0094738006591797s
Received healthy response to inference request in 1.025399923324585s
5 requests
0 failed requests
5th percentile: 0.8788187026977539
10th percentile: 0.9114824771881104
20th percentile: 0.9768100261688233
30th percentile: 1.0126590251922607
40th percentile: 1.019029474258423
50th percentile: 1.025399923324585
60th percentile: 1.0835421085357666
70th percentile: 1.1416842937469482
80th percentile: 1.2810851573944093
90th percentile: 1.5017446994781494
95th percentile: 1.6120744705200194
99th percentile: 1.7003382873535156
mean time: 1.1548376560211182
Pipeline stage StressChecker completed in 6.68s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.08s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.69s
Running M-Eval for topic stay_in_character
inv-kazbek-7b_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
inv-kazbek-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-kazbek-7b_v1
Running pipeline stage ISVCDeleter
Checking if service inv-kazbek-7b-v1 is running
Tearing down inference service inv-kazbek-7b-v1
Toredown service inv-kazbek-7b-v1
Pipeline stage ISVCDeleter completed in 4.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key inv-kazbek-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key inv-kazbek-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-kazbek-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-kazbek-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-kazbek-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-kazbek-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-kazbek-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-kazbek-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.32s
inv-kazbek-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics