submission_id: wespro-neuralkuno-7b-slerp_v2
developer_uid: WesPro
status: torndown
model_repo: WesPro/NeuralKuno-7B-slerp
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-06T22:00:08+00:00
model_name: wespro-neuralkuno-7b-slerp_v2
model_eval_status: success
model_group: WesPro/NeuralKuno-7B-sle
num_battles: 102007
num_wins: 49966
celo_rating: 1150.71
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: wespro-neuralkuno-7b-slerp_v2
ineligible_reason: propriety_total_count < 800
language_model: WesPro/NeuralKuno-7B-slerp
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-06
win_ratio: 0.4898291293734744
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-neuralkuno-7b-slerp-v2-mkmlizer
Waiting for job on wespro-neuralkuno-7b-slerp-v2-mkmlizer to finish
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║     _____            __           __                                ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║       /___/                                                         ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║                                                                     ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  Version: 0.6.11                                                    ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║                                                                     ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  belonging to:                                                      ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║                                                                     ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ║                                                                     ║
wespro-neuralkuno-7b-slerp-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.2MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
README.md:   0%|          | 0.00/1.91k [00:00<?, ?B/s]
README.md: 100%|██████████| 1.91k/1.91k [00:00<00:00, 25.9MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
config.json:   0%|          | 0.00/640 [00:00<?, ?B/s]
config.json: 100%|██████████| 640/640 [00:00<00:00, 5.76MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/391 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 391/391 [00:00<00:00, 3.30MB/s]
wespro-neuralkuno-7b-slerp-v2-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<01:47, 18.3MB/s]
model-00001-of-00008.safetensors:   2%|▏         | 41.9M/1.98G [00:00<00:25, 77.3MB/s]
model-00001-of-00008.safetensors:  11%|█         | 210M/1.98G [00:00<00:04, 419MB/s]  
model-00001-of-00008.safetensors:  15%|█▍        | 294M/1.98G [00:03<00:21, 77.7MB/s]
model-00001-of-00008.safetensors:  17%|█▋        | 346M/1.98G [00:03<00:19, 84.2MB/s]
model-00001-of-00008.safetensors:  26%|██▌       | 514M/1.98G [00:03<00:08, 172MB/s] 
model-00001-of-00008.safetensors:  65%|██████▌   | 1.29G/1.98G [00:03<00:00, 724MB/s]
model-00001-of-00008.safetensors:  81%|████████  | 1.60G/1.98G [00:04<00:00, 667MB/s]
model-00001-of-00008.safetensors:  93%|█████████▎| 1.84G/1.98G [00:04<00:00, 781MB/s]
model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 418MB/s]
wespro-neuralkuno-7b-slerp-v2-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 [00:00<01:26, 22.4MB/s]
model-00002-of-00008.safetensors:   3%|▎         | 62.9M/1.95G [00:00<00:14, 133MB/s] 
model-00002-of-00008.safetensors:   5%|▍         | 94.4M/1.95G [00:00<00:11, 155MB/s]
model-00002-of-00008.safetensors:   6%|▋         | 126M/1.95G [00:02<00:51, 35.0MB/s]
model-00002-of-00008.safetensors:   8%|▊         | 147M/1.95G [00:02<00:40, 44.9MB/s]
model-00002-of-00008.safetensors:  20%|█▉        | 388M/1.95G [00:03<00:07, 217MB/s] 
model-00002-of-00008.safetensors:  24%|██▎       | 461M/1.95G [00:03<00:06, 234MB/s]
model-00002-of-00008.safetensors:  49%|████▉     | 954M/1.95G [00:03<00:01, 733MB/s]
model-00002-of-00008.safetensors:  61%|██████    | 1.18G/1.95G [00:03<00:00, 864MB/s]
model-00002-of-00008.safetensors:  70%|███████   | 1.36G/1.95G [00:04<00:01, 510MB/s]
model-00002-of-00008.safetensors:  81%|████████  | 1.58G/1.95G [00:04<00:00, 668MB/s]
model-00002-of-00008.safetensors:  89%|████████▉ | 1.74G/1.95G [00:04<00:00, 580MB/s]
model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 403MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
model-00003-of-00008.safetensors:   0%|          | 0.00/1.97G [00:00<?, ?B/s]
model-00003-of-00008.safetensors:   1%|          | 10.5M/1.97G [00:00<01:16, 25.6MB/s]
model-00003-of-00008.safetensors:   1%|          | 21.0M/1.97G [00:00<00:47, 40.8MB/s]
model-00003-of-00008.safetensors:   4%|▍         | 83.9M/1.97G [00:00<00:12, 156MB/s] 
model-00003-of-00008.safetensors:   6%|▌         | 115M/1.97G [00:00<00:10, 180MB/s] 
model-00003-of-00008.safetensors:  10%|█         | 199M/1.97G [00:00<00:05, 334MB/s]
model-00003-of-00008.safetensors:  58%|█████▊    | 1.14G/1.97G [00:01<00:00, 2.59GB/s]
model-00003-of-00008.safetensors:  76%|███████▌  | 1.49G/1.97G [00:01<00:00, 1.74GB/s]
model-00003-of-00008.safetensors:  89%|████████▉ | 1.75G/1.97G [00:01<00:00, 1.74GB/s]
model-00003-of-00008.safetensors: 100%|█████████▉| 1.97G/1.97G [00:01<00:00, 1.23GB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
model-00004-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]
model-00004-of-00008.safetensors:   1%|          | 10.5M/1.98G [00:00<01:13, 26.9MB/s]
model-00004-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:00<00:16, 115MB/s] 
model-00004-of-00008.safetensors:   5%|▍         | 94.4M/1.98G [00:00<00:15, 118MB/s]
model-00004-of-00008.safetensors:   6%|▌         | 115M/1.98G [00:02<00:45, 40.7MB/s]
model-00004-of-00008.safetensors:   7%|▋         | 136M/1.98G [00:02<00:36, 51.1MB/s]
model-00004-of-00008.safetensors:   9%|▉         | 178M/1.98G [00:02<00:21, 83.8MB/s]
model-00004-of-00008.safetensors:  10%|█         | 199M/1.98G [00:02<00:18, 96.1MB/s]
model-00004-of-00008.safetensors:  11%|█         | 220M/1.98G [00:02<00:16, 110MB/s] 
model-00004-of-00008.safetensors:  14%|█▍        | 273M/1.98G [00:02<00:09, 171MB/s]
model-00004-of-00008.safetensors:  15%|█▌        | 304M/1.98G [00:03<00:10, 156MB/s]
model-00004-of-00008.safetensors:  30%|███       | 598M/1.98G [00:03<00:02, 633MB/s]
model-00004-of-00008.safetensors:  59%|█████▉    | 1.17G/1.98G [00:03<00:00, 1.32GB/s]
model-00004-of-00008.safetensors:  67%|██████▋   | 1.33G/1.98G [00:03<00:00, 932MB/s] 
model-00004-of-00008.safetensors:  74%|███████▎  | 1.46G/1.98G [00:03<00:00, 896MB/s]
model-00004-of-00008.safetensors:  79%|███████▉  | 1.57G/1.98G [00:04<00:00, 928MB/s]
model-00004-of-00008.safetensors:  85%|████████▌ | 1.69G/1.98G [00:04<00:00, 801MB/s]
model-00004-of-00008.safetensors:  90%|████████▉ | 1.78G/1.98G [00:04<00:00, 774MB/s]
model-00004-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 443MB/s]
wespro-neuralkuno-7b-slerp-v2-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<01:05, 29.1MB/s]
model-00006-of-00008.safetensors:   2%|▏         | 41.9M/1.92G [00:00<00:17, 109MB/s] 
model-00006-of-00008.safetensors:   9%|▉         | 178M/1.92G [00:01<00:11, 158MB/s] 
model-00006-of-00008.safetensors:  10%|█         | 199M/1.92G [00:02<00:19, 90.1MB/s]
model-00006-of-00008.safetensors:  11%|█▏        | 220M/1.92G [00:02<00:23, 71.6MB/s]
model-00006-of-00008.safetensors:  14%|█▍        | 273M/1.92G [00:02<00:15, 104MB/s] 
model-00006-of-00008.safetensors:  16%|█▌        | 304M/1.92G [00:02<00:13, 120MB/s]
model-00006-of-00008.safetensors:  20%|██        | 388M/1.92G [00:02<00:07, 203MB/s]
model-00006-of-00008.safetensors:  26%|██▌       | 493M/1.92G [00:03<00:04, 326MB/s]
model-00006-of-00008.safetensors:  35%|███▍      | 671M/1.92G [00:03<00:02, 566MB/s]
model-00006-of-00008.safetensors:  47%|████▋     | 902M/1.92G [00:03<00:01, 899MB/s]
model-00006-of-00008.safetensors:  63%|██████▎   | 1.21G/1.92G [00:03<00:00, 1.25GB/s]
model-00006-of-00008.safetensors:  71%|███████   | 1.37G/1.92G [00:04<00:01, 433MB/s] 
model-00006-of-00008.safetensors:  77%|███████▋  | 1.48G/1.92G [00:04<00:00, 466MB/s]
model-00006-of-00008.safetensors:  83%|████████▎ | 1.59G/1.92G [00:04<00:00, 529MB/s]
model-00006-of-00008.safetensors:  90%|█████████ | 1.73G/1.92G [00:04<00:00, 652MB/s]
model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:04<00:00, 388MB/s]
wespro-neuralkuno-7b-slerp-v2-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<00:44, 43.3MB/s]
model-00007-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:00<00:13, 136MB/s] 
model-00007-of-00008.safetensors:   6%|▌         | 115M/1.95G [00:00<00:05, 308MB/s] 
model-00007-of-00008.safetensors:  14%|█▍        | 273M/1.95G [00:00<00:02, 676MB/s]
model-00007-of-00008.safetensors:  18%|█▊        | 357M/1.95G [00:02<00:14, 110MB/s]
model-00007-of-00008.safetensors:  22%|██▏       | 430M/1.95G [00:02<00:10, 147MB/s]
model-00007-of-00008.safetensors:  27%|██▋       | 524M/1.95G [00:02<00:06, 209MB/s]
model-00007-of-00008.safetensors:  42%|████▏     | 818M/1.95G [00:02<00:02, 475MB/s]
model-00007-of-00008.safetensors:  53%|█████▎    | 1.04G/1.95G [00:03<00:01, 677MB/s]
model-00007-of-00008.safetensors:  61%|██████    | 1.18G/1.95G [00:03<00:01, 736MB/s]
model-00007-of-00008.safetensors:  68%|██████▊   | 1.32G/1.95G [00:03<00:00, 806MB/s]
model-00007-of-00008.safetensors:  81%|████████  | 1.57G/1.95G [00:03<00:00, 996MB/s]
model-00007-of-00008.safetensors:  88%|████████▊ | 1.71G/1.95G [00:03<00:00, 611MB/s]
model-00007-of-00008.safetensors:  99%|█████████▉| 1.94G/1.95G [00:04<00:00, 839MB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 476MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
model-00008-of-00008.safetensors:   0%|          | 0.00/789M [00:00<?, ?B/s]
model-00008-of-00008.safetensors:   1%|▏         | 10.5M/789M [00:00<00:28, 27.0MB/s]
model-00008-of-00008.safetensors:  16%|█▌        | 128M/789M [00:00<00:01, 336MB/s]  
model-00008-of-00008.safetensors:  41%|████▏     | 327M/789M [00:00<00:00, 795MB/s]
model-00008-of-00008.safetensors:  59%|█████▉    | 464M/789M [00:01<00:00, 344MB/s]
model-00008-of-00008.safetensors:  80%|████████  | 631M/789M [00:01<00:00, 513MB/s]
model-00008-of-00008.safetensors: 100%|█████████▉| 789M/789M [00:01<00:00, 540MB/s]
wespro-neuralkuno-7b-slerp-v2-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, 117MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/414 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 5.87MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 21.5MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 62.2MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/967 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 8.10MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Downloaded to shared memory in 35.807s
wespro-neuralkuno-7b-slerp-v2-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Saving mkml model at /dev/shm/model_cache
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Reading /tmp/tmpgra3uyh3/model.safetensors.index.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:00<00:52,  5.54it/s]
Profiling:   5%|▍         | 14/291 [00:00<00:04, 59.86it/s]
Profiling:  12%|█▏        | 35/291 [00:00<00:02, 115.96it/s]
Profiling:  17%|█▋        | 49/291 [00:00<00:02, 93.71it/s] 
Profiling:  23%|██▎       | 68/291 [00:00<00:01, 119.15it/s]
Profiling:  28%|██▊       | 82/291 [00:01<00:06, 30.34it/s] 
Profiling:  35%|███▍      | 101/291 [00:02<00:04, 44.31it/s]
Profiling:  41%|████      | 120/291 [00:02<00:03, 56.52it/s]
Profiling:  46%|████▌     | 134/291 [00:02<00:02, 66.92it/s]
Profiling:  53%|█████▎    | 153/291 [00:02<00:01, 85.93it/s]
Profiling:  58%|█████▊    | 168/291 [00:02<00:01, 89.77it/s]
Profiling:  65%|██████▍   | 188/291 [00:02<00:00, 108.73it/s]
Profiling:  70%|██████▉   | 203/291 [00:03<00:02, 32.98it/s] 
Profiling:  75%|███████▌  | 219/291 [00:04<00:01, 42.63it/s]
Profiling:  81%|████████  | 235/291 [00:04<00:01, 51.56it/s]
Profiling:  85%|████████▍ | 247/291 [00:04<00:00, 59.72it/s]
Profiling:  91%|█████████ | 265/291 [00:04<00:00, 75.57it/s]
Profiling:  96%|█████████▌| 278/291 [00:04<00:00, 82.71it/s]
Profiling: 100%|██████████| 291/291 [00:04<00:00, 62.51it/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Processed model WesPro/NeuralKuno-7B-slerp in 51.002s
wespro-neuralkuno-7b-slerp-v2-mkmlizer: creating bucket guanaco-mkml-models
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-neuralkuno-7b-slerp-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/tokenizer_config.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/config.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/tokenizer.model
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/special_tokens_map.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/tokenizer.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/wespro-neuralkuno-7b-slerp-v2/mkml_model.tensors
wespro-neuralkuno-7b-slerp-v2-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.
wespro-neuralkuno-7b-slerp-v2-mkmlizer:   warnings.warn(
wespro-neuralkuno-7b-slerp-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.5MB/s]
wespro-neuralkuno-7b-slerp-v2-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.
wespro-neuralkuno-7b-slerp-v2-mkmlizer:   warnings.warn(
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.76MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 13.0MB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.5MB/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 17.4MB/s]
wespro-neuralkuno-7b-slerp-v2-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.
wespro-neuralkuno-7b-slerp-v2-mkmlizer:   warnings.warn(
wespro-neuralkuno-7b-slerp-v2-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:10, 140MB/s]
pytorch_model.bin:   3%|▎         | 41.9M/1.44G [00:00<00:08, 163MB/s]
pytorch_model.bin:   9%|▉         | 136M/1.44G [00:00<00:03, 406MB/s] 
pytorch_model.bin:  14%|█▍        | 199M/1.44G [00:00<00:02, 478MB/s]
pytorch_model.bin:  17%|█▋        | 252M/1.44G [00:00<00:02, 486MB/s]
pytorch_model.bin:  21%|██        | 304M/1.44G [00:01<00:04, 238MB/s]
pytorch_model.bin:  24%|██▍       | 346M/1.44G [00:01<00:04, 264MB/s]
pytorch_model.bin:  39%|███▉      | 566M/1.44G [00:01<00:01, 640MB/s]
pytorch_model.bin:  89%|████████▉ | 1.29G/1.44G [00:01<00:00, 2.07GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.00GB/s]
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Saving duration: 0.229s
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.104s
wespro-neuralkuno-7b-slerp-v2-mkmlizer: creating bucket guanaco-reward-models
wespro-neuralkuno-7b-slerp-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-neuralkuno-7b-slerp-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/config.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/special_tokens_map.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/tokenizer_config.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/merges.txt
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/vocab.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/tokenizer.json
wespro-neuralkuno-7b-slerp-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-neuralkuno-7b-slerp-v2_reward/reward.tensors
Job wespro-neuralkuno-7b-slerp-v2-mkmlizer completed after 80.66s with status: succeeded
Stopping job with name wespro-neuralkuno-7b-slerp-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service wespro-neuralkuno-7b-slerp-v2
Waiting for inference service wespro-neuralkuno-7b-slerp-v2 to be ready
Inference service wespro-neuralkuno-7b-slerp-v2 ready after 40.23852849006653s
Pipeline stage ISVCDeployer completed in 47.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5569868087768555s
Received healthy response to inference request in 0.9182953834533691s
Received healthy response to inference request in 1.7459499835968018s
Received healthy response to inference request in 1.6799743175506592s
Received healthy response to inference request in 0.6905117034912109s
5 requests
0 failed requests
5th percentile: 0.7360684394836425
10th percentile: 0.7816251754760742
20th percentile: 0.8727386474609375
30th percentile: 1.0460336685180665
40th percentile: 1.301510238647461
50th percentile: 1.5569868087768555
60th percentile: 1.606181812286377
70th percentile: 1.6553768157958983
80th percentile: 1.6931694507598878
90th percentile: 1.7195597171783448
95th percentile: 1.7327548503875732
99th percentile: 1.743310956954956
mean time: 1.3183436393737793
Pipeline stage StressChecker completed in 7.39s
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
wespro-neuralkuno-7b-slerp_v2 status is now deployed due to DeploymentManager action
wespro-neuralkuno-7b-slerp_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-neuralkuno-7b-slerp_v2
Running pipeline stage ISVCDeleter
Checking if service wespro-neuralkuno-7b-slerp-v2 is running
Tearing down inference service wespro-neuralkuno-7b-slerp-v2
Toredown service wespro-neuralkuno-7b-slerp-v2
Pipeline stage ISVCDeleter completed in 3.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-neuralkuno-7b-slerp-v2/config.json from bucket guanaco-mkml-models
Deleting key wespro-neuralkuno-7b-slerp-v2/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key wespro-neuralkuno-7b-slerp-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-neuralkuno-7b-slerp-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-neuralkuno-7b-slerp-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key wespro-neuralkuno-7b-slerp-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-neuralkuno-7b-slerp-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.24s
wespro-neuralkuno-7b-slerp_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics