submission_id: saishf-west-hermes-7b_v1
developer_uid: saishf
status: torndown
model_repo: saishf/West-Hermes-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': 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: 2024-03-26T12:42:13+00:00
model_name: saishf-west-hermes-7b_v1
model_eval_status: success
model_group: saishf/West-Hermes-7B
num_battles: 67296
num_wins: 32336
celo_rating: 1143.77
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: saishf-west-hermes-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: saishf/West-Hermes-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-26
win_ratio: 0.48050404184498335
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-west-hermes-7b-v1-mkmlizer
Waiting for job on saishf-west-hermes-7b-v1-mkmlizer to finish
saishf-west-hermes-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-west-hermes-7b-v1-mkmlizer: ║     _____            __           __                                ║
saishf-west-hermes-7b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
saishf-west-hermes-7b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
saishf-west-hermes-7b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
saishf-west-hermes-7b-v1-mkmlizer: ║       /___/                                                         ║
saishf-west-hermes-7b-v1-mkmlizer: ║                                                                     ║
saishf-west-hermes-7b-v1-mkmlizer: ║  Version: 0.6.11                                                    ║
saishf-west-hermes-7b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
saishf-west-hermes-7b-v1-mkmlizer: ║                                                                     ║
saishf-west-hermes-7b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
saishf-west-hermes-7b-v1-mkmlizer: ║  belonging to:                                                      ║
saishf-west-hermes-7b-v1-mkmlizer: ║                                                                     ║
saishf-west-hermes-7b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
saishf-west-hermes-7b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
saishf-west-hermes-7b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
saishf-west-hermes-7b-v1-mkmlizer: ║                                                                     ║
saishf-west-hermes-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-west-hermes-7b-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.63k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.63k/1.63k [00:00<00:00, 20.7MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
README.md:   0%|          | 0.00/4.50k [00:00<?, ?B/s]
README.md: 100%|██████████| 4.50k/4.50k [00:00<00:00, 27.7MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
config.json:   0%|          | 0.00/642 [00:00<?, ?B/s]
config.json: 100%|██████████| 642/642 [00:00<00:00, 7.16MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/389 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 389/389 [00:00<00:00, 2.88MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00001-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]
model-00001-of-00008.safetensors:   1%|          | 10.5M/1.95G [00:00<01:26, 22.4MB/s]
model-00001-of-00008.safetensors:   1%|          | 21.0M/1.95G [00:01<02:25, 13.2MB/s]
model-00001-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:01<01:30, 21.2MB/s]
model-00001-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:02<01:46, 18.0MB/s]
model-00001-of-00008.safetensors:   3%|▎         | 52.4M/1.95G [00:02<01:26, 21.9MB/s]
model-00001-of-00008.safetensors:   4%|▍         | 73.4M/1.95G [00:02<00:47, 39.4MB/s]
model-00001-of-00008.safetensors:   8%|▊         | 147M/1.95G [00:02<00:14, 120MB/s]  
model-00001-of-00008.safetensors:  15%|█▌        | 294M/1.95G [00:02<00:05, 311MB/s]
model-00001-of-00008.safetensors:  18%|█▊        | 357M/1.95G [00:03<00:04, 334MB/s]
model-00001-of-00008.safetensors:  23%|██▎       | 440M/1.95G [00:03<00:03, 403MB/s]
model-00001-of-00008.safetensors:  43%|████▎     | 828M/1.95G [00:03<00:01, 1.08GB/s]
model-00001-of-00008.safetensors:  62%|██████▏   | 1.21G/1.95G [00:03<00:00, 1.65GB/s]
model-00001-of-00008.safetensors:  73%|███████▎  | 1.43G/1.95G [00:03<00:00, 1.14GB/s]
model-00001-of-00008.safetensors:  82%|████████▏ | 1.60G/1.95G [00:03<00:00, 1.09GB/s]
model-00001-of-00008.safetensors:  90%|█████████ | 1.76G/1.95G [00:04<00:00, 875MB/s] 
model-00001-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 441MB/s]
saishf-west-hermes-7b-v1-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<05:47, 5.57MB/s]
model-00002-of-00008.safetensors:   1%|          | 21.0M/1.95G [00:02<02:55, 11.0MB/s]
model-00002-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:02<01:49, 17.5MB/s]
model-00002-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:02<01:32, 20.5MB/s]
model-00002-of-00008.safetensors:   5%|▍         | 94.4M/1.95G [00:02<00:26, 70.6MB/s]
model-00002-of-00008.safetensors:   9%|▉         | 178M/1.95G [00:02<00:10, 165MB/s]  
model-00002-of-00008.safetensors:  17%|█▋        | 336M/1.95G [00:03<00:04, 375MB/s]
model-00002-of-00008.safetensors:  26%|██▌       | 503M/1.95G [00:03<00:02, 504MB/s]
model-00002-of-00008.safetensors:  33%|███▎      | 640M/1.95G [00:03<00:02, 636MB/s]
model-00002-of-00008.safetensors:  55%|█████▍    | 1.07G/1.95G [00:03<00:00, 914MB/s]
model-00002-of-00008.safetensors:  60%|██████    | 1.17G/1.95G [00:03<00:01, 729MB/s]
model-00002-of-00008.safetensors:  65%|██████▍   | 1.26G/1.95G [00:04<00:01, 523MB/s]
model-00002-of-00008.safetensors:  68%|██████▊   | 1.33G/1.95G [00:04<00:01, 513MB/s]
model-00002-of-00008.safetensors:  71%|███████▏  | 1.39G/1.95G [00:04<00:01, 491MB/s]
model-00002-of-00008.safetensors:  75%|███████▍  | 1.45G/1.95G [00:04<00:01, 490MB/s]
model-00002-of-00008.safetensors:  82%|████████▏ | 1.59G/1.95G [00:04<00:00, 647MB/s]
model-00002-of-00008.safetensors:  88%|████████▊ | 1.72G/1.95G [00:05<00:00, 749MB/s]
model-00002-of-00008.safetensors:  97%|█████████▋| 1.88G/1.95G [00:05<00:00, 955MB/s]
model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:05<00:00, 375MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00003-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]
model-00003-of-00008.safetensors:   1%|          | 10.5M/1.89G [00:01<05:03, 6.19MB/s]
model-00003-of-00008.safetensors:   2%|▏         | 31.5M/1.89G [00:01<01:25, 21.7MB/s]
model-00003-of-00008.safetensors:   3%|▎         | 62.9M/1.89G [00:01<00:38, 47.8MB/s]
model-00003-of-00008.safetensors:   8%|▊         | 157M/1.89G [00:02<00:11, 153MB/s]  
model-00003-of-00008.safetensors:  17%|█▋        | 315M/1.89G [00:02<00:04, 353MB/s]
model-00003-of-00008.safetensors:  21%|██        | 398M/1.89G [00:02<00:03, 382MB/s]
model-00003-of-00008.safetensors:  41%|████      | 776M/1.89G [00:02<00:01, 975MB/s]
model-00003-of-00008.safetensors:  63%|██████▎   | 1.20G/1.89G [00:02<00:00, 1.54GB/s]
model-00003-of-00008.safetensors:  76%|███████▌  | 1.43G/1.89G [00:03<00:00, 844MB/s] 
model-00003-of-00008.safetensors:  84%|████████▍ | 1.60G/1.89G [00:03<00:00, 947MB/s]
model-00003-of-00008.safetensors:  99%|█████████▉| 1.87G/1.89G [00:03<00:00, 1.22GB/s]
model-00003-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 552MB/s] 
saishf-west-hermes-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 [00:00<01:43, 18.7MB/s]
model-00004-of-00008.safetensors:   1%|          | 21.0M/1.95G [00:02<04:46, 6.71MB/s]
model-00004-of-00008.safetensors:   2%|▏         | 41.9M/1.95G [00:02<01:52, 16.9MB/s]
model-00004-of-00008.safetensors:   8%|▊         | 147M/1.95G [00:03<00:20, 86.2MB/s] 
model-00004-of-00008.safetensors:  14%|█▍        | 273M/1.95G [00:03<00:08, 189MB/s] 
model-00004-of-00008.safetensors:  18%|█▊        | 357M/1.95G [00:03<00:06, 236MB/s]
model-00004-of-00008.safetensors:  44%|████▍     | 860M/1.95G [00:03<00:01, 836MB/s]
model-00004-of-00008.safetensors:  55%|█████▌    | 1.08G/1.95G [00:03<00:00, 1.00GB/s]
model-00004-of-00008.safetensors:  66%|██████▌   | 1.29G/1.95G [00:04<00:00, 666MB/s] 
model-00004-of-00008.safetensors:  74%|███████▎  | 1.43G/1.95G [00:04<00:00, 691MB/s]
model-00004-of-00008.safetensors:  80%|████████  | 1.56G/1.95G [00:04<00:00, 571MB/s]
model-00004-of-00008.safetensors:  87%|████████▋ | 1.69G/1.95G [00:04<00:00, 656MB/s]
model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 397MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00005-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]
model-00005-of-00008.safetensors:   1%|          | 10.5M/1.98G [00:01<05:01, 6.53MB/s]
model-00005-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:01<02:23, 13.7MB/s]
model-00005-of-00008.safetensors:   2%|▏         | 31.5M/1.98G [00:02<01:55, 16.9MB/s]
model-00005-of-00008.safetensors:   2%|▏         | 41.9M/1.98G [00:02<01:42, 18.8MB/s]
model-00005-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:02<01:16, 25.3MB/s]
model-00005-of-00008.safetensors:   3%|▎         | 62.9M/1.98G [00:02<00:58, 32.9MB/s]
model-00005-of-00008.safetensors:   6%|▋         | 126M/1.98G [00:03<00:16, 109MB/s]  
model-00005-of-00008.safetensors:  14%|█▍        | 273M/1.98G [00:03<00:05, 319MB/s]
model-00005-of-00008.safetensors:  17%|█▋        | 336M/1.98G [00:03<00:05, 316MB/s]
model-00005-of-00008.safetensors:  23%|██▎       | 451M/1.98G [00:03<00:03, 465MB/s]
model-00005-of-00008.safetensors:  59%|█████▉    | 1.17G/1.98G [00:03<00:00, 1.72GB/s]
model-00005-of-00008.safetensors:  70%|███████   | 1.39G/1.98G [00:04<00:00, 932MB/s] 
model-00005-of-00008.safetensors:  79%|███████▉  | 1.56G/1.98G [00:04<00:00, 660MB/s]
model-00005-of-00008.safetensors:  85%|████████▌ | 1.69G/1.98G [00:04<00:00, 675MB/s]
model-00005-of-00008.safetensors:  94%|█████████▍| 1.86G/1.98G [00:04<00:00, 815MB/s]
model-00005-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 394MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00006-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]
model-00006-of-00008.safetensors:   1%|          | 10.5M/1.89G [00:01<05:22, 5.82MB/s]
model-00006-of-00008.safetensors:   3%|▎         | 52.4M/1.89G [00:01<00:53, 34.1MB/s]
model-00006-of-00008.safetensors:   8%|▊         | 147M/1.89G [00:02<00:15, 116MB/s]  
model-00006-of-00008.safetensors:  13%|█▎        | 252M/1.89G [00:02<00:07, 219MB/s]
model-00006-of-00008.safetensors:  17%|█▋        | 325M/1.89G [00:02<00:06, 235MB/s]
model-00006-of-00008.safetensors:  23%|██▎       | 430M/1.89G [00:02<00:04, 346MB/s]
model-00006-of-00008.safetensors:  34%|███▍      | 650M/1.89G [00:02<00:01, 638MB/s]
model-00006-of-00008.safetensors:  63%|██████▎   | 1.20G/1.89G [00:02<00:00, 1.53GB/s]
model-00006-of-00008.safetensors:  77%|███████▋  | 1.45G/1.89G [00:03<00:00, 967MB/s] 
model-00006-of-00008.safetensors:  87%|████████▋ | 1.64G/1.89G [00:03<00:00, 940MB/s]
model-00006-of-00008.safetensors:  95%|█████████▌| 1.80G/1.89G [00:03<00:00, 993MB/s]
model-00006-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 513MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00007-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]
model-00007-of-00008.safetensors:   1%|          | 10.5M/1.98G [00:02<07:42, 4.26MB/s]
model-00007-of-00008.safetensors:   2%|▏         | 31.5M/1.98G [00:02<02:05, 15.5MB/s]
model-00007-of-00008.safetensors:   3%|▎         | 52.4M/1.98G [00:02<01:05, 29.3MB/s]
model-00007-of-00008.safetensors:  11%|█         | 210M/1.98G [00:02<00:10, 172MB/s]  
model-00007-of-00008.safetensors:  18%|█▊        | 357M/1.98G [00:02<00:05, 318MB/s]
model-00007-of-00008.safetensors:  23%|██▎       | 451M/1.98G [00:03<00:03, 385MB/s]
model-00007-of-00008.safetensors:  51%|█████     | 1.01G/1.98G [00:03<00:00, 1.06GB/s]
model-00007-of-00008.safetensors:  59%|█████▉    | 1.16G/1.98G [00:03<00:01, 654MB/s] 
model-00007-of-00008.safetensors:  65%|██████▍   | 1.28G/1.98G [00:04<00:01, 573MB/s]
model-00007-of-00008.safetensors:  72%|███████▏  | 1.42G/1.98G [00:04<00:00, 668MB/s]
model-00007-of-00008.safetensors:  83%|████████▎ | 1.64G/1.98G [00:04<00:00, 905MB/s]
model-00007-of-00008.safetensors:  90%|█████████ | 1.79G/1.98G [00:04<00:00, 905MB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 379MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
model-00008-of-00008.safetensors:   0%|          | 0.00/906M [00:00<?, ?B/s]
model-00008-of-00008.safetensors:   1%|          | 10.5M/906M [00:01<01:43, 8.66MB/s]
model-00008-of-00008.safetensors:   3%|▎         | 25.2M/906M [00:01<00:44, 20.0MB/s]
model-00008-of-00008.safetensors:   4%|▍         | 35.7M/906M [00:01<00:36, 23.9MB/s]
model-00008-of-00008.safetensors:   5%|▌         | 46.2M/906M [00:01<00:26, 32.0MB/s]
model-00008-of-00008.safetensors:   9%|▊         | 77.6M/906M [00:02<00:11, 70.4MB/s]
model-00008-of-00008.safetensors:  13%|█▎        | 120M/906M [00:02<00:06, 120MB/s]  
model-00008-of-00008.safetensors:  31%|███       | 277M/906M [00:02<00:01, 362MB/s]
model-00008-of-00008.safetensors:  41%|████      | 371M/906M [00:02<00:01, 471MB/s]
model-00008-of-00008.safetensors:  88%|████████▊ | 801M/906M [00:02<00:00, 1.30GB/s]
model-00008-of-00008.safetensors: 100%|█████████▉| 906M/906M [00:05<00:00, 173MB/s] 
saishf-west-hermes-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, 149MB/s]
saishf-west-hermes-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, 6.76MB/s]
saishf-west-hermes-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, 30.9MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 64.1MB/s]
saishf-west-hermes-7b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/967 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 16.0MB/s]
saishf-west-hermes-7b-v1-mkmlizer: Downloaded to shared memory in 39.934s
saishf-west-hermes-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-west-hermes-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
saishf-west-hermes-7b-v1-mkmlizer: Reading /tmp/tmpu7izb1yv/model.safetensors.index.json
saishf-west-hermes-7b-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:00<00:35,  8.28it/s]
Profiling:   5%|▌         | 15/291 [00:00<00:03, 77.61it/s]
Profiling:   9%|▉         | 26/291 [00:00<00:03, 86.28it/s]
Profiling:  14%|█▍        | 41/291 [00:00<00:03, 76.28it/s]
Profiling:  19%|█▉        | 56/291 [00:00<00:02, 93.45it/s]
Profiling:  23%|██▎       | 67/291 [00:00<00:02, 93.52it/s]
Profiling:  29%|██▊       | 83/291 [00:00<00:01, 107.89it/s]
Profiling:  33%|███▎      | 95/291 [00:02<00:08, 24.28it/s] 
Profiling:  36%|███▋      | 106/291 [00:02<00:06, 30.59it/s]
Profiling:  41%|████      | 118/291 [00:02<00:04, 37.34it/s]
Profiling:  46%|████▌     | 133/291 [00:02<00:03, 50.30it/s]
Profiling:  49%|████▉     | 144/291 [00:02<00:02, 57.92it/s]
Profiling:  55%|█████▍    | 160/291 [00:02<00:01, 74.19it/s]
Profiling:  59%|█████▉    | 172/291 [00:03<00:01, 69.06it/s]
Profiling:  64%|██████▍   | 187/291 [00:03<00:01, 82.20it/s]
Profiling:  68%|██████▊   | 198/291 [00:03<00:01, 85.48it/s]
Profiling:  72%|███████▏  | 209/291 [00:04<00:03, 22.66it/s]
Profiling:  76%|███████▌  | 221/291 [00:04<00:02, 29.53it/s]
Profiling:  80%|████████  | 234/291 [00:05<00:01, 38.80it/s]
Profiling:  84%|████████▍ | 244/291 [00:05<00:01, 43.10it/s]
Profiling:  88%|████████▊ | 256/291 [00:05<00:00, 52.52it/s]
Profiling:  92%|█████████▏| 269/291 [00:05<00:00, 64.51it/s]
Profiling:  96%|█████████▌| 280/291 [00:05<00:00, 58.71it/s]
Profiling: 100%|██████████| 291/291 [00:05<00:00, 50.48it/s]
saishf-west-hermes-7b-v1-mkmlizer: quantized model in 17.082s
saishf-west-hermes-7b-v1-mkmlizer: Processed model saishf/West-Hermes-7B in 57.928s
saishf-west-hermes-7b-v1-mkmlizer: creating bucket guanaco-mkml-models
saishf-west-hermes-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-west-hermes-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-west-hermes-7b-v1
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/config.json
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/special_tokens_map.json
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/tokenizer.model
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/tokenizer_config.json
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/tokenizer.json
saishf-west-hermes-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/saishf-west-hermes-7b-v1/mkml_model.tensors
saishf-west-hermes-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-west-hermes-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.
saishf-west-hermes-7b-v1-mkmlizer:   warnings.warn(
saishf-west-hermes-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, 9.41MB/s]
saishf-west-hermes-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.
saishf-west-hermes-7b-v1-mkmlizer:   warnings.warn(
saishf-west-hermes-7b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.04MB/s]
saishf-west-hermes-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, 11.5MB/s]
saishf-west-hermes-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, 66.6MB/s]
saishf-west-hermes-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.
saishf-west-hermes-7b-v1-mkmlizer:   warnings.warn(
saishf-west-hermes-7b-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:15, 92.3MB/s]
pytorch_model.bin:  10%|█         | 147M/1.44G [00:00<00:02, 530MB/s]  
pytorch_model.bin:  20%|█▉        | 283M/1.44G [00:00<00:01, 707MB/s]
pytorch_model.bin:  27%|██▋       | 388M/1.44G [00:00<00:01, 786MB/s]
pytorch_model.bin:  33%|███▎      | 482M/1.44G [00:00<00:01, 784MB/s]
pytorch_model.bin:  46%|████▌     | 661M/1.44G [00:00<00:00, 1.07GB/s]
pytorch_model.bin:  59%|█████▉    | 849M/1.44G [00:00<00:00, 1.30GB/s]
pytorch_model.bin:  84%|████████▍ | 1.21G/1.44G [00:01<00:00, 1.98GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:10<00:00, 143MB/s] 
saishf-west-hermes-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-west-hermes-7b-v1-mkmlizer: Saving duration: 0.246s
saishf-west-hermes-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.911s
saishf-west-hermes-7b-v1-mkmlizer: creating bucket guanaco-reward-models
saishf-west-hermes-7b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-west-hermes-7b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/config.json
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/tokenizer_config.json
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/special_tokens_map.json
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/merges.txt
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/vocab.json
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/tokenizer.json
saishf-west-hermes-7b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-west-hermes-7b-v1_reward/reward.tensors
Job saishf-west-hermes-7b-v1-mkmlizer completed after 95.61s with status: succeeded
Stopping job with name saishf-west-hermes-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 100.60s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service saishf-west-hermes-7b-v1
Waiting for inference service saishf-west-hermes-7b-v1 to be ready
Inference service saishf-west-hermes-7b-v1 ready after 40.32205677032471s
Pipeline stage ISVCDeployer completed in 47.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6928229331970215s
Received healthy response to inference request in 0.8053750991821289s
Received healthy response to inference request in 0.7562313079833984s
Received healthy response to inference request in 1.0750012397766113s
Received healthy response to inference request in 0.8722743988037109s
5 requests
0 failed requests
5th percentile: 0.7660600662231445
10th percentile: 0.7758888244628906
20th percentile: 0.7955463409423829
30th percentile: 0.8187549591064454
40th percentile: 0.8455146789550781
50th percentile: 0.8722743988037109
60th percentile: 0.9533651351928711
70th percentile: 1.0344558715820311
80th percentile: 1.1985655784606934
90th percentile: 1.4456942558288575
95th percentile: 1.5692585945129394
99th percentile: 1.668110065460205
mean time: 1.0403409957885743
Pipeline stage StressChecker completed in 6.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.05s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
saishf-west-hermes-7b_v1 status is now deployed due to DeploymentManager action
saishf-west-hermes-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of saishf-west-hermes-7b_v1
Running pipeline stage ISVCDeleter
Checking if service saishf-west-hermes-7b-v1 is running
Tearing down inference service saishf-west-hermes-7b-v1
Toredown service saishf-west-hermes-7b-v1
Pipeline stage ISVCDeleter completed in 4.50s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key saishf-west-hermes-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key saishf-west-hermes-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key saishf-west-hermes-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key saishf-west-hermes-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key saishf-west-hermes-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key saishf-west-hermes-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key saishf-west-hermes-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key saishf-west-hermes-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.00s
saishf-west-hermes-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics