submission_id: inv-dykh-tau-7b_v1
developer_uid: Inv
status: torndown
model_repo: Inv/Dykh-Tau-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: 2024-03-26T17:57:13+00:00
model_name: inv-dykh-tau-7b_v1
model_eval_status: success
model_group: Inv/Dykh-Tau-7B
num_battles: 67255
num_wins: 33297
celo_rating: 1153.83
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-dykh-tau-7b_v1
ineligible_reason: propriety_total_count < 800
language_model: Inv/Dykh-Tau-7B
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-03-26
win_ratio: 0.4950858672217679
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-dykh-tau-7b-v1-mkmlizer
Waiting for job on inv-dykh-tau-7b-v1-mkmlizer to finish
inv-dykh-tau-7b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-dykh-tau-7b-v1-mkmlizer: ║     _____            __           __                                ║
inv-dykh-tau-7b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
inv-dykh-tau-7b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
inv-dykh-tau-7b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
inv-dykh-tau-7b-v1-mkmlizer: ║       /___/                                                         ║
inv-dykh-tau-7b-v1-mkmlizer: ║                                                                     ║
inv-dykh-tau-7b-v1-mkmlizer: ║  Version: 0.6.11                                                    ║
inv-dykh-tau-7b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
inv-dykh-tau-7b-v1-mkmlizer: ║                                                                     ║
inv-dykh-tau-7b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
inv-dykh-tau-7b-v1-mkmlizer: ║  belonging to:                                                      ║
inv-dykh-tau-7b-v1-mkmlizer: ║                                                                     ║
inv-dykh-tau-7b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
inv-dykh-tau-7b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
inv-dykh-tau-7b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
inv-dykh-tau-7b-v1-mkmlizer: ║                                                                     ║
inv-dykh-tau-7b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-dykh-tau-7b-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.2MB/s]
inv-dykh-tau-7b-v1-mkmlizer: 
README.md:   0%|          | 0.00/873 [00:00<?, ?B/s]
README.md: 100%|██████████| 873/873 [00:00<00:00, 14.1MB/s]
inv-dykh-tau-7b-v1-mkmlizer: 
config.json:   0%|          | 0.00/651 [00:00<?, ?B/s]
config.json: 100%|██████████| 651/651 [00:00<00:00, 10.5MB/s]
inv-dykh-tau-7b-v1-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/336 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 336/336 [00:00<00:00, 5.51MB/s]
inv-dykh-tau-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<01:15, 26.1MB/s]
model-00001-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:01<02:09, 15.2MB/s]
model-00001-of-00008.safetensors:   2%|▏         | 31.5M/1.98G [00:01<01:20, 24.2MB/s]
model-00001-of-00008.safetensors:   3%|▎         | 62.9M/1.98G [00:01<00:32, 58.7MB/s]
model-00001-of-00008.safetensors:   7%|▋         | 136M/1.98G [00:01<00:13, 132MB/s]  
model-00001-of-00008.safetensors:   8%|▊         | 168M/1.98G [00:01<00:11, 151MB/s]
model-00001-of-00008.safetensors:  10%|▉         | 189M/1.98G [00:02<00:11, 152MB/s]
model-00001-of-00008.safetensors:  11%|█         | 220M/1.98G [00:02<00:09, 181MB/s]
model-00001-of-00008.safetensors:  15%|█▌        | 304M/1.98G [00:02<00:05, 315MB/s]
model-00001-of-00008.safetensors:  21%|██        | 409M/1.98G [00:02<00:03, 477MB/s]
model-00001-of-00008.safetensors:  25%|██▌       | 503M/1.98G [00:02<00:02, 560MB/s]
model-00001-of-00008.safetensors:  29%|██▉       | 577M/1.98G [00:02<00:02, 586MB/s]
model-00001-of-00008.safetensors:  37%|███▋      | 734M/1.98G [00:02<00:01, 833MB/s]
model-00001-of-00008.safetensors:  69%|██████▉   | 1.36G/1.98G [00:02<00:00, 2.17GB/s]
model-00001-of-00008.safetensors:  81%|████████  | 1.59G/1.98G [00:03<00:00, 1.32GB/s]
model-00001-of-00008.safetensors:  90%|████████▉ | 1.77G/1.98G [00:03<00:00, 1.26GB/s]
model-00001-of-00008.safetensors:  98%|█████████▊| 1.95G/1.98G [00:03<00:00, 1.32GB/s]
model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 528MB/s] 
inv-dykh-tau-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 [00:00<03:00, 10.9MB/s]
model-00002-of-00008.safetensors:   1%|          | 21.0M/1.98G [00:01<01:33, 21.0MB/s]
model-00002-of-00008.safetensors:   2%|▏         | 41.9M/1.98G [00:01<00:43, 44.8MB/s]
model-00002-of-00008.safetensors:   3%|▎         | 62.9M/1.98G [00:01<00:30, 62.6MB/s]
model-00002-of-00008.safetensors:   5%|▍         | 94.4M/1.98G [00:01<00:18, 99.9MB/s]
model-00002-of-00008.safetensors:   6%|▋         | 126M/1.98G [00:01<00:13, 138MB/s]  
model-00002-of-00008.safetensors:   7%|▋         | 147M/1.98G [00:01<00:14, 131MB/s]
model-00002-of-00008.safetensors:  10%|▉         | 189M/1.98G [00:02<00:10, 177MB/s]
model-00002-of-00008.safetensors:  12%|█▏        | 231M/1.98G [00:02<00:08, 214MB/s]
model-00002-of-00008.safetensors:  15%|█▍        | 294M/1.98G [00:02<00:05, 289MB/s]
model-00002-of-00008.safetensors:  19%|█▊        | 367M/1.98G [00:02<00:04, 385MB/s]
model-00002-of-00008.safetensors:  26%|██▌       | 514M/1.98G [00:02<00:02, 622MB/s]
model-00002-of-00008.safetensors:  30%|██▉       | 587M/1.98G [00:02<00:02, 579MB/s]
model-00002-of-00008.safetensors:  39%|███▊      | 765M/1.98G [00:02<00:01, 869MB/s]
model-00002-of-00008.safetensors:  66%|██████▌   | 1.30G/1.98G [00:02<00:00, 1.99GB/s]
model-00002-of-00008.safetensors:  77%|███████▋  | 1.52G/1.98G [00:03<00:00, 1.23GB/s]
model-00002-of-00008.safetensors:  86%|████████▌ | 1.70G/1.98G [00:03<00:00, 923MB/s] 
model-00002-of-00008.safetensors:  98%|█████████▊| 1.94G/1.98G [00:03<00:00, 1.15GB/s]
model-00002-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 480MB/s] 
inv-dykh-tau-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 [00:00<02:59, 10.8MB/s]
model-00003-of-00008.safetensors:   2%|▏         | 31.5M/1.95G [00:01<01:11, 26.6MB/s]
model-00003-of-00008.safetensors:   3%|▎         | 62.9M/1.95G [00:01<00:31, 60.5MB/s]
model-00003-of-00008.safetensors:   8%|▊         | 157M/1.95G [00:01<00:09, 184MB/s]  
model-00003-of-00008.safetensors:  11%|█         | 210M/1.95G [00:01<00:08, 203MB/s]
model-00003-of-00008.safetensors:  13%|█▎        | 252M/1.95G [00:01<00:07, 230MB/s]
model-00003-of-00008.safetensors:  16%|█▌        | 304M/1.95G [00:02<00:05, 277MB/s]
model-00003-of-00008.safetensors:  22%|██▏       | 430M/1.95G [00:02<00:03, 466MB/s]
model-00003-of-00008.safetensors:  26%|██▌       | 503M/1.95G [00:02<00:02, 503MB/s]
model-00003-of-00008.safetensors:  33%|███▎      | 640M/1.95G [00:02<00:01, 702MB/s]
model-00003-of-00008.safetensors:  64%|██████▎   | 1.24G/1.95G [00:02<00:00, 2.00GB/s]
model-00003-of-00008.safetensors:  76%|███████▌  | 1.48G/1.95G [00:02<00:00, 1.48GB/s]
model-00003-of-00008.safetensors:  86%|████████▌ | 1.68G/1.95G [00:02<00:00, 1.38GB/s]
model-00003-of-00008.safetensors:  95%|█████████▍| 1.85G/1.95G [00:03<00:00, 1.36GB/s]
model-00003-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 554MB/s] 
inv-dykh-tau-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<03:36, 8.68MB/s]
model-00005-of-00008.safetensors:   2%|▏         | 31.5M/1.89G [00:01<01:02, 29.9MB/s]
model-00005-of-00008.safetensors:   3%|▎         | 62.9M/1.89G [00:01<00:27, 66.1MB/s]
model-00005-of-00008.safetensors:   8%|▊         | 147M/1.89G [00:01<00:09, 182MB/s]  
model-00005-of-00008.safetensors:  10%|▉         | 189M/1.89G [00:01<00:09, 177MB/s]
model-00005-of-00008.safetensors:  13%|█▎        | 241M/1.89G [00:01<00:07, 233MB/s]
model-00005-of-00008.safetensors:  18%|█▊        | 336M/1.89G [00:02<00:04, 363MB/s]
model-00005-of-00008.safetensors:  26%|██▌       | 493M/1.89G [00:02<00:02, 617MB/s]
model-00005-of-00008.safetensors:  31%|███       | 587M/1.89G [00:02<00:02, 631MB/s]
model-00005-of-00008.safetensors:  41%|████      | 765M/1.89G [00:02<00:01, 898MB/s]
model-00005-of-00008.safetensors:  68%|██████▊   | 1.28G/1.89G [00:02<00:00, 1.87GB/s]
model-00005-of-00008.safetensors:  79%|███████▉  | 1.49G/1.89G [00:02<00:00, 1.15GB/s]
model-00005-of-00008.safetensors:  88%|████████▊ | 1.66G/1.89G [00:02<00:00, 1.17GB/s]
model-00005-of-00008.safetensors:  96%|█████████▌| 1.82G/1.89G [00:03<00:00, 1.25GB/s]
model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 576MB/s] 
inv-dykh-tau-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<02:34, 12.4MB/s]
model-00006-of-00008.safetensors:   2%|▏         | 31.5M/1.92G [00:01<01:20, 23.6MB/s]
model-00006-of-00008.safetensors:   5%|▍         | 94.4M/1.92G [00:01<00:20, 87.2MB/s]
model-00006-of-00008.safetensors:   8%|▊         | 147M/1.92G [00:01<00:14, 119MB/s]  
model-00006-of-00008.safetensors:  10%|▉         | 189M/1.92G [00:01<00:11, 149MB/s]
model-00006-of-00008.safetensors:  12%|█▏        | 231M/1.92G [00:02<00:09, 188MB/s]
model-00006-of-00008.safetensors:  16%|█▌        | 304M/1.92G [00:02<00:05, 282MB/s]
model-00006-of-00008.safetensors:  19%|█▉        | 367M/1.92G [00:02<00:04, 349MB/s]
model-00006-of-00008.safetensors:  26%|██▌       | 503M/1.92G [00:02<00:02, 553MB/s]
model-00006-of-00008.safetensors:  30%|██▉       | 577M/1.92G [00:02<00:02, 567MB/s]
model-00006-of-00008.safetensors:  34%|███▍      | 650M/1.92G [00:02<00:02, 593MB/s]
model-00006-of-00008.safetensors:  65%|██████▍   | 1.25G/1.92G [00:02<00:00, 1.95GB/s]
model-00006-of-00008.safetensors:  77%|███████▋  | 1.48G/1.92G [00:03<00:00, 1.16GB/s]
model-00006-of-00008.safetensors:  86%|████████▌ | 1.66G/1.92G [00:03<00:00, 1.13GB/s]
model-00006-of-00008.safetensors:  95%|█████████▍| 1.82G/1.92G [00:03<00:00, 1.04GB/s]
model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:03<00:00, 532MB/s] 
inv-dykh-tau-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<04:06, 7.85MB/s]
model-00007-of-00008.safetensors:   1%|          | 21.0M/1.95G [00:01<02:05, 15.3MB/s]
model-00007-of-00008.safetensors:   6%|▋         | 126M/1.95G [00:01<00:15, 116MB/s]  
model-00007-of-00008.safetensors:   8%|▊         | 157M/1.95G [00:01<00:13, 130MB/s]
model-00007-of-00008.safetensors:  10%|▉         | 189M/1.95G [00:02<00:11, 154MB/s]
model-00007-of-00008.safetensors:  11%|█▏        | 220M/1.95G [00:02<00:09, 180MB/s]
model-00007-of-00008.safetensors:  15%|█▍        | 283M/1.95G [00:02<00:06, 265MB/s]
model-00007-of-00008.safetensors:  20%|██        | 398M/1.95G [00:02<00:03, 454MB/s]
model-00007-of-00008.safetensors:  29%|██▊       | 556M/1.95G [00:02<00:01, 712MB/s]
model-00007-of-00008.safetensors:  33%|███▎      | 650M/1.95G [00:02<00:02, 639MB/s]
model-00007-of-00008.safetensors:  64%|██████▎   | 1.24G/1.95G [00:02<00:00, 1.81GB/s]
model-00007-of-00008.safetensors:  75%|███████▌  | 1.47G/1.95G [00:03<00:00, 1.16GB/s]
model-00007-of-00008.safetensors:  85%|████████▍ | 1.65G/1.95G [00:03<00:00, 1.15GB/s]
model-00007-of-00008.safetensors:  93%|█████████▎| 1.81G/1.95G [00:03<00:00, 1.09GB/s]
model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 553MB/s] 
inv-dykh-tau-7b-v1-mkmlizer: 
model-00008-of-00008.safetensors:   0%|          | 0.00/872M [00:00<?, ?B/s]
model-00008-of-00008.safetensors:   0%|          | 2.13M/872M [00:00<06:17, 2.31MB/s]
model-00008-of-00008.safetensors:   1%|▏         | 12.6M/872M [00:01<01:08, 12.5MB/s]
model-00008-of-00008.safetensors:   5%|▌         | 44.1M/872M [00:01<00:16, 49.3MB/s]
model-00008-of-00008.safetensors:   7%|▋         | 65.0M/872M [00:01<00:13, 61.4MB/s]
model-00008-of-00008.safetensors:  24%|██▍       | 212M/872M [00:01<00:02, 274MB/s]  
model-00008-of-00008.safetensors:  39%|███▊      | 338M/872M [00:01<00:01, 444MB/s]
model-00008-of-00008.safetensors:  48%|████▊     | 422M/872M [00:01<00:00, 512MB/s]
model-00008-of-00008.safetensors:  81%|████████  | 705M/872M [00:02<00:00, 1.02GB/s]
model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:02<00:00, 422MB/s] 
inv-dykh-tau-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, 162MB/s]
inv-dykh-tau-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]
inv-dykh-tau-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, 19.2MB/s]
inv-dykh-tau-7b-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 11.1MB/s]
inv-dykh-tau-7b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/1.18k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.18k/1.18k [00:00<00:00, 11.9MB/s]
inv-dykh-tau-7b-v1-mkmlizer: Downloaded to shared memory in 32.168s
inv-dykh-tau-7b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
inv-dykh-tau-7b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-dykh-tau-7b-v1-mkmlizer: Reading /tmp/tmpxqa0vc4j/model.safetensors.index.json
inv-dykh-tau-7b-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:00<00:35,  8.27it/s]
Profiling:   4%|▍         | 11/291 [00:00<00:05, 55.04it/s]
Profiling:   8%|▊         | 22/291 [00:00<00:03, 75.54it/s]
Profiling:  13%|█▎        | 37/291 [00:00<00:03, 75.83it/s]
Profiling:  16%|█▋        | 48/291 [00:00<00:02, 83.61it/s]
Profiling:  21%|██        | 61/291 [00:00<00:02, 95.10it/s]
Profiling:  26%|██▌       | 76/291 [00:00<00:02, 88.40it/s]
Profiling:  30%|███       | 88/291 [00:01<00:02, 92.82it/s]
Profiling:  34%|███▍      | 99/291 [00:01<00:02, 94.29it/s]
Profiling:  41%|████      | 118/291 [00:01<00:01, 97.32it/s]
Profiling:  45%|████▌     | 131/291 [00:01<00:01, 104.59it/s]
Profiling:  50%|████▉     | 145/291 [00:01<00:01, 108.51it/s]
Profiling:  55%|█████▍    | 160/291 [00:03<00:05, 25.68it/s] 
Profiling:  59%|█████▉    | 172/291 [00:03<00:03, 32.25it/s]
Profiling:  64%|██████▎   | 185/291 [00:03<00:02, 41.27it/s]
Profiling:  68%|██████▊   | 197/291 [00:04<00:04, 20.76it/s]
Profiling:  71%|███████   | 207/291 [00:04<00:03, 25.64it/s]
Profiling:  76%|███████▌  | 221/291 [00:04<00:01, 35.08it/s]
Profiling:  79%|███████▉  | 231/291 [00:04<00:01, 40.44it/s]
Profiling:  83%|████████▎ | 242/291 [00:05<00:01, 48.91it/s]
Profiling:  88%|████████▊ | 256/291 [00:05<00:00, 62.82it/s]
Profiling:  93%|█████████▎| 271/291 [00:05<00:00, 78.23it/s]
Profiling:  97%|█████████▋| 283/291 [00:05<00:00, 75.88it/s]
Profiling: 100%|██████████| 291/291 [00:05<00:00, 52.11it/s]
inv-dykh-tau-7b-v1-mkmlizer: quantized model in 16.095s
inv-dykh-tau-7b-v1-mkmlizer: Processed model Inv/Dykh-Tau-7B in 49.167s
inv-dykh-tau-7b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-dykh-tau-7b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-dykh-tau-7b-v1
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/special_tokens_map.json
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/tokenizer_config.json
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/config.json
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/tokenizer.json
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/tokenizer.model
inv-dykh-tau-7b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-dykh-tau-7b-v1/mkml_model.tensors
inv-dykh-tau-7b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
inv-dykh-tau-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-dykh-tau-7b-v1-mkmlizer:   warnings.warn(
inv-dykh-tau-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, 11.9MB/s]
inv-dykh-tau-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-dykh-tau-7b-v1-mkmlizer:   warnings.warn(
inv-dykh-tau-7b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.44MB/s]
inv-dykh-tau-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, 11.0MB/s]
inv-dykh-tau-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, 96.7MB/s]
inv-dykh-tau-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-dykh-tau-7b-v1-mkmlizer:   warnings.warn(
inv-dykh-tau-7b-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|          | 10.5M/1.44G [00:00<00:18, 79.1MB/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:20, 70.4MB/s]
pytorch_model.bin:   2%|▏         | 31.5M/1.44G [00:00<00:17, 79.9MB/s]
pytorch_model.bin:   7%|▋         | 105M/1.44G [00:00<00:04, 291MB/s]  
pytorch_model.bin:  15%|█▍        | 210M/1.44G [00:00<00:02, 529MB/s]
pytorch_model.bin:  25%|██▌       | 367M/1.44G [00:00<00:01, 738MB/s]
pytorch_model.bin:  31%|███       | 451M/1.44G [00:00<00:01, 761MB/s]
pytorch_model.bin:  42%|████▏     | 608M/1.44G [00:00<00:00, 975MB/s]
pytorch_model.bin:  52%|█████▏    | 753M/1.44G [00:01<00:00, 1.10GB/s]
pytorch_model.bin:  63%|██████▎   | 910M/1.44G [00:01<00:00, 1.22GB/s]
pytorch_model.bin:  80%|███████▉  | 1.15G/1.44G [00:01<00:00, 1.57GB/s]
pytorch_model.bin:  98%|█████████▊| 1.41G/1.44G [00:01<00:00, 1.86GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 969MB/s] 
inv-dykh-tau-7b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-dykh-tau-7b-v1-mkmlizer: Saving duration: 0.242s
inv-dykh-tau-7b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.924s
Job inv-dykh-tau-7b-v1-mkmlizer completed after 75.27s with status: succeeded
Stopping job with name inv-dykh-tau-7b-v1-mkmlizer
Pipeline stage MKMLizer completed in 80.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-dykh-tau-7b-v1
Waiting for inference service inv-dykh-tau-7b-v1 to be ready
Inference service inv-dykh-tau-7b-v1 ready after 40.51326298713684s
Pipeline stage ISVCDeployer completed in 49.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6902763843536377s
Received healthy response to inference request in 1.1593656539916992s
Received healthy response to inference request in 1.1535065174102783s
Received healthy response to inference request in 1.1731503009796143s
Received healthy response to inference request in 1.1548271179199219s
5 requests
0 failed requests
5th percentile: 1.153770637512207
10th percentile: 1.1540347576141357
20th percentile: 1.1545629978179932
30th percentile: 1.1557348251342774
40th percentile: 1.1575502395629882
50th percentile: 1.1593656539916992
60th percentile: 1.1648795127868652
70th percentile: 1.1703933715820312
80th percentile: 1.2765755176544191
90th percentile: 1.4834259510040284
95th percentile: 1.5868511676788328
99th percentile: 1.6695913410186767
mean time: 1.2662251949310304
Pipeline stage StressChecker completed in 7.21s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
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
inv-dykh-tau-7b_v1 status is now deployed due to DeploymentManager action
inv-dykh-tau-7b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of inv-dykh-tau-7b_v1
Running pipeline stage ISVCDeleter
Checking if service inv-dykh-tau-7b-v1 is running
Tearing down inference service inv-dykh-tau-7b-v1
Toredown service inv-dykh-tau-7b-v1
Pipeline stage ISVCDeleter completed in 4.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key inv-dykh-tau-7b-v1/config.json from bucket guanaco-mkml-models
Deleting key inv-dykh-tau-7b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key inv-dykh-tau-7b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key inv-dykh-tau-7b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key inv-dykh-tau-7b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key inv-dykh-tau-7b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key inv-dykh-tau-7b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key inv-dykh-tau-7b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.33s
inv-dykh-tau-7b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics