fizzarolli-llama-3-lust-_3078

developer_uid: Fizzarolli
submission_id: fizzarolli-llama-3-lust-_3078_v1
model_name: fizzarolli-llama-3-lust2_8389
model_group: Fizzarolli/llama-3-lust-
status: torndown
timestamp: 2024-04-20T03:59:32+00:00
num_battles: 6114
num_wins: 2165
celo_rating: 1038.78
family_friendly_score: 0.0
submission_type: basic
model_repo: Fizzarolli/llama-3-lust-8b-step-748
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: fizzarolli-llama-3-lust2_8389
is_internal_developer: False
language_model: Fizzarolli/llama-3-lust-8b-step-748
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-19
win_ratio: 0.354105332024861
generation_params: {'temperature': 0.95, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 60, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|description|>{bot_name}\n{memory}</s>\n', 'prompt_template': '<|message|>{user_name}\n{prompt}</s>\n<|message|>{bot_name}\n', 'bot_template': '<|message|>{bot_name}\n{message}</s>\n', 'user_template': '<|message|>{user_name}\n{message}</s>\n', 'response_template': '<|message|>{bot_name}\n', 'truncate_by_message': False}
model_eval_status: pending
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name fizzarolli-llama-3-lust-3078-v1-mkmlizer
Waiting for job on fizzarolli-llama-3-lust-3078-v1-mkmlizer to finish
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║     _____            __           __                                ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║       /___/                                                         ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║                                                                     ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  Version: 0.6.11                                                    ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║                                                                     ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  belonging to:                                                      ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║                                                                     ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  Chai Research Corp.                                                ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ║                                                                     ║
fizzarolli-llama-3-lust-3078-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 16.2MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
config.json:   0%|          | 0.00/696 [00:00<?, ?B/s]
config.json: 100%|██████████| 696/696 [00:00<00:00, 9.30MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
generation_config.json:   0%|          | 0.00/147 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 147/147 [00:00<00:00, 2.37MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model-00001-of-00004.bin:   0%|          | 0.00/4.98G [00:00<?, ?B/s]
pytorch_model-00001-of-00004.bin:   0%|          | 10.5M/4.98G [00:01<12:23, 6.68MB/s]
pytorch_model-00001-of-00004.bin:   1%|          | 41.9M/4.98G [00:01<02:34, 31.9MB/s]
pytorch_model-00001-of-00004.bin:   2%|▏         | 83.9M/4.98G [00:01<01:20, 60.6MB/s]
pytorch_model-00001-of-00004.bin:   2%|▏         | 105M/4.98G [00:02<01:11, 67.9MB/s] 
pytorch_model-00001-of-00004.bin:   3%|▎         | 126M/4.98G [00:02<00:57, 84.9MB/s]
pytorch_model-00001-of-00004.bin:   3%|▎         | 157M/4.98G [00:02<00:44, 109MB/s] 
pytorch_model-00001-of-00004.bin:   4%|▍         | 189M/4.98G [00:02<00:37, 128MB/s]
pytorch_model-00001-of-00004.bin:   4%|▍         | 210M/4.98G [00:02<00:35, 135MB/s]
pytorch_model-00001-of-00004.bin:   5%|▍         | 231M/4.98G [00:02<00:31, 149MB/s]
pytorch_model-00001-of-00004.bin:   5%|▌         | 252M/4.98G [00:02<00:30, 154MB/s]
pytorch_model-00001-of-00004.bin:   6%|▋         | 315M/4.98G [00:03<00:19, 241MB/s]
pytorch_model-00001-of-00004.bin:   7%|▋         | 367M/4.98G [00:03<00:16, 281MB/s]
pytorch_model-00001-of-00004.bin:   9%|▉         | 440M/4.98G [00:03<00:11, 379MB/s]
pytorch_model-00001-of-00004.bin:  12%|█▏        | 587M/4.98G [00:03<00:07, 611MB/s]
pytorch_model-00001-of-00004.bin:  15%|█▌        | 755M/4.98G [00:03<00:05, 772MB/s]
pytorch_model-00001-of-00004.bin:  17%|█▋        | 839M/4.98G [00:03<00:05, 693MB/s]
pytorch_model-00001-of-00004.bin:  20%|██        | 1.01G/4.98G [00:03<00:04, 919MB/s]
pytorch_model-00001-of-00004.bin:  28%|██▊       | 1.38G/4.98G [00:04<00:02, 1.27GB/s]
pytorch_model-00001-of-00004.bin:  30%|███       | 1.51G/4.98G [00:04<00:06, 575MB/s] 
pytorch_model-00001-of-00004.bin:  32%|███▏      | 1.60G/4.98G [00:04<00:05, 581MB/s]
pytorch_model-00001-of-00004.bin:  34%|███▍      | 1.69G/4.98G [00:05<00:05, 558MB/s]
pytorch_model-00001-of-00004.bin:  35%|███▌      | 1.76G/4.98G [00:05<00:05, 561MB/s]
pytorch_model-00001-of-00004.bin:  37%|███▋      | 1.84G/4.98G [00:05<00:05, 540MB/s]
pytorch_model-00001-of-00004.bin:  39%|███▊      | 1.92G/4.98G [00:05<00:05, 565MB/s]
pytorch_model-00001-of-00004.bin:  41%|████      | 2.03G/4.98G [00:05<00:04, 659MB/s]
pytorch_model-00001-of-00004.bin:  44%|████▎     | 2.17G/4.98G [00:05<00:03, 758MB/s]
pytorch_model-00001-of-00004.bin:  46%|████▌     | 2.28G/4.98G [00:05<00:03, 794MB/s]
pytorch_model-00001-of-00004.bin:  50%|████▉     | 2.46G/4.98G [00:05<00:02, 1.04GB/s]
pytorch_model-00001-of-00004.bin:  52%|█████▏    | 2.58G/4.98G [00:06<00:02, 806MB/s] 
pytorch_model-00001-of-00004.bin:  54%|█████▎    | 2.67G/4.98G [00:06<00:02, 780MB/s]
pytorch_model-00001-of-00004.bin:  56%|█████▌    | 2.79G/4.98G [00:06<00:02, 853MB/s]
pytorch_model-00001-of-00004.bin:  62%|██████▏   | 3.08G/4.98G [00:06<00:01, 1.31GB/s]
pytorch_model-00001-of-00004.bin:  67%|██████▋   | 3.34G/4.98G [00:06<00:01, 1.63GB/s]
pytorch_model-00001-of-00004.bin:  74%|███████▍  | 3.68G/4.98G [00:06<00:00, 2.00GB/s]
pytorch_model-00001-of-00004.bin:  78%|███████▊  | 3.90G/4.98G [00:07<00:01, 677MB/s] 
pytorch_model-00001-of-00004.bin:  82%|████████▏ | 4.06G/4.98G [00:07<00:01, 740MB/s]
pytorch_model-00001-of-00004.bin:  84%|████████▍ | 4.20G/4.98G [00:07<00:00, 803MB/s]
pytorch_model-00001-of-00004.bin:  87%|████████▋ | 4.34G/4.98G [00:08<00:00, 750MB/s]
pytorch_model-00001-of-00004.bin:  95%|█████████▍| 4.72G/4.98G [00:08<00:00, 1.21GB/s]
pytorch_model-00001-of-00004.bin: 100%|█████████▉| 4.98G/4.98G [00:08<00:00, 594MB/s] 
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model-00002-of-00004.bin:   0%|          | 0.00/5.00G [00:00<?, ?B/s]
pytorch_model-00002-of-00004.bin:   0%|          | 10.5M/5.00G [00:00<04:43, 17.6MB/s]
pytorch_model-00002-of-00004.bin:   0%|          | 21.0M/5.00G [00:02<12:02, 6.89MB/s]
pytorch_model-00002-of-00004.bin:   1%|          | 31.5M/5.00G [00:03<08:16, 10.0MB/s]
pytorch_model-00002-of-00004.bin:   2%|▏         | 94.4M/5.00G [00:03<01:48, 45.2MB/s]
pytorch_model-00002-of-00004.bin:   2%|▏         | 115M/5.00G [00:03<01:28, 55.4MB/s] 
pytorch_model-00002-of-00004.bin:   3%|▎         | 136M/5.00G [00:03<01:12, 66.7MB/s]
pytorch_model-00002-of-00004.bin:   4%|▍         | 210M/5.00G [00:03<00:33, 141MB/s] 
pytorch_model-00002-of-00004.bin:  10%|▉         | 482M/5.00G [00:03<00:09, 497MB/s]
pytorch_model-00002-of-00004.bin:  23%|██▎       | 1.16G/5.00G [00:04<00:02, 1.53GB/s]
pytorch_model-00002-of-00004.bin:  29%|██▉       | 1.45G/5.00G [00:05<00:05, 598MB/s] 
pytorch_model-00002-of-00004.bin:  33%|███▎      | 1.66G/5.00G [00:05<00:06, 555MB/s]
pytorch_model-00002-of-00004.bin:  36%|███▋      | 1.81G/5.00G [00:05<00:05, 606MB/s]
pytorch_model-00002-of-00004.bin:  39%|███▉      | 1.95G/5.00G [00:05<00:04, 667MB/s]
pytorch_model-00002-of-00004.bin:  42%|████▏     | 2.09G/5.00G [00:06<00:04, 678MB/s]
pytorch_model-00002-of-00004.bin:  44%|████▍     | 2.20G/5.00G [00:06<00:04, 693MB/s]
pytorch_model-00002-of-00004.bin:  54%|█████▍    | 2.69G/5.00G [00:06<00:01, 1.34GB/s]
pytorch_model-00002-of-00004.bin:  58%|█████▊    | 2.92G/5.00G [00:06<00:01, 1.26GB/s]
pytorch_model-00002-of-00004.bin:  62%|██████▏   | 3.10G/5.00G [00:06<00:01, 1.14GB/s]
pytorch_model-00002-of-00004.bin:  65%|██████▌   | 3.26G/5.00G [00:07<00:02, 830MB/s] 
pytorch_model-00002-of-00004.bin:  68%|██████▊   | 3.39G/5.00G [00:07<00:02, 799MB/s]
pytorch_model-00002-of-00004.bin:  70%|███████   | 3.50G/5.00G [00:07<00:01, 847MB/s]
pytorch_model-00002-of-00004.bin:  74%|███████▍  | 3.70G/5.00G [00:07<00:01, 1.04GB/s]
pytorch_model-00002-of-00004.bin:  77%|███████▋  | 3.87G/5.00G [00:07<00:00, 1.14GB/s]
pytorch_model-00002-of-00004.bin:  80%|████████  | 4.01G/5.00G [00:07<00:00, 1.08GB/s]
pytorch_model-00002-of-00004.bin:  83%|████████▎ | 4.13G/5.00G [00:07<00:00, 1.08GB/s]
pytorch_model-00002-of-00004.bin:  85%|████████▌ | 4.26G/5.00G [00:08<00:00, 1.06GB/s]
pytorch_model-00002-of-00004.bin:  87%|████████▋ | 4.37G/5.00G [00:08<00:00, 812MB/s] 
pytorch_model-00002-of-00004.bin:  90%|█████████ | 4.51G/5.00G [00:08<00:00, 910MB/s]
pytorch_model-00002-of-00004.bin:  92%|█████████▏| 4.61G/5.00G [00:08<00:00, 860MB/s]
pytorch_model-00002-of-00004.bin: 100%|█████████▉| 5.00G/5.00G [00:08<00:00, 577MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model-00003-of-00004.bin:   0%|          | 0.00/4.92G [00:00<?, ?B/s]
pytorch_model-00003-of-00004.bin:   0%|          | 10.5M/4.92G [00:01<08:07, 10.1MB/s]
pytorch_model-00003-of-00004.bin:   0%|          | 21.0M/4.92G [00:02<09:12, 8.87MB/s]
pytorch_model-00003-of-00004.bin:   1%|          | 31.5M/4.92G [00:02<05:48, 14.0MB/s]
pytorch_model-00003-of-00004.bin:   1%|          | 41.9M/4.92G [00:02<04:24, 18.4MB/s]
pytorch_model-00003-of-00004.bin:   1%|          | 52.4M/4.92G [00:03<03:30, 23.1MB/s]
pytorch_model-00003-of-00004.bin:   1%|▏         | 62.9M/4.92G [00:03<03:01, 26.7MB/s]
pytorch_model-00003-of-00004.bin:   2%|▏         | 83.9M/4.92G [00:03<01:45, 45.7MB/s]
pytorch_model-00003-of-00004.bin:   3%|▎         | 147M/4.92G [00:03<00:40, 119MB/s]  
pytorch_model-00003-of-00004.bin:   6%|▋         | 315M/4.92G [00:03<00:13, 338MB/s]
pytorch_model-00003-of-00004.bin:   7%|▋         | 367M/4.92G [00:03<00:12, 356MB/s]
pytorch_model-00003-of-00004.bin:   9%|▉         | 451M/4.92G [00:03<00:10, 446MB/s]
pytorch_model-00003-of-00004.bin:  17%|█▋        | 849M/4.92G [00:04<00:03, 1.20GB/s]
pytorch_model-00003-of-00004.bin:  22%|██▏       | 1.08G/4.92G [00:04<00:03, 1.01GB/s]
pytorch_model-00003-of-00004.bin:  25%|██▍       | 1.23G/4.92G [00:05<00:08, 424MB/s] 
pytorch_model-00003-of-00004.bin:  27%|██▋       | 1.34G/4.92G [00:05<00:07, 484MB/s]
pytorch_model-00003-of-00004.bin:  30%|███       | 1.49G/4.92G [00:05<00:06, 558MB/s]
pytorch_model-00003-of-00004.bin:  32%|███▏      | 1.59G/4.92G [00:05<00:06, 510MB/s]
pytorch_model-00003-of-00004.bin:  34%|███▍      | 1.68G/4.92G [00:05<00:05, 554MB/s]
pytorch_model-00003-of-00004.bin:  36%|███▌      | 1.76G/4.92G [00:06<00:05, 585MB/s]
pytorch_model-00003-of-00004.bin:  38%|███▊      | 1.86G/4.92G [00:06<00:04, 647MB/s]
pytorch_model-00003-of-00004.bin:  40%|████      | 1.97G/4.92G [00:06<00:04, 713MB/s]
pytorch_model-00003-of-00004.bin:  42%|████▏     | 2.07G/4.92G [00:06<00:04, 702MB/s]
pytorch_model-00003-of-00004.bin:  44%|████▍     | 2.18G/4.92G [00:06<00:03, 787MB/s]
pytorch_model-00003-of-00004.bin:  50%|█████     | 2.46G/4.92G [00:06<00:01, 1.25GB/s]
pytorch_model-00003-of-00004.bin:  58%|█████▊    | 2.85G/4.92G [00:06<00:01, 1.62GB/s]
pytorch_model-00003-of-00004.bin:  61%|██████▏   | 3.02G/4.92G [00:07<00:03, 501MB/s] 
pytorch_model-00003-of-00004.bin:  64%|██████▍   | 3.15G/4.92G [00:08<00:03, 478MB/s]
pytorch_model-00003-of-00004.bin:  66%|██████▌   | 3.25G/4.92G [00:08<00:03, 472MB/s]
pytorch_model-00003-of-00004.bin:  68%|██████▊   | 3.34G/4.92G [00:08<00:02, 524MB/s]
pytorch_model-00003-of-00004.bin:  70%|██████▉   | 3.44G/4.92G [00:08<00:02, 553MB/s]
pytorch_model-00003-of-00004.bin:  73%|███████▎  | 3.57G/4.92G [00:08<00:02, 660MB/s]
pytorch_model-00003-of-00004.bin:  80%|████████  | 3.95G/4.92G [00:08<00:00, 1.25GB/s]
pytorch_model-00003-of-00004.bin:  84%|████████▍ | 4.14G/4.92G [00:09<00:01, 599MB/s] 
pytorch_model-00003-of-00004.bin:  87%|████████▋ | 4.28G/4.92G [00:09<00:01, 594MB/s]
pytorch_model-00003-of-00004.bin:  89%|████████▉ | 4.39G/4.92G [00:09<00:00, 643MB/s]
pytorch_model-00003-of-00004.bin:  92%|█████████▏| 4.51G/4.92G [00:10<00:00, 668MB/s]
pytorch_model-00003-of-00004.bin:  94%|█████████▍| 4.61G/4.92G [00:10<00:00, 684MB/s]
pytorch_model-00003-of-00004.bin: 100%|█████████▉| 4.92G/4.92G [00:10<00:00, 472MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model-00004-of-00004.bin:   0%|          | 0.00/1.17G [00:00<?, ?B/s]
pytorch_model-00004-of-00004.bin:   1%|          | 10.5M/1.17G [00:00<01:41, 11.4MB/s]
pytorch_model-00004-of-00004.bin:   2%|▏         | 21.0M/1.17G [00:01<01:15, 15.1MB/s]
pytorch_model-00004-of-00004.bin:   3%|▎         | 31.5M/1.17G [00:01<01:02, 18.3MB/s]
pytorch_model-00004-of-00004.bin:   4%|▎         | 41.9M/1.17G [00:02<00:58, 19.2MB/s]
pytorch_model-00004-of-00004.bin:   4%|▍         | 52.4M/1.17G [00:02<00:49, 22.7MB/s]
pytorch_model-00004-of-00004.bin:   5%|▌         | 62.9M/1.17G [00:02<00:36, 30.6MB/s]
pytorch_model-00004-of-00004.bin:   6%|▋         | 73.4M/1.17G [00:03<00:32, 34.0MB/s]
pytorch_model-00004-of-00004.bin:   8%|▊         | 94.4M/1.17G [00:03<00:19, 54.9MB/s]
pytorch_model-00004-of-00004.bin:  22%|██▏       | 252M/1.17G [00:03<00:03, 285MB/s]  
pytorch_model-00004-of-00004.bin:  28%|██▊       | 325M/1.17G [00:03<00:02, 365MB/s]
pytorch_model-00004-of-00004.bin:  36%|███▌      | 419M/1.17G [00:03<00:01, 468MB/s]
pytorch_model-00004-of-00004.bin:  42%|████▏     | 493M/1.17G [00:03<00:01, 437MB/s]
pytorch_model-00004-of-00004.bin:  62%|██████▏   | 728M/1.17G [00:03<00:00, 825MB/s]
pytorch_model-00004-of-00004.bin: 100%|█████████▉| 1.17G/1.17G [00:03<00:00, 295MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model.bin.index.json:   0%|          | 0.00/23.9k [00:00<?, ?B/s]
pytorch_model.bin.index.json: 100%|██████████| 23.9k/23.9k [00:00<00:00, 120MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/449 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 449/449 [00:00<00:00, 4.16MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/9.08M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 9.08M/9.08M [00:00<00:00, 50.5MB/s]
tokenizer.json: 100%|██████████| 9.08M/9.08M [00:00<00:00, 49.6MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/50.6k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 50.6k/50.6k [00:00<00:00, 238MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Downloaded to shared memory in 33.841s
fizzarolli-llama-3-lust-3078-v1-mkmlizer: quantizing model to /dev/shm/model_cache
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Reading /tmp/tmpkqp3_taj/pytorch_model.bin.index.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:05<28:35,  5.91s/it]
Profiling:  29%|██▊       | 83/291 [00:06<00:12, 16.00it/s]
Profiling:  64%|██████▍   | 187/291 [00:07<00:02, 35.27it/s]
Profiling:  99%|█████████▊| 287/291 [00:08<00:00, 60.38it/s]
Profiling: 100%|██████████| 291/291 [00:13<00:00, 21.64it/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
fizzarolli-llama-3-lust-3078-v1-mkmlizer: quantized model in 26.786s
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Processed model Fizzarolli/llama-3-lust-8b-step-748 in 61.759s
fizzarolli-llama-3-lust-3078-v1-mkmlizer: creating bucket guanaco-mkml-models
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fizzarolli-llama-3-lust-3078-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1/special_tokens_map.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1/tokenizer_config.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1/config.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1/tokenizer.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/fizzarolli-llama-3-lust-3078-v1/mkml_model.tensors
fizzarolli-llama-3-lust-3078-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fizzarolli-llama-3-lust-3078-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.
fizzarolli-llama-3-lust-3078-v1-mkmlizer:   warnings.warn(
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 5.57MB/s]
fizzarolli-llama-3-lust-3078-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.
fizzarolli-llama-3-lust-3078-v1-mkmlizer:   warnings.warn(
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.10MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 27.6MB/s]
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 30.3MB/s]
fizzarolli-llama-3-lust-3078-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.
fizzarolli-llama-3-lust-3078-v1-mkmlizer:   warnings.warn(
fizzarolli-llama-3-lust-3078-v1-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|▏         | 21.0M/1.44G [00:00<00:08, 163MB/s]
pytorch_model.bin:   3%|▎         | 41.9M/1.44G [00:00<00:12, 110MB/s]
pytorch_model.bin:   8%|▊         | 115M/1.44G [00:00<00:05, 264MB/s] 
pytorch_model.bin:  10%|█         | 147M/1.44G [00:00<00:04, 267MB/s]
pytorch_model.bin:  23%|██▎       | 336M/1.44G [00:00<00:01, 703MB/s]
pytorch_model.bin:  36%|███▌      | 514M/1.44G [00:00<00:00, 961MB/s]
pytorch_model.bin:  43%|████▎     | 627M/1.44G [00:01<00:00, 825MB/s]
pytorch_model.bin:  50%|████▉     | 721M/1.44G [00:01<00:01, 682MB/s]
pytorch_model.bin:  60%|██████    | 868M/1.44G [00:01<00:00, 840MB/s]
pytorch_model.bin:  79%|███████▉  | 1.14G/1.44G [00:01<00:00, 1.28GB/s]
pytorch_model.bin:  99%|█████████▉| 1.43G/1.44G [00:01<00:00, 1.29GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 811MB/s] 
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Saving duration: 0.501s
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.277s
fizzarolli-llama-3-lust-3078-v1-mkmlizer: creating bucket guanaco-reward-models
fizzarolli-llama-3-lust-3078-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fizzarolli-llama-3-lust-3078-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/config.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/tokenizer_config.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/special_tokens_map.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/vocab.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/merges.txt
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/tokenizer.json
fizzarolli-llama-3-lust-3078-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fizzarolli-llama-3-lust-3078-v1_reward/reward.tensors
Job fizzarolli-llama-3-lust-3078-v1-mkmlizer completed after 84.64s with status: succeeded
Stopping job with name fizzarolli-llama-3-lust-3078-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service fizzarolli-llama-3-lust-3078-v1
Waiting for inference service fizzarolli-llama-3-lust-3078-v1 to be ready
Inference service fizzarolli-llama-3-lust-3078-v1 ready after 40.24237394332886s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2410037517547607s
Received healthy response to inference request in 0.9579777717590332s
Received healthy response to inference request in 0.8372979164123535s
Received healthy response to inference request in 1.6908433437347412s
Received healthy response to inference request in 1.17756986618042s
5 requests
0 failed requests
5th percentile: 0.8614338874816895
10th percentile: 0.8855698585510254
20th percentile: 0.9338418006896972
30th percentile: 1.0018961906433106
40th percentile: 1.0897330284118651
50th percentile: 1.17756986618042
60th percentile: 1.2029434204101563
70th percentile: 1.2283169746398925
80th percentile: 1.330971670150757
90th percentile: 1.5109075069427491
95th percentile: 1.600875425338745
99th percentile: 1.6728497600555419
mean time: 1.1809385299682618
Pipeline stage StressChecker completed in 6.82s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.11s
fizzarolli-llama-3-lust-_3078_v1 status is now deployed due to DeploymentManager action
fizzarolli-llama-3-lust-_3078_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of fizzarolli-llama-3-lust-_3078_v1
deverdever-heavenly-goat-v8_v2 status is now torndown due to DeploymentManager action
Running pipeline stage ISVCDeleter
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Checking if service fizzarolli-llama-3-lust-3078-v1 is running
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key dreamgen-opus-v1-2-llama-3-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.34s
dreamgen-opus-v1-2-llama-3-8b_v3 status is now torndown due to DeploymentManager action
Tearing down inference service fizzarolli-llama-3-lust-3078-v1
Toredown service fizzarolli-llama-3-lust-3078-v1
Pipeline stage ISVCDeleter completed in 3.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-3078-v1/config.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-3078-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-3078-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-3078-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key fizzarolli-llama-3-lust-3078-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key fizzarolli-llama-3-lust-3078-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.19s
fizzarolli-llama-3-lust-_3078_v1 status is now torndown due to DeploymentManager action