submission_id: grimjim-kukulemon-spiked-9b_v1
developer_uid: grimjim.
status: torndown
model_repo: grimjim/kukulemon-spiked-9B
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: 2024-04-05T03:06:49+00:00
model_name: grimjim-kukulemon-spiked-9b_v1
model_eval_status: success
model_group: grimjim/kukulemon-spiked
num_battles: 168272
num_wins: 84843
celo_rating: 1162.26
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 8986628096.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: grimjim-kukulemon-spiked-9b_v1
ineligible_reason: propriety_total_count < 800
language_model: grimjim/kukulemon-spiked-9B
model_size: 9B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-04
win_ratio: 0.5042015308548065
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name grimjim-kukulemon-spiked-9b-v1-mkmlizer
Waiting for job on grimjim-kukulemon-spiked-9b-v1-mkmlizer to finish
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║     _____            __           __                                ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║       /___/                                                         ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║                                                                     ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  Version: 0.6.11                                                    ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║                                                                     ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  belonging to:                                                      ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║                                                                     ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ║                                                                     ║
grimjim-kukulemon-spiked-9b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.56k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.56k/1.56k [00:00<00:00, 17.8MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
mergekit_config.yml:   0%|          | 0.00/272 [00:00<?, ?B/s]
mergekit_config.yml: 100%|██████████| 272/272 [00:00<00:00, 2.41MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
model-00001-of-00002.safetensors:   0%|          | 0.00/10.0G [00:00<?, ?B/s]
model-00001-of-00002.safetensors:   0%|          | 10.5M/10.0G [00:01<20:08, 8.27MB/s]
model-00001-of-00002.safetensors:   0%|          | 31.5M/10.0G [00:01<05:47, 28.7MB/s]
model-00001-of-00002.safetensors:   1%|          | 62.9M/10.0G [00:01<02:33, 64.6MB/s]
model-00001-of-00002.safetensors:   1%|          | 94.4M/10.0G [00:01<01:44, 94.5MB/s]
model-00001-of-00002.safetensors:   1%|▏         | 126M/10.0G [00:01<01:17, 127MB/s]  
model-00001-of-00002.safetensors:   2%|▏         | 157M/10.0G [00:01<01:03, 156MB/s]
model-00001-of-00002.safetensors:   2%|▏         | 189M/10.0G [00:02<01:00, 163MB/s]
model-00001-of-00002.safetensors:   2%|▏         | 220M/10.0G [00:02<00:59, 163MB/s]
model-00001-of-00002.safetensors:   3%|▎         | 252M/10.0G [00:02<00:50, 193MB/s]
model-00001-of-00002.safetensors:   3%|▎         | 283M/10.0G [00:02<00:47, 203MB/s]
model-00001-of-00002.safetensors:   3%|▎         | 315M/10.0G [00:02<00:51, 188MB/s]
model-00001-of-00002.safetensors:   4%|▍         | 377M/10.0G [00:02<00:34, 275MB/s]
model-00001-of-00002.safetensors:   6%|▋         | 640M/10.0G [00:02<00:14, 640MB/s]
model-00001-of-00002.safetensors:   8%|▊         | 828M/10.0G [00:03<00:10, 887MB/s]
model-00001-of-00002.safetensors:  13%|█▎        | 1.32G/10.0G [00:03<00:05, 1.73GB/s]
model-00001-of-00002.safetensors:  15%|█▌        | 1.52G/10.0G [00:03<00:08, 978MB/s] 
model-00001-of-00002.safetensors:  17%|█▋        | 1.68G/10.0G [00:03<00:09, 911MB/s]
model-00001-of-00002.safetensors:  18%|█▊        | 1.81G/10.0G [00:04<00:09, 880MB/s]
model-00001-of-00002.safetensors:  19%|█▉        | 1.94G/10.0G [00:04<00:08, 932MB/s]
model-00001-of-00002.safetensors:  21%|██        | 2.06G/10.0G [00:04<00:08, 951MB/s]
model-00001-of-00002.safetensors:  22%|██▏       | 2.17G/10.0G [00:04<00:07, 990MB/s]
model-00001-of-00002.safetensors:  23%|██▎       | 2.29G/10.0G [00:04<00:07, 978MB/s]
model-00001-of-00002.safetensors:  24%|██▍       | 2.40G/10.0G [00:04<00:08, 925MB/s]
model-00001-of-00002.safetensors:  25%|██▌       | 2.51G/10.0G [00:04<00:09, 796MB/s]
model-00001-of-00002.safetensors:  26%|██▌       | 2.61G/10.0G [00:04<00:08, 838MB/s]
model-00001-of-00002.safetensors:  27%|██▋       | 2.73G/10.0G [00:05<00:08, 827MB/s]
model-00001-of-00002.safetensors:  28%|██▊       | 2.84G/10.0G [00:05<00:08, 891MB/s]
model-00001-of-00002.safetensors:  30%|███       | 3.01G/10.0G [00:05<00:06, 1.07GB/s]
model-00001-of-00002.safetensors:  32%|███▏      | 3.23G/10.0G [00:05<00:05, 1.35GB/s]
model-00001-of-00002.safetensors:  34%|███▍      | 3.38G/10.0G [00:05<00:04, 1.36GB/s]
model-00001-of-00002.safetensors:  35%|███▌      | 3.54G/10.0G [00:05<00:04, 1.40GB/s]
model-00001-of-00002.safetensors:  37%|███▋      | 3.69G/10.0G [00:05<00:05, 1.22GB/s]
model-00001-of-00002.safetensors:  42%|████▏     | 4.20G/10.0G [00:05<00:02, 2.20GB/s]
model-00001-of-00002.safetensors:  45%|████▍     | 4.46G/10.0G [00:06<00:02, 1.90GB/s]
model-00001-of-00002.safetensors:  47%|████▋     | 4.68G/10.0G [00:06<00:04, 1.33GB/s]
model-00001-of-00002.safetensors:  49%|████▊     | 4.85G/10.0G [00:06<00:03, 1.33GB/s]
model-00001-of-00002.safetensors:  50%|█████     | 5.02G/10.0G [00:06<00:03, 1.40GB/s]
model-00001-of-00002.safetensors:  53%|█████▎    | 5.25G/10.0G [00:06<00:03, 1.56GB/s]
model-00001-of-00002.safetensors:  54%|█████▍    | 5.43G/10.0G [00:06<00:02, 1.61GB/s]
model-00001-of-00002.safetensors:  57%|█████▋    | 5.66G/10.0G [00:06<00:02, 1.75GB/s]
model-00001-of-00002.safetensors:  59%|█████▊    | 5.86G/10.0G [00:07<00:02, 1.80GB/s]
model-00001-of-00002.safetensors:  61%|██████    | 6.06G/10.0G [00:07<00:02, 1.77GB/s]
model-00001-of-00002.safetensors:  62%|██████▏   | 6.25G/10.0G [00:07<00:02, 1.76GB/s]
model-00001-of-00002.safetensors:  64%|██████▍   | 6.44G/10.0G [00:07<00:02, 1.71GB/s]
model-00001-of-00002.safetensors:  66%|██████▌   | 6.62G/10.0G [00:07<00:02, 1.56GB/s]
model-00001-of-00002.safetensors:  68%|██████▊   | 6.78G/10.0G [00:07<00:02, 1.57GB/s]
model-00001-of-00002.safetensors:  70%|██████▉   | 6.96G/10.0G [00:07<00:01, 1.62GB/s]
model-00001-of-00002.safetensors:  71%|███████▏  | 7.13G/10.0G [00:07<00:01, 1.60GB/s]
model-00001-of-00002.safetensors:  73%|███████▎  | 7.30G/10.0G [00:07<00:01, 1.54GB/s]
model-00001-of-00002.safetensors:  76%|███████▌  | 7.57G/10.0G [00:08<00:01, 1.79GB/s]
model-00001-of-00002.safetensors:  78%|███████▊  | 7.76G/10.0G [00:08<00:01, 1.74GB/s]
model-00001-of-00002.safetensors:  79%|███████▉  | 7.94G/10.0G [00:08<00:01, 1.63GB/s]
model-00001-of-00002.safetensors:  81%|████████  | 8.11G/10.0G [00:08<00:01, 1.43GB/s]
model-00001-of-00002.safetensors:  83%|████████▎ | 8.26G/10.0G [00:08<00:01, 1.21GB/s]
model-00001-of-00002.safetensors:  84%|████████▍ | 8.40G/10.0G [00:08<00:01, 1.21GB/s]
model-00001-of-00002.safetensors:  85%|████████▌ | 8.54G/10.0G [00:08<00:01, 1.14GB/s]
model-00001-of-00002.safetensors:  87%|████████▋ | 8.67G/10.0G [00:09<00:01, 1.13GB/s]
model-00001-of-00002.safetensors:  88%|████████▊ | 8.79G/10.0G [00:09<00:01, 1.13GB/s]
model-00001-of-00002.safetensors:  90%|████████▉ | 8.95G/10.0G [00:09<00:00, 1.24GB/s]
model-00001-of-00002.safetensors:  91%|█████████▏| 9.14G/10.0G [00:09<00:00, 1.38GB/s]
model-00001-of-00002.safetensors:  94%|█████████▍| 9.38G/10.0G [00:09<00:00, 1.51GB/s]
model-00001-of-00002.safetensors:  96%|█████████▌| 9.57G/10.0G [00:09<00:00, 1.60GB/s]
model-00001-of-00002.safetensors:  97%|█████████▋| 9.74G/10.0G [00:09<00:00, 1.57GB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 10.0G/10.0G [00:09<00:00, 1.62GB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 10.0G/10.0G [00:15<00:00, 659MB/s] 
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
model-00002-of-00002.safetensors:   0%|          | 0.00/7.97G [00:00<?, ?B/s]
model-00002-of-00002.safetensors:   0%|          | 10.5M/7.97G [00:02<31:56, 4.16MB/s]
model-00002-of-00002.safetensors:   1%|          | 62.9M/7.97G [00:02<04:07, 32.0MB/s]
model-00002-of-00002.safetensors:   4%|▍         | 304M/7.97G [00:02<00:39, 196MB/s]  
model-00002-of-00002.safetensors:   5%|▌         | 409M/7.97G [00:03<00:31, 242MB/s]
model-00002-of-00002.safetensors:  12%|█▏        | 954M/7.97G [00:03<00:09, 743MB/s]
model-00002-of-00002.safetensors:  14%|█▍        | 1.14G/7.97G [00:03<00:12, 544MB/s]
model-00002-of-00002.safetensors:  16%|█▌        | 1.28G/7.97G [00:04<00:13, 479MB/s]
model-00002-of-00002.safetensors:  17%|█▋        | 1.38G/7.97G [00:04<00:17, 375MB/s]
model-00002-of-00002.safetensors:  18%|█▊        | 1.47G/7.97G [00:04<00:17, 378MB/s]
model-00002-of-00002.safetensors:  20%|██        | 1.61G/7.97G [00:05<00:13, 479MB/s]
model-00002-of-00002.safetensors:  24%|██▍       | 1.94G/7.97G [00:05<00:07, 784MB/s]
model-00002-of-00002.safetensors:  26%|██▌       | 2.07G/7.97G [00:05<00:07, 792MB/s]
model-00002-of-00002.safetensors:  27%|██▋       | 2.18G/7.97G [00:05<00:07, 819MB/s]
model-00002-of-00002.safetensors:  29%|██▉       | 2.30G/7.97G [00:05<00:07, 800MB/s]
model-00002-of-00002.safetensors:  34%|███▍      | 2.69G/7.97G [00:05<00:03, 1.37GB/s]
model-00002-of-00002.safetensors:  37%|███▋      | 2.98G/7.97G [00:05<00:03, 1.63GB/s]
model-00002-of-00002.safetensors:  42%|████▏     | 3.36G/7.97G [00:05<00:02, 2.10GB/s]
model-00002-of-00002.safetensors:  45%|████▌     | 3.61G/7.97G [00:06<00:03, 1.43GB/s]
model-00002-of-00002.safetensors:  48%|████▊     | 3.81G/7.97G [00:06<00:03, 1.35GB/s]
model-00002-of-00002.safetensors:  50%|████▉     | 3.98G/7.97G [00:06<00:03, 1.33GB/s]
model-00002-of-00002.safetensors:  52%|█████▏    | 4.15G/7.97G [00:06<00:02, 1.33GB/s]
model-00002-of-00002.safetensors:  54%|█████▍    | 4.31G/7.97G [00:06<00:02, 1.25GB/s]
model-00002-of-00002.safetensors:  56%|█████▌    | 4.46G/7.97G [00:07<00:03, 1.12GB/s]
model-00002-of-00002.safetensors:  59%|█████▉    | 4.72G/7.97G [00:07<00:02, 1.42GB/s]
model-00002-of-00002.safetensors:  61%|██████▏   | 4.89G/7.97G [00:07<00:02, 1.35GB/s]
model-00002-of-00002.safetensors:  64%|██████▎   | 5.08G/7.97G [00:07<00:01, 1.46GB/s]
model-00002-of-00002.safetensors:  66%|██████▌   | 5.24G/7.97G [00:07<00:01, 1.37GB/s]
model-00002-of-00002.safetensors:  68%|██████▊   | 5.39G/7.97G [00:07<00:02, 1.15GB/s]
model-00002-of-00002.safetensors:  69%|██████▉   | 5.52G/7.97G [00:07<00:02, 1.07GB/s]
model-00002-of-00002.safetensors:  72%|███████▏  | 5.70G/7.97G [00:07<00:01, 1.25GB/s]
model-00002-of-00002.safetensors:  73%|███████▎  | 5.84G/7.97G [00:08<00:01, 1.25GB/s]
model-00002-of-00002.safetensors:  75%|███████▌  | 5.99G/7.97G [00:08<00:01, 1.27GB/s]
model-00002-of-00002.safetensors:  78%|███████▊  | 6.21G/7.97G [00:08<00:01, 1.46GB/s]
model-00002-of-00002.safetensors:  80%|████████  | 6.40G/7.97G [00:08<00:01, 1.54GB/s]
model-00002-of-00002.safetensors:  83%|████████▎ | 6.64G/7.97G [00:08<00:00, 1.75GB/s]
model-00002-of-00002.safetensors:  86%|████████▌ | 6.83G/7.97G [00:08<00:00, 1.54GB/s]
model-00002-of-00002.safetensors:  88%|████████▊ | 6.99G/7.97G [00:08<00:00, 1.39GB/s]
model-00002-of-00002.safetensors:  90%|████████▉ | 7.14G/7.97G [00:08<00:00, 1.40GB/s]
model-00002-of-00002.safetensors:  92%|█████████▏| 7.34G/7.97G [00:09<00:00, 1.50GB/s]
model-00002-of-00002.safetensors:  95%|█████████▍| 7.56G/7.97G [00:09<00:00, 1.69GB/s]
model-00002-of-00002.safetensors:  97%|█████████▋| 7.76G/7.97G [00:09<00:00, 1.71GB/s]
model-00002-of-00002.safetensors: 100%|█████████▉| 7.94G/7.97G [00:09<00:00, 1.52GB/s]
model-00002-of-00002.safetensors: 100%|█████████▉| 7.97G/7.97G [00:10<00:00, 789MB/s] 
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/28.5k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 28.5k/28.5k [00:00<00:00, 203MB/s]
grimjim-kukulemon-spiked-9b-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, 3.66MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 11.1MB/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 11.1MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 41.0MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/967 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 15.7MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Downloaded to shared memory in 35.865s
grimjim-kukulemon-spiked-9b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Saving mkml model at /dev/shm/model_cache
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Reading /tmp/tmpgxsezsxc/model.safetensors.index.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
Profiling:   0%|          | 0/363 [00:00<?, ?it/s]
Profiling:   0%|          | 1/363 [00:00<01:32,  3.90it/s]
Profiling:   4%|▎         | 13/363 [00:00<00:07, 44.14it/s]
Profiling:  10%|█         | 38/363 [00:00<00:02, 109.01it/s]
Profiling:  16%|█▌        | 58/363 [00:00<00:02, 133.32it/s]
Profiling:  23%|██▎       | 83/363 [00:00<00:01, 163.09it/s]
Profiling:  28%|██▊       | 102/363 [00:00<00:01, 167.12it/s]
Profiling:  33%|███▎      | 121/363 [00:00<00:01, 173.02it/s]
Profiling:  40%|████      | 146/363 [00:01<00:01, 191.05it/s]
Profiling:  46%|████▌     | 166/363 [00:01<00:01, 188.06it/s]
Profiling:  52%|█████▏    | 188/363 [00:01<00:00, 197.18it/s]
Profiling:  58%|█████▊    | 209/363 [00:04<00:06, 22.52it/s] 
Profiling:  63%|██████▎   | 229/363 [00:04<00:04, 30.31it/s]
Profiling:  69%|██████▉   | 251/363 [00:04<00:02, 41.59it/s]
Profiling:  75%|███████▍  | 272/363 [00:04<00:01, 54.61it/s]
Profiling:  80%|████████  | 292/363 [00:04<00:01, 68.71it/s]
Profiling:  87%|████████▋ | 317/363 [00:04<00:00, 90.66it/s]
Profiling:  93%|█████████▎| 337/363 [00:04<00:00, 105.31it/s]
Profiling:  99%|█████████▉| 359/363 [00:04<00:00, 125.24it/s]
Profiling: 100%|██████████| 363/363 [00:05<00:00, 70.88it/s] 
grimjim-kukulemon-spiked-9b-v1-mkmlizer: quantized model in 17.175s
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Processed model grimjim/kukulemon-spiked-9B in 54.092s
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/grimjim-kukulemon-spiked-9b-v1/mkml_model.tensors
grimjim-kukulemon-spiked-9b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
grimjim-kukulemon-spiked-9b-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.
grimjim-kukulemon-spiked-9b-v1-mkmlizer:   warnings.warn(
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.2MB/s]
grimjim-kukulemon-spiked-9b-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.
grimjim-kukulemon-spiked-9b-v1-mkmlizer:   warnings.warn(
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.32MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 42.7MB/s]
grimjim-kukulemon-spiked-9b-v1-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.5MB/s]
grimjim-kukulemon-spiked-9b-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.
grimjim-kukulemon-spiked-9b-v1-mkmlizer:   warnings.warn(
grimjim-kukulemon-spiked-9b-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, 168MB/s]
pytorch_model.bin:   4%|▍         | 62.9M/1.44G [00:00<00:07, 182MB/s]
pytorch_model.bin:   9%|▊         | 126M/1.44G [00:00<00:04, 315MB/s] 
pytorch_model.bin:  16%|█▌        | 231M/1.44G [00:00<00:02, 537MB/s]
pytorch_model.bin:  20%|██        | 294M/1.44G [00:00<00:02, 405MB/s]
pytorch_model.bin:  24%|██▍       | 346M/1.44G [00:01<00:03, 317MB/s]
pytorch_model.bin:  28%|██▊       | 409M/1.44G [00:01<00:02, 376MB/s]
pytorch_model.bin:  40%|███▉      | 577M/1.44G [00:01<00:01, 659MB/s]
pytorch_model.bin:  85%|████████▍ | 1.23G/1.44G [00:01<00:00, 2.05GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:10<00:00, 138MB/s] 
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-kukulemon-spiked-9b-v1-mkmlizer: creating bucket guanaco-reward-models
grimjim-kukulemon-spiked-9b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
grimjim-kukulemon-spiked-9b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/config.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/special_tokens_map.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/merges.txt
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/tokenizer_config.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/vocab.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/tokenizer.json
grimjim-kukulemon-spiked-9b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-kukulemon-spiked-9b-v1_reward/reward.tensors
Job grimjim-kukulemon-spiked-9b-v1-mkmlizer completed after 95.16s with status: succeeded
Stopping job with name grimjim-kukulemon-spiked-9b-v1-mkmlizer
Pipeline stage MKMLizer completed in 99.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-kukulemon-spiked-9b-v1
Waiting for inference service grimjim-kukulemon-spiked-9b-v1 to be ready
Inference service grimjim-kukulemon-spiked-9b-v1 ready after 40.287622690200806s
Pipeline stage ISVCDeployer completed in 47.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.501786708831787s
Received healthy response to inference request in 1.1252334117889404s
Received healthy response to inference request in 1.281430721282959s
Received healthy response to inference request in 1.0450403690338135s
Received healthy response to inference request in 1.2689876556396484s
5 requests
0 failed requests
5th percentile: 1.0610789775848388
10th percentile: 1.0771175861358642
20th percentile: 1.109194803237915
30th percentile: 1.153984260559082
40th percentile: 1.2114859580993653
50th percentile: 1.2689876556396484
60th percentile: 1.2739648818969727
70th percentile: 1.2789421081542969
80th percentile: 1.3255019187927246
90th percentile: 1.4136443138122559
95th percentile: 1.4577155113220215
99th percentile: 1.492972469329834
mean time: 1.2444957733154296
Pipeline stage StressChecker completed in 7.29s
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 0.08s
grimjim-kukulemon-spiked-9b_v1 status is now deployed due to DeploymentManager action
grimjim-kukulemon-spiked-9b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of grimjim-kukulemon-spiked-9b_v1
Running pipeline stage ISVCDeleter
Checking if service grimjim-kukulemon-spiked-9b-v1 is running
Tearing down inference service grimjim-kukulemon-spiked-9b-v1
Toredown service grimjim-kukulemon-spiked-9b-v1
Pipeline stage ISVCDeleter completed in 3.28s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key grimjim-kukulemon-spiked-9b-v1/config.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-spiked-9b-v1/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-spiked-9b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-spiked-9b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-spiked-9b-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key grimjim-kukulemon-spiked-9b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key grimjim-kukulemon-spiked-9b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.10s
grimjim-kukulemon-spiked-9b_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics