submission_id: huggyllama-llama-7b_v172
developer_uid: chai_backend_admin
status: rejected
model_repo: huggyllama/llama-7b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, '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: 2024-04-02T16:15:37+00:00
model_name: auto_submit_ricum_wamobetame
model_eval_status: success
model_group: huggyllama/llama-7b
num_battles: 43
num_wins: 19
celo_rating: None
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
display_name: auto_submit_ricum_wamobetame
ineligible_reason: model is not deployable
language_model: huggyllama/llama-7b
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-02
win_ratio: 0.4418604651162791
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name huggyllama-llama-7b-v172-mkmlizer
Waiting for job on huggyllama-llama-7b-v172-mkmlizer to finish
huggyllama-llama-7b-v172-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
huggyllama-llama-7b-v172-mkmlizer: ║     _____            __           __                                ║
huggyllama-llama-7b-v172-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
huggyllama-llama-7b-v172-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
huggyllama-llama-7b-v172-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
huggyllama-llama-7b-v172-mkmlizer: ║       /___/                                                         ║
huggyllama-llama-7b-v172-mkmlizer: ║                                                                     ║
huggyllama-llama-7b-v172-mkmlizer: ║  Version: 0.6.11                                                    ║
huggyllama-llama-7b-v172-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
huggyllama-llama-7b-v172-mkmlizer: ║                                                                     ║
huggyllama-llama-7b-v172-mkmlizer: ║  The license key for the current software has been verified as      ║
huggyllama-llama-7b-v172-mkmlizer: ║  belonging to:                                                      ║
huggyllama-llama-7b-v172-mkmlizer: ║                                                                     ║
huggyllama-llama-7b-v172-mkmlizer: ║  Chai Research Corp.                                                ║
huggyllama-llama-7b-v172-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
huggyllama-llama-7b-v172-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
huggyllama-llama-7b-v172-mkmlizer: ║                                                                     ║
huggyllama-llama-7b-v172-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
huggyllama-llama-7b-v172-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.48k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.48k/1.48k [00:00<00:00, 15.0MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
LICENSE:   0%|          | 0.00/10.6k [00:00<?, ?B/s]
LICENSE: 100%|██████████| 10.6k/10.6k [00:00<00:00, 67.1MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
README.md:   0%|          | 0.00/472 [00:00<?, ?B/s]
README.md: 100%|██████████| 472/472 [00:00<00:00, 3.91MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
config.json:   0%|          | 0.00/594 [00:00<?, ?B/s]
config.json: 100%|██████████| 594/594 [00:00<00:00, 3.21MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
generation_config.json:   0%|          | 0.00/137 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 137/137 [00:00<00:00, 1.07MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
model-00001-of-00002.safetensors:   0%|          | 0.00/9.98G [00:00<?, ?B/s]
model-00001-of-00002.safetensors:   0%|          | 10.5M/9.98G [00:00<12:50, 12.9MB/s]
model-00001-of-00002.safetensors:   0%|          | 21.0M/9.98G [00:01<08:29, 19.5MB/s]
model-00001-of-00002.safetensors:   0%|          | 31.5M/9.98G [00:01<06:34, 25.2MB/s]
model-00001-of-00002.safetensors:   1%|          | 94.4M/9.98G [00:01<01:33, 105MB/s] 
model-00001-of-00002.safetensors:   2%|▏         | 220M/9.98G [00:01<00:39, 245MB/s] 
model-00001-of-00002.safetensors:   3%|▎         | 262M/9.98G [00:01<00:40, 240MB/s]
model-00001-of-00002.safetensors:   3%|▎         | 304M/9.98G [00:02<00:39, 247MB/s]
model-00001-of-00002.safetensors:   4%|▍         | 409M/9.98G [00:02<00:26, 359MB/s]
model-00001-of-00002.safetensors:   5%|▍         | 461M/9.98G [00:02<00:34, 274MB/s]
model-00001-of-00002.safetensors:   5%|▌         | 503M/9.98G [00:02<00:32, 291MB/s]
model-00001-of-00002.safetensors:   7%|▋         | 661M/9.98G [00:02<00:18, 517MB/s]
model-00001-of-00002.safetensors:   7%|▋         | 734M/9.98G [00:02<00:17, 538MB/s]
model-00001-of-00002.safetensors:   8%|▊         | 807M/9.98G [00:03<00:18, 509MB/s]
model-00001-of-00002.safetensors:   9%|▊         | 870M/9.98G [00:03<00:24, 372MB/s]
model-00001-of-00002.safetensors:   9%|▉         | 923M/9.98G [00:03<00:23, 378MB/s]
model-00001-of-00002.safetensors:  10%|▉         | 975M/9.98G [00:03<00:23, 381MB/s]
model-00001-of-00002.safetensors:  12%|█▏        | 1.15G/9.98G [00:03<00:13, 652MB/s]
model-00001-of-00002.safetensors:  15%|█▌        | 1.54G/9.98G [00:03<00:06, 1.37GB/s]
model-00001-of-00002.safetensors:  19%|█▊        | 1.86G/9.98G [00:03<00:04, 1.79GB/s]
model-00001-of-00002.safetensors:  21%|██        | 2.08G/9.98G [00:04<00:05, 1.48GB/s]
model-00001-of-00002.safetensors:  23%|██▎       | 2.26G/9.98G [00:04<00:06, 1.14GB/s]
model-00001-of-00002.safetensors:  24%|██▍       | 2.42G/9.98G [00:04<00:06, 1.12GB/s]
model-00001-of-00002.safetensors:  26%|██▌       | 2.59G/9.98G [00:04<00:06, 1.22GB/s]
model-00001-of-00002.safetensors:  27%|██▋       | 2.74G/9.98G [00:04<00:07, 933MB/s] 
model-00001-of-00002.safetensors:  29%|██▊       | 2.86G/9.98G [00:05<00:07, 985MB/s]
model-00001-of-00002.safetensors:  30%|██▉       | 2.99G/9.98G [00:05<00:07, 917MB/s]
model-00001-of-00002.safetensors:  31%|███       | 3.09G/9.98G [00:05<00:07, 907MB/s]
model-00001-of-00002.safetensors:  33%|███▎      | 3.32G/9.98G [00:05<00:05, 1.21GB/s]
model-00001-of-00002.safetensors:  35%|███▍      | 3.47G/9.98G [00:05<00:05, 1.16GB/s]
model-00001-of-00002.safetensors:  37%|███▋      | 3.72G/9.98G [00:05<00:04, 1.47GB/s]
model-00001-of-00002.safetensors:  39%|███▉      | 3.89G/9.98G [00:05<00:04, 1.33GB/s]
model-00001-of-00002.safetensors:  40%|████      | 4.04G/9.98G [00:05<00:04, 1.29GB/s]
model-00001-of-00002.safetensors:  42%|████▏     | 4.23G/9.98G [00:06<00:04, 1.42GB/s]
model-00001-of-00002.safetensors:  44%|████▍     | 4.38G/9.98G [00:06<00:04, 1.30GB/s]
model-00001-of-00002.safetensors:  46%|████▌     | 4.59G/9.98G [00:06<00:03, 1.48GB/s]
model-00001-of-00002.safetensors:  48%|████▊     | 4.76G/9.98G [00:06<00:03, 1.48GB/s]
model-00001-of-00002.safetensors:  49%|████▉     | 4.92G/9.98G [00:06<00:03, 1.27GB/s]
model-00001-of-00002.safetensors:  51%|█████     | 5.05G/9.98G [00:06<00:03, 1.28GB/s]
model-00001-of-00002.safetensors:  52%|█████▏    | 5.19G/9.98G [00:06<00:04, 1.15GB/s]
model-00001-of-00002.safetensors:  53%|█████▎    | 5.34G/9.98G [00:07<00:04, 1.11GB/s]
model-00001-of-00002.safetensors:  55%|█████▍    | 5.45G/9.98G [00:07<00:04, 975MB/s] 
model-00001-of-00002.safetensors:  56%|█████▌    | 5.60G/9.98G [00:07<00:04, 1.06GB/s]
model-00001-of-00002.safetensors:  58%|█████▊    | 5.83G/9.98G [00:07<00:03, 1.33GB/s]
model-00001-of-00002.safetensors:  61%|██████    | 6.05G/9.98G [00:07<00:02, 1.52GB/s]
model-00001-of-00002.safetensors:  62%|██████▏   | 6.22G/9.98G [00:07<00:02, 1.33GB/s]
model-00001-of-00002.safetensors:  64%|██████▍   | 6.38G/9.98G [00:07<00:02, 1.37GB/s]
model-00001-of-00002.safetensors:  65%|██████▌   | 6.52G/9.98G [00:07<00:02, 1.16GB/s]
model-00001-of-00002.safetensors:  67%|██████▋   | 6.65G/9.98G [00:08<00:03, 889MB/s] 
model-00001-of-00002.safetensors:  68%|██████▊   | 6.75G/9.98G [00:08<00:03, 874MB/s]
model-00001-of-00002.safetensors:  69%|██████▊   | 6.86G/9.98G [00:08<00:03, 793MB/s]
model-00001-of-00002.safetensors:  70%|██████▉   | 6.96G/9.98G [00:08<00:03, 841MB/s]
model-00001-of-00002.safetensors:  71%|███████   | 7.06G/9.98G [00:08<00:03, 836MB/s]
model-00001-of-00002.safetensors:  72%|███████▏  | 7.16G/9.98G [00:08<00:03, 853MB/s]
model-00001-of-00002.safetensors:  73%|███████▎  | 7.26G/9.98G [00:08<00:03, 804MB/s]
model-00001-of-00002.safetensors:  74%|███████▎  | 7.34G/9.98G [00:09<00:03, 775MB/s]
model-00001-of-00002.safetensors:  74%|███████▍  | 7.42G/9.98G [00:09<00:03, 712MB/s]
model-00001-of-00002.safetensors:  76%|███████▋  | 7.61G/9.98G [00:09<00:02, 979MB/s]
model-00001-of-00002.safetensors:  77%|███████▋  | 7.72G/9.98G [00:09<00:02, 980MB/s]
model-00001-of-00002.safetensors:  78%|███████▊  | 7.82G/9.98G [00:09<00:02, 961MB/s]
model-00001-of-00002.safetensors:  79%|███████▉  | 7.93G/9.98G [00:09<00:02, 870MB/s]
model-00001-of-00002.safetensors:  81%|████████  | 8.10G/9.98G [00:09<00:01, 1.07GB/s]
model-00001-of-00002.safetensors:  84%|████████▎ | 8.35G/9.98G [00:09<00:01, 1.45GB/s]
model-00001-of-00002.safetensors:  85%|████████▌ | 8.50G/9.98G [00:10<00:01, 1.38GB/s]
model-00001-of-00002.safetensors:  87%|████████▋ | 8.70G/9.98G [00:10<00:00, 1.48GB/s]
model-00001-of-00002.safetensors:  89%|████████▉ | 8.89G/9.98G [00:10<00:00, 1.56GB/s]
model-00001-of-00002.safetensors:  91%|█████████ | 9.06G/9.98G [00:10<00:00, 1.44GB/s]
model-00001-of-00002.safetensors:  92%|█████████▏| 9.22G/9.98G [00:10<00:00, 1.33GB/s]
model-00001-of-00002.safetensors:  94%|█████████▍| 9.41G/9.98G [00:10<00:00, 1.47GB/s]
model-00001-of-00002.safetensors:  96%|█████████▌| 9.58G/9.98G [00:10<00:00, 1.54GB/s]
model-00001-of-00002.safetensors:  98%|█████████▊| 9.82G/9.98G [00:10<00:00, 1.76GB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 9.98G/9.98G [00:11<00:00, 880MB/s] 
huggyllama-llama-7b-v172-mkmlizer: 
model-00002-of-00002.safetensors:   0%|          | 0.00/3.50G [00:00<?, ?B/s]
model-00002-of-00002.safetensors:   0%|          | 10.5M/3.50G [00:01<08:16, 7.04MB/s]
model-00002-of-00002.safetensors:   1%|          | 41.9M/3.50G [00:01<01:44, 33.2MB/s]
model-00002-of-00002.safetensors:   2%|▏         | 73.4M/3.50G [00:01<00:56, 61.2MB/s]
model-00002-of-00002.safetensors:   3%|▎         | 94.4M/3.50G [00:01<00:47, 71.2MB/s]
model-00002-of-00002.safetensors:   4%|▎         | 126M/3.50G [00:02<00:35, 95.7MB/s] 
model-00002-of-00002.safetensors:   4%|▍         | 147M/3.50G [00:02<00:32, 104MB/s] 
model-00002-of-00002.safetensors:   5%|▍         | 168M/3.50G [00:02<00:37, 88.5MB/s]
model-00002-of-00002.safetensors:   6%|▌         | 199M/3.50G [00:02<00:28, 117MB/s] 
model-00002-of-00002.safetensors:   7%|▋         | 231M/3.50G [00:02<00:23, 140MB/s]
model-00002-of-00002.safetensors:   8%|▊         | 283M/3.50G [00:02<00:15, 207MB/s]
model-00002-of-00002.safetensors:  10%|▉         | 336M/3.50G [00:03<00:12, 263MB/s]
model-00002-of-00002.safetensors:  11%|█         | 377M/3.50G [00:03<00:11, 268MB/s]
model-00002-of-00002.safetensors:  12%|█▏        | 409M/3.50G [00:03<00:12, 250MB/s]
model-00002-of-00002.safetensors:  14%|█▍        | 493M/3.50G [00:03<00:08, 364MB/s]
model-00002-of-00002.safetensors:  17%|█▋        | 587M/3.50G [00:03<00:05, 492MB/s]
model-00002-of-00002.safetensors:  32%|███▏      | 1.13G/3.50G [00:03<00:01, 1.71GB/s]
model-00002-of-00002.safetensors:  41%|████▏     | 1.45G/3.50G [00:03<00:01, 2.03GB/s]
model-00002-of-00002.safetensors:  48%|████▊     | 1.68G/3.50G [00:04<00:02, 820MB/s] 
model-00002-of-00002.safetensors:  53%|█████▎    | 1.86G/3.50G [00:04<00:02, 816MB/s]
model-00002-of-00002.safetensors:  57%|█████▋    | 2.00G/3.50G [00:04<00:01, 775MB/s]
model-00002-of-00002.safetensors:  61%|██████    | 2.13G/3.50G [00:05<00:01, 722MB/s]
model-00002-of-00002.safetensors:  64%|██████▍   | 2.23G/3.50G [00:05<00:01, 743MB/s]
model-00002-of-00002.safetensors:  67%|██████▋   | 2.34G/3.50G [00:05<00:01, 591MB/s]
model-00002-of-00002.safetensors:  69%|██████▉   | 2.43G/3.50G [00:05<00:01, 636MB/s]
model-00002-of-00002.safetensors:  72%|███████▏  | 2.52G/3.50G [00:05<00:01, 567MB/s]
model-00002-of-00002.safetensors:  74%|███████▍  | 2.59G/3.50G [00:06<00:01, 548MB/s]
model-00002-of-00002.safetensors:  76%|███████▌  | 2.66G/3.50G [00:06<00:01, 578MB/s]
model-00002-of-00002.safetensors:  87%|████████▋ | 3.03G/3.50G [00:06<00:00, 1.23GB/s]
model-00002-of-00002.safetensors:  99%|█████████▉| 3.46G/3.50G [00:06<00:00, 1.92GB/s]
model-00002-of-00002.safetensors: 100%|█████████▉| 3.50G/3.50G [00:07<00:00, 498MB/s] 
huggyllama-llama-7b-v172-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/26.8k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 26.8k/26.8k [00:00<00:00, 138MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
pytorch_model.bin.index.json:   0%|          | 0.00/26.8k [00:00<?, ?B/s]
pytorch_model.bin.index.json: 100%|██████████| 26.8k/26.8k [00:00<00:00, 188MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/411 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 411/411 [00:00<00:00, 6.48MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.84M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.84M/1.84M [00:00<00:00, 28.5MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 500k/500k [00:00<00:00, 61.2MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/700 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 700/700 [00:00<00:00, 8.58MB/s]
huggyllama-llama-7b-v172-mkmlizer: Downloaded to shared memory in 20.360s
huggyllama-llama-7b-v172-mkmlizer: quantizing model to /dev/shm/model_cache
huggyllama-llama-7b-v172-mkmlizer: Saving mkml model at /dev/shm/model_cache
huggyllama-llama-7b-v172-mkmlizer: Reading /tmp/tmpoqgu1fng/model.safetensors.index.json
huggyllama-llama-7b-v172-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:01<07:41,  1.59s/it]
Profiling:   4%|▍         | 13/291 [00:01<00:26, 10.36it/s]
Profiling:   8%|▊         | 23/291 [00:01<00:13, 19.51it/s]
Profiling:  12%|█▏        | 35/291 [00:01<00:07, 32.27it/s]
Profiling:  16%|█▋        | 48/291 [00:02<00:05, 46.28it/s]
Profiling:  20%|█▉        | 58/291 [00:02<00:04, 55.78it/s]
Profiling:  23%|██▎       | 68/291 [00:02<00:03, 64.68it/s]
Profiling:  28%|██▊       | 81/291 [00:02<00:02, 78.67it/s]
Profiling:  32%|███▏      | 93/291 [00:02<00:02, 87.14it/s]
Profiling:  36%|███▌      | 105/291 [00:02<00:01, 95.14it/s]
Profiling:  42%|████▏     | 121/291 [00:02<00:01, 111.13it/s]
Profiling:  47%|████▋     | 138/291 [00:02<00:01, 125.53it/s]
Profiling:  53%|█████▎    | 154/291 [00:02<00:01, 133.96it/s]
Profiling:  58%|█████▊    | 169/291 [00:02<00:00, 138.18it/s]
Profiling:  63%|██████▎   | 184/291 [00:03<00:00, 141.39it/s]
Profiling:  69%|██████▉   | 201/291 [00:03<00:00, 147.60it/s]
Profiling:  75%|███████▍  | 217/291 [00:03<00:00, 146.91it/s]
Profiling:  80%|███████▉  | 232/291 [00:05<00:02, 20.29it/s] 
Profiling:  85%|████████▌ | 248/291 [00:05<00:01, 27.69it/s]
Profiling:  91%|█████████ | 265/291 [00:05<00:00, 37.66it/s]
Profiling:  97%|█████████▋| 281/291 [00:05<00:00, 48.76it/s]
Profiling: 100%|██████████| 291/291 [00:06<00:00, 47.53it/s]
huggyllama-llama-7b-v172-mkmlizer: Processed model huggyllama/llama-7b in 39.603s
huggyllama-llama-7b-v172-mkmlizer: creating bucket guanaco-mkml-models
huggyllama-llama-7b-v172-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
huggyllama-llama-7b-v172-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/huggyllama-llama-7b-v172
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/huggyllama-llama-7b-v172/config.json
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/huggyllama-llama-7b-v172/tokenizer.model
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/huggyllama-llama-7b-v172/tokenizer_config.json
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/huggyllama-llama-7b-v172/tokenizer.json
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/huggyllama-llama-7b-v172/special_tokens_map.json
huggyllama-llama-7b-v172-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/huggyllama-llama-7b-v172/mkml_model.tensors
huggyllama-llama-7b-v172-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
huggyllama-llama-7b-v172-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.
huggyllama-llama-7b-v172-mkmlizer:   warnings.warn(
huggyllama-llama-7b-v172-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 4.47MB/s]
huggyllama-llama-7b-v172-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.
huggyllama-llama-7b-v172-mkmlizer:   warnings.warn(
huggyllama-llama-7b-v172-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 1.63MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 12.6MB/s]
huggyllama-llama-7b-v172-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 36.5MB/s]
huggyllama-llama-7b-v172-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.
huggyllama-llama-7b-v172-mkmlizer:   warnings.warn(
huggyllama-llama-7b-v172-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, 76.3MB/s]
pytorch_model.bin:   2%|▏         | 31.5M/1.44G [00:00<00:09, 142MB/s] 
pytorch_model.bin:   8%|▊         | 115M/1.44G [00:00<00:03, 417MB/s] 
pytorch_model.bin:  13%|█▎        | 189M/1.44G [00:00<00:02, 485MB/s]
pytorch_model.bin:  19%|█▉        | 273M/1.44G [00:00<00:01, 598MB/s]
pytorch_model.bin:  28%|██▊       | 398M/1.44G [00:00<00:01, 766MB/s]
pytorch_model.bin:  33%|███▎      | 482M/1.44G [00:00<00:01, 728MB/s]
pytorch_model.bin:  39%|███▉      | 566M/1.44G [00:00<00:01, 646MB/s]
pytorch_model.bin:  46%|████▌     | 658M/1.44G [00:01<00:01, 589MB/s]
pytorch_model.bin:  50%|████▉     | 721M/1.44G [00:01<00:01, 563MB/s]
pytorch_model.bin:  63%|██████▎   | 910M/1.44G [00:01<00:00, 867MB/s]
pytorch_model.bin:  72%|███████▏  | 1.04G/1.44G [00:01<00:00, 965MB/s]
pytorch_model.bin:  99%|█████████▉| 1.43G/1.44G [00:01<00:00, 1.76GB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:05<00:00, 280MB/s] 
huggyllama-llama-7b-v172-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
huggyllama-llama-7b-v172-mkmlizer: Saving duration: 0.317s
huggyllama-llama-7b-v172-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.539s
huggyllama-llama-7b-v172-mkmlizer: creating bucket guanaco-reward-models
huggyllama-llama-7b-v172-mkmlizer: Bucket 's3://guanaco-reward-models/' created
huggyllama-llama-7b-v172-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/special_tokens_map.json
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/tokenizer_config.json
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/config.json
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/merges.txt
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/vocab.json
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/tokenizer.json
huggyllama-llama-7b-v172-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/huggyllama-llama-7b-v172_reward/reward.tensors
Job huggyllama-llama-7b-v172-mkmlizer completed after 64.51s with status: succeeded
Stopping job with name huggyllama-llama-7b-v172-mkmlizer
Pipeline stage MKMLizer completed in 67.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service huggyllama-llama-7b-v172
Waiting for inference service huggyllama-llama-7b-v172 to be ready
Exception raised while processing tagging_function
Traceback (most recent call last):
  File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api
    conversation_tag = self.tagging_function(conversation_state)
  File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length
TypeError: 'ConversationMessage' object is not subscriptable

Inference service huggyllama-llama-7b-v172 ready after 40.41971254348755s
Pipeline stage ISVCDeployer completed in 47.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.8871142864227295s
Received healthy response to inference request in 0.4154062271118164s
Received healthy response to inference request in 0.39936232566833496s
Received healthy response to inference request in 0.6078071594238281s
Received healthy response to inference request in 0.7206530570983887s
5 requests
0 failed requests
5th percentile: 0.40257110595703127
10th percentile: 0.40577988624572753
20th percentile: 0.4121974468231201
30th percentile: 0.45388641357421877
40th percentile: 0.5308467864990234
50th percentile: 0.6078071594238281
60th percentile: 0.6529455184936523
70th percentile: 0.6980838775634766
80th percentile: 0.7539453029632569
90th percentile: 0.8205297946929931
95th percentile: 0.8538220405578613
99th percentile: 0.8804558372497558
mean time: 0.6060686111450195
Pipeline stage StressChecker completed in 3.93s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
huggyllama-llama-7b_v172 status is now deployed due to DeploymentManager action
huggyllama-llama-7b_v172 status is now rejected due to ELO is less than acceptable minimum 6.5

Usage Metrics

Latency Metrics