submission_id: mistralai-mistral-7b-ins_4696_v4
developer_uid: Meliodia
status: torndown
model_repo: mistralai/Mistral-7B-Instruct-v0.1
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<s>[INST] 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}.\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-08T19:49:33+00:00
model_name: mistralai-mistral-7b-ins_4696_v4
model_eval_status: success
model_group: mistralai/Mistral-7B-Ins
num_battles: 32851
num_wins: 15725
celo_rating: 1142.01
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: mistralai-mistral-7b-ins_4696_v4
ineligible_reason: propriety_total_count < 800
language_model: mistralai/Mistral-7B-Instruct-v0.1
model_size: 7B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-08
win_ratio: 0.47867644820553407
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mistral-7b-ins-4696-v4-mkmlizer
Waiting for job on mistralai-mistral-7b-ins-4696-v4-mkmlizer to finish
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║                                                                     ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  Version: 0.6.11                                                    ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║                                                                     ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║                                                                     ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ║                                                                     ║
mistralai-mistral-7b-ins-4696-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
.gitattributes:   0%|          | 0.00/1.52k [00:00<?, ?B/s]
.gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 18.5MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
README.md:   0%|          | 0.00/3.90k [00:00<?, ?B/s]
README.md: 100%|██████████| 3.90k/3.90k [00:00<00:00, 50.8MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
config.json:   0%|          | 0.00/571 [00:00<?, ?B/s]
config.json: 100%|██████████| 571/571 [00:00<00:00, 4.69MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
generation_config.json:   0%|          | 0.00/116 [00:00<?, ?B/s]
generation_config.json: 100%|██████████| 116/116 [00:00<00:00, 962kB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
model-00001-of-00002.safetensors:   0%|          | 0.00/9.94G [00:00<?, ?B/s]
model-00001-of-00002.safetensors:   0%|          | 10.5M/9.94G [00:00<01:58, 84.1MB/s]
model-00001-of-00002.safetensors:   0%|          | 21.0M/9.94G [00:00<02:11, 75.4MB/s]
model-00001-of-00002.safetensors:   1%|          | 83.9M/9.94G [00:00<00:54, 180MB/s] 
model-00001-of-00002.safetensors:   1%|▏         | 126M/9.94G [00:00<00:41, 236MB/s] 
model-00001-of-00002.safetensors:   2%|▏         | 157M/9.94G [00:00<00:51, 191MB/s]
model-00001-of-00002.safetensors:   2%|▏         | 189M/9.94G [00:01<00:48, 199MB/s]
model-00001-of-00002.safetensors:   4%|▎         | 367M/9.94G [00:01<00:18, 531MB/s]
model-00001-of-00002.safetensors:   6%|▌         | 577M/9.94G [00:01<00:10, 883MB/s]
model-00001-of-00002.safetensors:   7%|▋         | 692M/9.94G [00:01<00:09, 945MB/s]
model-00001-of-00002.safetensors:  11%|█▏        | 1.13G/9.94G [00:01<00:04, 1.84GB/s]
model-00001-of-00002.safetensors:  13%|█▎        | 1.34G/9.94G [00:01<00:05, 1.45GB/s]
model-00001-of-00002.safetensors:  16%|█▋        | 1.64G/9.94G [00:01<00:04, 1.79GB/s]
model-00001-of-00002.safetensors:  19%|█▊        | 1.86G/9.94G [00:01<00:04, 1.76GB/s]
model-00001-of-00002.safetensors:  21%|██        | 2.06G/9.94G [00:01<00:04, 1.82GB/s]
model-00001-of-00002.safetensors:  24%|██▎       | 2.34G/9.94G [00:02<00:03, 1.93GB/s]
model-00001-of-00002.safetensors:  26%|██▌       | 2.55G/9.94G [00:02<00:03, 1.93GB/s]
model-00001-of-00002.safetensors:  28%|██▊       | 2.76G/9.94G [00:02<00:03, 1.94GB/s]
model-00001-of-00002.safetensors:  30%|███       | 2.99G/9.94G [00:02<00:03, 2.01GB/s]
model-00001-of-00002.safetensors:  32%|███▏      | 3.20G/9.94G [00:02<00:03, 1.95GB/s]
model-00001-of-00002.safetensors:  35%|███▍      | 3.46G/9.94G [00:02<00:03, 2.13GB/s]
model-00001-of-00002.safetensors:  38%|███▊      | 3.74G/9.94G [00:02<00:02, 2.26GB/s]
model-00001-of-00002.safetensors:  40%|███▉      | 3.97G/9.94G [00:02<00:02, 2.23GB/s]
model-00001-of-00002.safetensors:  42%|████▏     | 4.20G/9.94G [00:03<00:02, 2.00GB/s]
model-00001-of-00002.safetensors:  45%|████▍     | 4.45G/9.94G [00:03<00:02, 2.10GB/s]
model-00001-of-00002.safetensors:  47%|████▋     | 4.67G/9.94G [00:03<00:02, 2.06GB/s]
model-00001-of-00002.safetensors:  49%|████▉     | 4.92G/9.94G [00:03<00:02, 2.08GB/s]
model-00001-of-00002.safetensors:  52%|█████▏    | 5.14G/9.94G [00:03<00:02, 2.10GB/s]
model-00001-of-00002.safetensors:  54%|█████▍    | 5.36G/9.94G [00:03<00:02, 1.87GB/s]
model-00001-of-00002.safetensors:  57%|█████▋    | 5.62G/9.94G [00:03<00:02, 2.04GB/s]
model-00001-of-00002.safetensors:  59%|█████▊    | 5.84G/9.94G [00:03<00:02, 2.04GB/s]
model-00001-of-00002.safetensors:  61%|██████    | 6.06G/9.94G [00:03<00:01, 2.04GB/s]
model-00001-of-00002.safetensors:  64%|██████▎   | 6.32G/9.94G [00:04<00:01, 2.11GB/s]
model-00001-of-00002.safetensors:  66%|██████▌   | 6.54G/9.94G [00:04<00:01, 1.86GB/s]
model-00001-of-00002.safetensors:  68%|██████▊   | 6.78G/9.94G [00:04<00:01, 1.95GB/s]
model-00001-of-00002.safetensors:  71%|███████   | 7.01G/9.94G [00:04<00:01, 2.01GB/s]
model-00001-of-00002.safetensors:  73%|███████▎  | 7.28G/9.94G [00:04<00:01, 2.13GB/s]
model-00001-of-00002.safetensors:  75%|███████▌  | 7.50G/9.94G [00:04<00:01, 1.90GB/s]
model-00001-of-00002.safetensors:  77%|███████▋  | 7.70G/9.94G [00:04<00:01, 1.82GB/s]
model-00001-of-00002.safetensors:  80%|███████▉  | 7.92G/9.94G [00:04<00:01, 1.88GB/s]
model-00001-of-00002.safetensors:  83%|████████▎ | 8.24G/9.94G [00:04<00:00, 2.24GB/s]
model-00001-of-00002.safetensors:  85%|████████▌ | 8.47G/9.94G [00:05<00:00, 2.21GB/s]
model-00001-of-00002.safetensors:  88%|████████▊ | 8.70G/9.94G [00:05<00:00, 2.09GB/s]
model-00001-of-00002.safetensors:  90%|████████▉ | 8.92G/9.94G [00:05<00:00, 1.79GB/s]
model-00001-of-00002.safetensors:  94%|█████████▎| 9.31G/9.94G [00:05<00:00, 2.23GB/s]
model-00001-of-00002.safetensors: 100%|█████████▉| 9.94G/9.94G [00:05<00:00, 1.76GB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
model-00002-of-00002.safetensors:   0%|          | 0.00/4.54G [00:00<?, ?B/s]
model-00002-of-00002.safetensors:   0%|          | 10.5M/4.54G [00:00<00:46, 97.2MB/s]
model-00002-of-00002.safetensors:   1%|          | 52.4M/4.54G [00:00<00:17, 252MB/s] 
model-00002-of-00002.safetensors:   2%|▏         | 83.9M/4.54G [00:00<00:17, 256MB/s]
model-00002-of-00002.safetensors:   3%|▎         | 126M/4.54G [00:00<00:15, 292MB/s] 
model-00002-of-00002.safetensors:   4%|▍         | 199M/4.54G [00:00<00:14, 298MB/s]
model-00002-of-00002.safetensors:   5%|▌         | 231M/4.54G [00:00<00:15, 275MB/s]
model-00002-of-00002.safetensors:   7%|▋         | 325M/4.54G [00:00<00:09, 434MB/s]
model-00002-of-00002.safetensors:  15%|█▍        | 661M/4.54G [00:01<00:03, 1.17GB/s]
model-00002-of-00002.safetensors:  28%|██▊       | 1.26G/4.54G [00:01<00:01, 2.31GB/s]
model-00002-of-00002.safetensors:  35%|███▍      | 1.58G/4.54G [00:01<00:01, 2.54GB/s]
model-00002-of-00002.safetensors:  41%|████      | 1.86G/4.54G [00:01<00:01, 2.04GB/s]
model-00002-of-00002.safetensors:  46%|████▌     | 2.09G/4.54G [00:01<00:01, 1.81GB/s]
model-00002-of-00002.safetensors:  51%|█████     | 2.30G/4.54G [00:01<00:01, 1.81GB/s]
model-00002-of-00002.safetensors:  55%|█████▍    | 2.50G/4.54G [00:01<00:01, 1.70GB/s]
model-00002-of-00002.safetensors:  65%|██████▍   | 2.95G/4.54G [00:02<00:00, 2.36GB/s]
model-00002-of-00002.safetensors:  72%|███████▏  | 3.25G/4.54G [00:02<00:00, 2.53GB/s]
model-00002-of-00002.safetensors:  78%|███████▊  | 3.53G/4.54G [00:02<00:00, 2.41GB/s]
model-00002-of-00002.safetensors:  84%|████████▎ | 3.80G/4.54G [00:02<00:00, 2.13GB/s]
model-00002-of-00002.safetensors:  89%|████████▊ | 4.03G/4.54G [00:02<00:00, 2.10GB/s]
model-00002-of-00002.safetensors: 100%|█████████▉| 4.54G/4.54G [00:02<00:00, 1.76GB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
model.safetensors.index.json:   0%|          | 0.00/25.1k [00:00<?, ?B/s]
model.safetensors.index.json: 100%|██████████| 25.1k/25.1k [00:00<00:00, 118MB/s]
mistralai-mistral-7b-ins-4696-v4-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, 122MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
special_tokens_map.json:   0%|          | 0.00/72.0 [00:00<?, ?B/s]
special_tokens_map.json: 100%|██████████| 72.0/72.0 [00:00<00:00, 1.19MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
tokenizer.json:   0%|          | 0.00/1.80M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 15.3MB/s]
tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 15.3MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
tokenizer.model:   0%|          | 0.00/493k [00:00<?, ?B/s]
tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 51.4MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/1.47k [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 1.47k/1.47k [00:00<00:00, 24.6MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Downloaded to shared memory in 10.562s
mistralai-mistral-7b-ins-4696-v4-mkmlizer: quantizing model to /dev/shm/model_cache
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Saving mkml model at /dev/shm/model_cache
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Reading /tmp/tmpmwxd_tcr/model.safetensors.index.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
Profiling:   0%|          | 0/291 [00:00<?, ?it/s]
Profiling:   0%|          | 1/291 [00:01<06:21,  1.32s/it]
Profiling:   7%|▋         | 21/291 [00:01<00:13, 20.08it/s]
Profiling:  13%|█▎        | 39/291 [00:01<00:06, 39.02it/s]
Profiling:  20%|█▉        | 57/291 [00:01<00:03, 58.78it/s]
Profiling:  26%|██▌       | 76/291 [00:01<00:02, 80.10it/s]
Profiling:  33%|███▎      | 95/291 [00:01<00:01, 99.89it/s]
Profiling:  40%|███▉      | 116/291 [00:01<00:01, 122.59it/s]
Profiling:  46%|████▌     | 134/291 [00:02<00:01, 135.29it/s]
Profiling:  53%|█████▎    | 153/291 [00:02<00:00, 148.25it/s]
Profiling:  60%|█████▉    | 174/291 [00:02<00:00, 164.05it/s]
Profiling:  67%|██████▋   | 196/291 [00:02<00:00, 174.44it/s]
Profiling:  74%|███████▍  | 216/291 [00:04<00:02, 31.77it/s] 
Profiling:  82%|████████▏ | 238/291 [00:04<00:01, 43.59it/s]
Profiling:  88%|████████▊ | 257/291 [00:04<00:00, 55.23it/s]
Profiling:  95%|█████████▍| 276/291 [00:04<00:00, 69.11it/s]
Profiling: 100%|██████████| 291/291 [00:04<00:00, 60.40it/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: quantized model in 14.787s
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Processed model mistralai/Mistral-7B-Instruct-v0.1 in 26.276s
mistralai-mistral-7b-ins-4696-v4-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-7b-ins-4696-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/special_tokens_map.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/tokenizer_config.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/config.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/tokenizer.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/tokenizer.model
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/mistralai-mistral-7b-ins-4696-v4/mkml_model.tensors
mistralai-mistral-7b-ins-4696-v4-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
mistralai-mistral-7b-ins-4696-v4-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.
mistralai-mistral-7b-ins-4696-v4-mkmlizer:   warnings.warn(
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
config.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]
config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 12.8MB/s]
mistralai-mistral-7b-ins-4696-v4-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.
mistralai-mistral-7b-ins-4696-v4-mkmlizer:   warnings.warn(
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
tokenizer_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]
tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 3.23MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]
vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 42.5MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
tokenizer.json:   0%|          | 0.00/2.11M [00:00<?, ?B/s]
tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 26.9MB/s]
mistralai-mistral-7b-ins-4696-v4-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.
mistralai-mistral-7b-ins-4696-v4-mkmlizer:   warnings.warn(
mistralai-mistral-7b-ins-4696-v4-mkmlizer: 
pytorch_model.bin:   0%|          | 0.00/1.44G [00:00<?, ?B/s]
pytorch_model.bin:   1%|          | 10.5M/1.44G [00:00<00:45, 31.5MB/s]
pytorch_model.bin:   4%|▎         | 52.4M/1.44G [00:00<00:10, 131MB/s] 
pytorch_model.bin:  11%|█         | 157M/1.44G [00:00<00:03, 376MB/s] 
pytorch_model.bin:  15%|█▌        | 220M/1.44G [00:00<00:03, 405MB/s]
pytorch_model.bin:  23%|██▎       | 325M/1.44G [00:00<00:02, 546MB/s]
pytorch_model.bin:  28%|██▊       | 398M/1.44G [00:01<00:02, 355MB/s]
pytorch_model.bin:  33%|███▎      | 482M/1.44G [00:01<00:02, 417MB/s]
pytorch_model.bin:  38%|███▊      | 545M/1.44G [00:02<00:05, 152MB/s]
pytorch_model.bin:  45%|████▌     | 650M/1.44G [00:02<00:03, 228MB/s]
pytorch_model.bin:  53%|█████▎    | 765M/1.44G [00:02<00:02, 273MB/s]
pytorch_model.bin:  61%|██████    | 881M/1.44G [00:02<00:01, 368MB/s]
pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:03<00:00, 472MB/s]
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Saving duration: 0.219s
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 8.062s
mistralai-mistral-7b-ins-4696-v4-mkmlizer: creating bucket guanaco-reward-models
mistralai-mistral-7b-ins-4696-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mistral-7b-ins-4696-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/config.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/special_tokens_map.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/tokenizer_config.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/merges.txt
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/vocab.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/tokenizer.json
mistralai-mistral-7b-ins-4696-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mistral-7b-ins-4696-v4_reward/reward.tensors
Job mistralai-mistral-7b-ins-4696-v4-mkmlizer completed after 54.16s with status: succeeded
Stopping job with name mistralai-mistral-7b-ins-4696-v4-mkmlizer
Pipeline stage MKMLizer completed in 88.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mistral-7b-ins-4696-v4
Waiting for inference service mistralai-mistral-7b-ins-4696-v4 to be ready
Inference service mistralai-mistral-7b-ins-4696-v4 ready after 50.37974739074707s
Pipeline stage ISVCDeployer completed in 62.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7374041080474854s
Received healthy response to inference request in 1.2059073448181152s
Received healthy response to inference request in 1.1951394081115723s
Received healthy response to inference request in 1.2059762477874756s
Received healthy response to inference request in 2.098339796066284s
5 requests
0 failed requests
5th percentile: 1.1972929954528808
10th percentile: 1.1994465827941894
20th percentile: 1.2037537574768067
30th percentile: 1.2059211254119873
40th percentile: 1.2059486865997315
50th percentile: 1.2059762477874756
60th percentile: 1.4185473918914795
70th percentile: 1.6311185359954834
80th percentile: 1.8095912456512453
90th percentile: 1.9539655208587647
95th percentile: 2.0261526584625242
99th percentile: 2.083902368545532
mean time: 1.4885533809661866
Pipeline stage StressChecker completed in 8.26s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
mistralai-mistral-7b-ins_4696_v4 status is now deployed due to DeploymentManager action
mistralai-mistral-7b-ins_4696_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of mistralai-mistral-7b-ins_4696_v4
Running pipeline stage ISVCDeleter
Checking if service mistralai-mistral-7b-ins-4696-v4 is running
Tearing down inference service mistralai-mistral-7b-ins-4696-v4
Toredown service mistralai-mistral-7b-ins-4696-v4
Pipeline stage ISVCDeleter completed in 3.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mistral-7b-ins-4696-v4/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-7b-ins-4696-v4/mkml_model.tensors from bucket guanaco-mkml-models
Deleting key mistralai-mistral-7b-ins-4696-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-7b-ins-4696-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mistral-7b-ins-4696-v4/tokenizer.model from bucket guanaco-mkml-models
Deleting key mistralai-mistral-7b-ins-4696-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mistral-7b-ins-4696-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.44s
mistralai-mistral-7b-ins_4696_v4 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics