mistralai-mixtral-8x7b-_3473

developer_uid: zonemercy
submission_id: mistralai-mixtral-8x7b-_3473_v13
model_name: mistralai-mixtral-8x7b-_3473_v13
model_group: mistralai/Mixtral-8x7B-I
status: torndown
timestamp: 2024-04-07T14:06:55+00:00
num_battles: 24879
num_wins: 13098
celo_rating: 1173.71
family_friendly_score: 0.0
submission_type: basic
model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
model_architecture: MixtralForCausalLM
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: mistralai-mixtral-8x7b-_3473_v13
is_internal_developer: True
language_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model_size: 47B
ranking_group: single
us_pacific_date: 2024-04-07
win_ratio: 0.5264681056312552
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': 4, '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}
model_eval_status: pending
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-mixtral-8x7b-3473-v13-mkmlizer
Waiting for job on mistralai-mixtral-8x7b-3473-v13-mkmlizer to finish
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║     _____            __           __                                ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║       /___/                                                         ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  Version: 0.8.6                                                     ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  belonging to:                                                      ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ║                                                                     ║
mistralai-mixtral-8x7b-3473-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mixtral-8x7b-3473-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
mistralai-mixtral-8x7b-3473-v13-mkmlizer:   warnings.warn(warning_message, FutureWarning)
mistralai-mixtral-8x7b-3473-v13-mkmlizer: quantized model in 49.550s
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Processed model mistralai/Mixtral-8x7B-Instruct-v0.1 in 120.987s
mistralai-mixtral-8x7b-3473-v13-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mixtral-8x7b-3473-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/special_tokens_map.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/tokenizer.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/tokenizer.model
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/config.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/tokenizer_config.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/mistralai-mixtral-8x7b-3473-v13/flywheel_model.3.safetensors
mistralai-mixtral-8x7b-3473-v13-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
mistralai-mixtral-8x7b-3473-v13-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   1%|          | 10/995 [00:00<00:10, 90.32it/s]
Loading 0:   2%|▏         | 20/995 [00:00<00:11, 85.26it/s]
Loading 0:   4%|▎         | 35/995 [00:00<00:09, 105.23it/s]
Loading 0:   5%|▍         | 46/995 [00:00<00:10, 91.56it/s] 
Loading 0:   6%|▌         | 56/995 [00:00<00:20, 46.84it/s]
Loading 0:   7%|▋         | 66/995 [00:01<00:16, 55.89it/s]
Loading 0:   8%|▊         | 75/995 [00:01<00:14, 61.85it/s]
Loading 0:   8%|▊         | 84/995 [00:01<00:13, 67.68it/s]
Loading 0:  10%|▉         | 99/995 [00:01<00:10, 86.55it/s]
Loading 0:  11%|█         | 110/995 [00:01<00:17, 49.40it/s]
Loading 0:  12%|█▏        | 118/995 [00:01<00:18, 48.19it/s]
Loading 0:  13%|█▎        | 128/995 [00:02<00:15, 56.24it/s]
Loading 0:  14%|█▍        | 137/995 [00:02<00:13, 61.68it/s]
Loading 0:  15%|█▍        | 146/995 [00:02<00:12, 66.82it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:15, 54.55it/s]
Loading 0:  17%|█▋        | 171/995 [00:02<00:13, 60.21it/s]
Loading 0:  18%|█▊        | 180/995 [00:02<00:12, 65.48it/s]
Loading 0:  19%|█▉        | 190/995 [00:02<00:11, 71.79it/s]
Loading 0:  20%|██        | 199/995 [00:03<00:10, 72.86it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:15, 49.08it/s]
Loading 0:  22%|██▏       | 220/995 [00:03<00:13, 57.36it/s]
Loading 0:  23%|██▎       | 229/995 [00:03<00:12, 62.58it/s]
Loading 0:  24%|██▍       | 238/995 [00:03<00:11, 67.17it/s]
Loading 0:  25%|██▌       | 253/995 [00:03<00:08, 85.43it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:13, 54.80it/s]
Loading 0:  28%|██▊       | 278/995 [00:04<00:10, 67.47it/s]
Loading 0:  29%|██▉       | 288/995 [00:13<02:53,  4.09it/s]
Loading 0:  30%|██▉       | 297/995 [00:13<02:09,  5.39it/s]
Loading 0:  31%|███       | 306/995 [00:13<01:35,  7.19it/s]
Loading 0:  32%|███▏      | 320/995 [00:13<01:06, 10.19it/s]
Loading 0:  33%|███▎      | 329/995 [00:13<00:50, 13.14it/s]
Loading 0:  34%|███▍      | 338/995 [00:14<00:38, 17.00it/s]
Loading 0:  35%|███▌      | 350/995 [00:14<00:27, 23.77it/s]
Loading 0:  36%|███▌      | 360/995 [00:14<00:21, 30.11it/s]
Loading 0:  37%|███▋      | 369/995 [00:14<00:21, 29.56it/s]
Loading 0:  38%|███▊      | 381/995 [00:14<00:15, 39.29it/s]
Loading 0:  39%|███▉      | 390/995 [00:14<00:13, 45.50it/s]
Loading 0:  41%|████      | 405/995 [00:14<00:09, 61.63it/s]
Loading 0:  42%|████▏     | 415/995 [00:15<00:08, 67.42it/s]
Loading 0:  43%|████▎     | 425/995 [00:15<00:11, 49.69it/s]
Loading 0:  44%|████▎     | 433/995 [00:15<00:10, 53.33it/s]
Loading 0:  45%|████▍     | 444/995 [00:15<00:08, 63.89it/s]
Loading 0:  46%|████▌     | 454/995 [00:15<00:07, 69.93it/s]
Loading 0:  47%|████▋     | 468/995 [00:15<00:06, 84.55it/s]
Loading 0:  48%|████▊     | 478/995 [00:16<00:09, 53.39it/s]
Loading 0:  49%|████▉     | 486/995 [00:16<00:08, 57.16it/s]
Loading 0:  50%|████▉     | 494/995 [00:16<00:09, 55.02it/s]
Loading 0:  50%|█████     | 501/995 [00:16<00:09, 52.91it/s]
Loading 0:  51%|█████     | 508/995 [00:16<00:09, 49.47it/s]
Loading 0:  52%|█████▏    | 517/995 [00:16<00:08, 57.40it/s]
Loading 0:  53%|█████▎    | 526/995 [00:17<00:10, 43.87it/s]
Loading 0:  54%|█████▍    | 536/995 [00:17<00:08, 53.32it/s]
Loading 0:  55%|█████▍    | 544/995 [00:17<00:07, 58.62it/s]
Loading 0:  56%|█████▌    | 558/995 [00:17<00:05, 76.79it/s]
Loading 0:  57%|█████▋    | 568/995 [00:26<01:56,  3.65it/s]
Loading 0:  58%|█████▊    | 581/995 [00:26<01:18,  5.29it/s]
Loading 0:  59%|█████▉    | 592/995 [00:27<00:54,  7.39it/s]
Loading 0:  61%|██████    | 602/995 [00:27<00:39,  9.95it/s]
Loading 0:  62%|██████▏   | 612/995 [00:27<00:28, 13.36it/s]
Loading 0:  63%|██████▎   | 627/995 [00:27<00:18, 20.31it/s]
Loading 0:  64%|██████▍   | 637/995 [00:27<00:16, 22.20it/s]
Loading 0:  65%|██████▍   | 646/995 [00:27<00:12, 27.36it/s]
Loading 0:  66%|██████▌   | 656/995 [00:27<00:09, 34.55it/s]
Loading 0:  67%|██████▋   | 665/995 [00:27<00:07, 41.41it/s]
Loading 0:  68%|██████▊   | 675/995 [00:28<00:06, 49.43it/s]
Loading 0:  69%|██████▉   | 691/995 [00:28<00:06, 49.25it/s]
Loading 0:  70%|███████   | 700/995 [00:28<00:05, 55.27it/s]
Loading 0:  71%|███████▏  | 709/995 [00:28<00:04, 61.24it/s]
Loading 0:  72%|███████▏  | 720/995 [00:28<00:03, 70.59it/s]
Loading 0:  73%|███████▎  | 729/995 [00:28<00:03, 72.37it/s]
Loading 0:  74%|███████▍  | 739/995 [00:29<00:05, 49.44it/s]
Loading 0:  75%|███████▌  | 750/995 [00:29<00:04, 59.49it/s]
Loading 0:  76%|███████▋  | 759/995 [00:29<00:03, 64.94it/s]
Loading 0:  77%|███████▋  | 768/995 [00:29<00:03, 70.20it/s]
Loading 0:  79%|███████▊  | 783/995 [00:29<00:02, 87.36it/s]
Loading 0:  80%|███████▉  | 794/995 [00:29<00:03, 55.42it/s]
Loading 0:  81%|████████  | 802/995 [00:30<00:03, 59.37it/s]
Loading 0:  82%|████████▏ | 812/995 [00:30<00:02, 67.05it/s]
Loading 0:  83%|████████▎ | 821/995 [00:30<00:02, 71.46it/s]
Loading 0:  83%|████████▎ | 830/995 [00:30<00:02, 75.76it/s]
Loading 0:  85%|████████▍ | 842/995 [00:39<00:41,  3.67it/s]
Loading 0:  85%|████████▌ | 849/995 [00:39<00:32,  4.47it/s]
Loading 0:  86%|████████▋ | 859/995 [00:39<00:21,  6.38it/s]
Loading 0:  87%|████████▋ | 870/995 [00:40<00:13,  9.24it/s]
Loading 0:  88%|████████▊ | 879/995 [00:40<00:09, 12.33it/s]
Loading 0:  89%|████████▉ | 889/995 [00:40<00:06, 16.81it/s]
Loading 0:  90%|█████████ | 898/995 [00:40<00:05, 19.12it/s]
Loading 0:  91%|█████████▏| 910/995 [00:40<00:03, 26.87it/s]
Loading 0:  92%|█████████▏| 920/995 [00:40<00:02, 33.87it/s]
Loading 0:  94%|█████████▍| 936/995 [00:40<00:01, 49.19it/s]
Loading 0:  95%|█████████▌| 947/995 [00:41<00:00, 56.63it/s]
Loading 0:  96%|█████████▌| 957/995 [00:42<00:01, 19.03it/s]
Loading 0:  97%|█████████▋| 968/995 [00:42<00:01, 25.11it/s]
Loading 0:  98%|█████████▊| 978/995 [00:42<00:00, 31.53it/s]
Loading 0: 100%|█████████▉| 992/995 [00:42<00:00, 43.62it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mixtral-8x7b-3473-v13-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:720: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mixtral-8x7b-3473-v13-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
mistralai-mixtral-8x7b-3473-v13-mkmlizer:   warnings.warn(
mistralai-mixtral-8x7b-3473-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
mistralai-mixtral-8x7b-3473-v13-mkmlizer:   return self.fget.__get__(instance, owner)()
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Saving duration: 0.259s
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.528s
mistralai-mixtral-8x7b-3473-v13-mkmlizer: creating bucket guanaco-reward-models
mistralai-mixtral-8x7b-3473-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-mixtral-8x7b-3473-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/config.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/special_tokens_map.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/tokenizer_config.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/merges.txt
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/vocab.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/tokenizer.json
mistralai-mixtral-8x7b-3473-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-mixtral-8x7b-3473-v13_reward/reward.tensors
Job mistralai-mixtral-8x7b-3473-v13-mkmlizer completed after 168.73s with status: succeeded
Stopping job with name mistralai-mixtral-8x7b-3473-v13-mkmlizer
Pipeline stage MKMLizer completed in 179.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-mixtral-8x7b-3473-v13
Waiting for inference service mistralai-mixtral-8x7b-3473-v13 to be ready
Inference service mistralai-mixtral-8x7b-3473-v13 ready after 40.402530670166016s
Pipeline stage ISVCDeployer completed in 65.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.572707414627075s
Received healthy response to inference request in 2.212087392807007s
Received healthy response to inference request in 1.901130199432373s
Received healthy response to inference request in 1.637678861618042s
Received healthy response to inference request in 2.296719789505005s
5 requests
0 failed requests
5th percentile: 1.6903691291809082
10th percentile: 1.7430593967437744
20th percentile: 1.8484399318695068
30th percentile: 1.9633216381072998
40th percentile: 2.0877045154571534
50th percentile: 2.212087392807007
60th percentile: 2.245940351486206
70th percentile: 2.279793310165405
80th percentile: 2.351917314529419
90th percentile: 2.462312364578247
95th percentile: 2.517509889602661
99th percentile: 2.561667909622192
mean time: 2.1240647315979
Pipeline stage StressChecker completed in 11.29s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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-mixtral-8x7b-_3473_v13 status is now deployed due to DeploymentManager action
mistralai-mixtral-8x7b-_3473_v13 status is now inactive due to admin request
admin requested tearing down of mistralai-mixtral-8x7b-_3473_v13
Running pipeline stage ISVCDeleter
Checking if service mistralai-mixtral-8x7b-3473-v13 is running
Tearing down inference service mistralai-mixtral-8x7b-3473-v13
Toredown service mistralai-mixtral-8x7b-3473-v13
Pipeline stage ISVCDeleter completed in 3.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-mixtral-8x7b-3473-v13/config.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/tokenizer.model from bucket guanaco-mkml-models
Deleting key mistralai-mixtral-8x7b-3473-v13/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-mixtral-8x7b-3473-v13_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.34s
mistralai-mixtral-8x7b-_3473_v13 status is now torndown due to DeploymentManager action