mistralai-ministral-8b-_47735

developer_uid: fengjiayi
submission_id: mistralai-ministral-8b-_47735_v1
model_name: mistralai-ministral-8b-_47735_v1
model_group: mistralai/Ministral-8B-I
status: torndown
timestamp: 2025-01-23T05:25:13+00:00
num_battles: 5484
num_wins: 2616
celo_rating: 1208.45
family_friendly_score: 0.5972
family_friendly_standard_error: 0.006936168394726299
submission_type: basic
model_repo: mistralai/Ministral-8B-Instruct-2410
model_architecture: MistralForCausalLM
model_num_parameters: 8019808256.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: mistralai-ministral-8b-_47735_v1
is_internal_developer: False
language_model: mistralai/Ministral-8B-Instruct-2410
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-22
win_ratio: 0.47702407002188185
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': 1024, 'best_of': 8, '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}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name mistralai-ministral-8b-47735-v1-mkmlizer
Waiting for job on mistralai-ministral-8b-47735-v1-mkmlizer to finish
mistralai-ministral-8b-47735-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-ministral-8b-47735-v1-mkmlizer: ║     _____            __           __                                ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║       /___/                                                         ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  belonging to:                                                      ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-ministral-8b-47735-v1-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-ministral-8b-47735-v1-mkmlizer: Downloaded to shared memory in 37.486s
mistralai-ministral-8b-47735-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgnt9v1h8, device:0
mistralai-ministral-8b-47735-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-ministral-8b-47735-v1-mkmlizer: 
Loading 0:   0%|          | 0/327 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/327 [00:00<00:08, 37.50it/s]
Loading 0:   4%|▎         | 12/327 [00:00<00:06, 49.64it/s]
Loading 0:   6%|▌         | 18/327 [00:00<00:06, 50.73it/s]
Loading 0:   7%|▋         | 24/327 [00:00<00:06, 44.39it/s]
Loading 0:   9%|▉         | 29/327 [00:00<00:06, 44.70it/s]
Loading 0:  10%|█         | 34/327 [00:00<00:06, 45.32it/s]
Loading 0:  12%|█▏        | 40/327 [00:00<00:06, 41.49it/s]
Loading 0:  14%|█▍        | 45/327 [00:01<00:06, 42.58it/s]
Loading 0:  16%|█▌        | 52/327 [00:01<00:05, 48.39it/s]
Loading 0:  18%|█▊        | 58/327 [00:01<00:06, 43.56it/s]
Loading 0:  19%|█▉        | 63/327 [00:01<00:06, 42.95it/s]
Loading 0:  21%|██        | 69/327 [00:01<00:05, 46.83it/s]
Loading 0:  23%|██▎       | 74/327 [00:01<00:05, 46.47it/s]
Loading 0:  24%|██▍       | 79/327 [00:01<00:05, 45.24it/s]
Loading 0:  26%|██▌       | 84/327 [00:01<00:05, 46.00it/s]
Loading 0:  27%|██▋       | 89/327 [00:02<00:06, 37.94it/s]
Loading 0:  29%|██▉       | 95/327 [00:02<00:08, 28.19it/s]
Loading 0:  30%|███       | 99/327 [00:02<00:07, 29.39it/s]
Loading 0:  32%|███▏      | 104/327 [00:02<00:06, 32.35it/s]
Loading 0:  34%|███▍      | 111/327 [00:02<00:05, 39.72it/s]
Loading 0:  35%|███▌      | 116/327 [00:02<00:05, 40.90it/s]
Loading 0:  37%|███▋      | 121/327 [00:02<00:04, 42.79it/s]
Loading 0:  39%|███▉      | 127/327 [00:03<00:04, 40.29it/s]
Loading 0:  40%|████      | 132/327 [00:03<00:04, 40.41it/s]
Loading 0:  42%|████▏     | 138/327 [00:03<00:04, 43.88it/s]
Loading 0:  44%|████▎     | 143/327 [00:03<00:04, 43.39it/s]
Loading 0:  45%|████▌     | 148/327 [00:03<00:04, 41.56it/s]
Loading 0:  47%|████▋     | 153/327 [00:03<00:04, 42.73it/s]
Loading 0:  48%|████▊     | 158/327 [00:03<00:04, 34.87it/s]
Loading 0:  50%|█████     | 165/327 [00:04<00:03, 41.89it/s]
Loading 0:  52%|█████▏    | 170/327 [00:04<00:03, 42.49it/s]
Loading 0:  54%|█████▎    | 175/327 [00:04<00:03, 41.63it/s]
Loading 0:  55%|█████▌    | 180/327 [00:04<00:03, 42.88it/s]
Loading 0:  57%|█████▋    | 185/327 [00:04<00:03, 36.68it/s]
Loading 0:  59%|█████▊    | 192/327 [00:04<00:03, 43.96it/s]
Loading 0:  60%|██████    | 197/327 [00:04<00:02, 44.36it/s]
Loading 0:  62%|██████▏   | 202/327 [00:04<00:02, 45.15it/s]
Loading 0:  64%|██████▎   | 208/327 [00:05<00:02, 41.38it/s]
Loading 0:  65%|██████▌   | 213/327 [00:05<00:04, 26.38it/s]
Loading 0:  67%|██████▋   | 220/327 [00:05<00:03, 33.34it/s]
Loading 0:  69%|██████▉   | 226/327 [00:05<00:02, 33.80it/s]
Loading 0:  71%|███████   | 231/327 [00:05<00:02, 35.06it/s]
Loading 0:  72%|███████▏  | 236/327 [00:05<00:02, 37.96it/s]
Loading 0:  74%|███████▎  | 241/327 [00:06<00:02, 38.67it/s]
Loading 0:  75%|███████▌  | 246/327 [00:06<00:02, 39.62it/s]
Loading 0:  77%|███████▋  | 251/327 [00:06<00:01, 40.97it/s]
Loading 0:  78%|███████▊  | 256/327 [00:06<00:01, 42.41it/s]
Loading 0:  80%|███████▉  | 261/327 [00:06<00:01, 44.32it/s]
Loading 0:  81%|████████▏ | 266/327 [00:06<00:01, 34.22it/s]
Loading 0:  83%|████████▎ | 273/327 [00:06<00:01, 41.60it/s]
Loading 0:  85%|████████▌ | 278/327 [00:06<00:01, 42.52it/s]
Loading 0:  87%|████████▋ | 283/327 [00:07<00:01, 43.42it/s]
Loading 0:  88%|████████▊ | 288/327 [00:07<00:00, 44.68it/s]
Loading 0:  90%|████████▉ | 293/327 [00:07<00:00, 37.44it/s]
Loading 0:  92%|█████████▏| 300/327 [00:07<00:00, 45.04it/s]
Loading 0:  93%|█████████▎| 305/327 [00:07<00:00, 45.17it/s]
Loading 0:  95%|█████████▍| 310/327 [00:07<00:00, 43.98it/s]
Loading 0:  97%|█████████▋| 316/327 [00:07<00:00, 40.97it/s]
Loading 0:  98%|█████████▊| 321/327 [00:07<00:00, 42.18it/s]
Loading 0: 100%|██████████| 327/327 [00:13<00:00,  3.16it/s]
                                                            
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
mistralai-ministral-8b-47735-v1-mkmlizer: quantized model in 28.342s
mistralai-ministral-8b-47735-v1-mkmlizer: Processed model mistralai/Ministral-8B-Instruct-2410 in 65.829s
mistralai-ministral-8b-47735-v1-mkmlizer: creating bucket guanaco-mkml-models
mistralai-ministral-8b-47735-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-ministral-8b-47735-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v1
mistralai-ministral-8b-47735-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v1/config.json
mistralai-ministral-8b-47735-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v1/special_tokens_map.json
mistralai-ministral-8b-47735-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v1/tokenizer_config.json
mistralai-ministral-8b-47735-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v1/tokenizer.json
Job mistralai-ministral-8b-47735-v1-mkmlizer completed after 93.95s with status: succeeded
Stopping job with name mistralai-ministral-8b-47735-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-ministral-8b-47735-v1
Waiting for inference service mistralai-ministral-8b-47735-v1 to be ready
Inference service mistralai-ministral-8b-47735-v1 ready after 130.68011379241943s
Pipeline stage MKMLDeployer completed in 131.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6248760223388672s
Received healthy response to inference request in 1.4420065879821777s
Received healthy response to inference request in 1.2505848407745361s
Received healthy response to inference request in 1.5051534175872803s
Received healthy response to inference request in 1.1927850246429443s
5 requests
0 failed requests
5th percentile: 1.2043449878692627
10th percentile: 1.215904951095581
20th percentile: 1.2390248775482178
30th percentile: 1.2888691902160645
40th percentile: 1.365437889099121
50th percentile: 1.4420065879821777
60th percentile: 1.4672653198242187
70th percentile: 1.4925240516662597
80th percentile: 1.5290979385375976
90th percentile: 1.5769869804382324
95th percentile: 1.60093150138855
99th percentile: 1.6200871181488037
mean time: 1.4030811786651611
Pipeline stage StressChecker completed in 8.29s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.66s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2129.41s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v1 status is now inactive due to auto deactivation removed underperforming models
mistralai-ministral-8b-_47735_v1 status is now torndown due to DeploymentManager action