mistralai-ministral-8b-_47735

developer_uid: huohuo12

submission_id: mistralai-ministral-8b-_47735_v5

model_name: mistralai-ministral-8b-_47735_v5

model_group: mistralai/Ministral-8B-I

status: torndown

timestamp: 2025-02-20T07:27:19+00:00

num_battles: 5316

num_wins: 2470

celo_rating: 1219.95

family_friendly_score: 0.6264000000000001

family_friendly_standard_error: 0.006841389332584428

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

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.8390823429109988, 'latency_mean': 1.1916924023628235, 'latency_p50': 1.1971808671951294, 'latency_p90': 1.3175585746765137}, {'batch_size': 4, 'throughput': 1.720966158088068, 'latency_mean': 2.3096106839179993, 'latency_p50': 2.306963086128235, 'latency_p90': 2.5607077360153196}, {'batch_size': 5, 'throughput': 1.8489188255474105, 'latency_mean': 2.684568283557892, 'latency_p50': 2.6725200414657593, 'latency_p90': 3.0358683586120603}, {'batch_size': 8, 'throughput': 2.0344462518504254, 'latency_mean': 3.8994296550750733, 'latency_p50': 3.884808301925659, 'latency_p90': 4.416944909095764}, {'batch_size': 10, 'throughput': 2.1113056228430214, 'latency_mean': 4.697143125534057, 'latency_p50': 4.706804394721985, 'latency_p90': 5.249268579483032}, {'batch_size': 12, 'throughput': 2.1121140097136957, 'latency_mean': 5.629454009532928, 'latency_p50': 5.664814829826355, 'latency_p90': 6.415873456001282}, {'batch_size': 15, 'throughput': 2.1185967487842143, 'latency_mean': 6.974788898229599, 'latency_p50': 7.051318168640137, 'latency_p90': 7.693191790580749}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: mistralai-ministral-8b-_47735_v5

is_internal_developer: False

language_model: mistralai/Ministral-8B-Instruct-2410

model_size: 8B

ranking_group: single

throughput_3p7s: 2.03

us_pacific_date: 2025-02-19

win_ratio: 0.4646350639578631

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.025, 'top_k': 45, 'presence_penalty': 0.65, 'frequency_penalty': 0.35, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-v5-mkmlizer
Waiting for job on mistralai-ministral-8b-47735-v5-mkmlizer to finish
mistralai-ministral-8b-47735-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-ministral-8b-47735-v5-mkmlizer: ║     _____            __           __                                ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║       /___/                                                         ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  belonging to:                                                      ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-ministral-8b-47735-v5-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-ministral-8b-47735-v5-mkmlizer: Downloaded to shared memory in 37.752s
mistralai-ministral-8b-47735-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb25ddms_, device:0
mistralai-ministral-8b-47735-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-ministral-8b-47735-v5-mkmlizer: 
Loading 0:   0%|          | 0/327 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/327 [00:00<00:10, 31.15it/s]
Loading 0:   4%|▎         | 12/327 [00:00<00:07, 43.05it/s]
Loading 0:   5%|▌         | 17/327 [00:00<00:07, 42.25it/s]
Loading 0:   7%|▋         | 22/327 [00:00<00:08, 35.75it/s]
Loading 0:   8%|▊         | 26/327 [00:00<00:08, 33.92it/s]
Loading 0:   9%|▉         | 31/327 [00:00<00:07, 37.82it/s]
Loading 0:  11%|█         | 35/327 [00:00<00:08, 35.14it/s]
Loading 0:  12%|█▏        | 40/327 [00:01<00:07, 38.89it/s]
Loading 0:  14%|█▍        | 45/327 [00:01<00:07, 38.56it/s]
Loading 0:  16%|█▌        | 51/327 [00:01<00:06, 42.35it/s]
Loading 0:  17%|█▋        | 56/327 [00:01<00:06, 42.10it/s]
Loading 0:  19%|█▊        | 61/327 [00:01<00:06, 41.88it/s]
Loading 0:  20%|██        | 66/327 [00:01<00:06, 43.36it/s]
Loading 0:  22%|██▏       | 71/327 [00:01<00:07, 34.52it/s]
Loading 0:  24%|██▍       | 78/327 [00:01<00:05, 41.70it/s]
Loading 0:  25%|██▌       | 83/327 [00:02<00:05, 42.34it/s]
Loading 0:  27%|██▋       | 88/327 [00:02<00:05, 41.28it/s]
Loading 0:  28%|██▊       | 93/327 [00:02<00:05, 42.88it/s]
Loading 0:  30%|██▉       | 98/327 [00:02<00:08, 25.75it/s]
Loading 0:  32%|███▏      | 104/327 [00:02<00:07, 29.54it/s]
Loading 0:  34%|███▍      | 111/327 [00:02<00:06, 35.98it/s]
Loading 0:  35%|███▌      | 116/327 [00:03<00:05, 37.24it/s]
Loading 0:  37%|███▋      | 121/327 [00:03<00:05, 38.72it/s]
Loading 0:  39%|███▊      | 126/327 [00:03<00:04, 41.19it/s]
Loading 0:  40%|████      | 131/327 [00:03<00:05, 35.03it/s]
Loading 0:  42%|████▏     | 138/327 [00:03<00:04, 41.38it/s]
Loading 0:  44%|████▎     | 143/327 [00:03<00:04, 41.60it/s]
Loading 0:  45%|████▌     | 148/327 [00:03<00:04, 41.87it/s]
Loading 0:  47%|████▋     | 153/327 [00:03<00:04, 43.17it/s]
Loading 0:  48%|████▊     | 158/327 [00:04<00:04, 35.48it/s]
Loading 0:  50%|█████     | 165/327 [00:04<00:03, 41.85it/s]
Loading 0:  52%|█████▏    | 170/327 [00:04<00:03, 41.61it/s]
Loading 0:  54%|█████▎    | 175/327 [00:04<00:03, 41.55it/s]
Loading 0:  55%|█████▌    | 180/327 [00:04<00:03, 42.78it/s]
Loading 0:  57%|█████▋    | 185/327 [00:04<00:04, 34.34it/s]
Loading 0:  59%|█████▊    | 192/327 [00:04<00:03, 40.97it/s]
Loading 0:  60%|██████    | 197/327 [00:05<00:03, 41.39it/s]
Loading 0:  62%|██████▏   | 202/327 [00:05<00:03, 41.32it/s]
Loading 0:  63%|██████▎   | 207/327 [00:05<00:02, 42.14it/s]
Loading 0:  65%|██████▍   | 212/327 [00:05<00:03, 29.13it/s]
Loading 0:  66%|██████▌   | 216/327 [00:05<00:03, 30.69it/s]
Loading 0:  67%|██████▋   | 220/327 [00:05<00:03, 31.53it/s]
Loading 0:  69%|██████▊   | 224/327 [00:05<00:03, 32.97it/s]
Loading 0:  70%|██████▉   | 228/327 [00:06<00:02, 34.18it/s]
Loading 0:  71%|███████   | 232/327 [00:06<00:02, 34.23it/s]
Loading 0:  72%|███████▏  | 237/327 [00:06<00:02, 36.99it/s]
Loading 0:  74%|███████▎  | 241/327 [00:06<00:02, 36.63it/s]
Loading 0:  75%|███████▌  | 246/327 [00:06<00:02, 39.49it/s]
Loading 0:  77%|███████▋  | 251/327 [00:06<00:01, 39.66it/s]
Loading 0:  78%|███████▊  | 256/327 [00:06<00:01, 40.76it/s]
Loading 0:  80%|███████▉  | 261/327 [00:06<00:01, 42.76it/s]
Loading 0:  81%|████████▏ | 266/327 [00:07<00:01, 34.96it/s]
Loading 0:  83%|████████▎ | 273/327 [00:07<00:01, 41.59it/s]
Loading 0:  85%|████████▌ | 278/327 [00:07<00:01, 41.76it/s]
Loading 0:  87%|████████▋ | 283/327 [00:07<00:01, 41.98it/s]
Loading 0:  88%|████████▊ | 288/327 [00:07<00:00, 43.41it/s]
Loading 0:  90%|████████▉ | 293/327 [00:07<00:00, 35.44it/s]
Loading 0:  92%|█████████▏| 300/327 [00:07<00:00, 42.11it/s]
Loading 0:  93%|█████████▎| 305/327 [00:07<00:00, 42.19it/s]
Loading 0:  95%|█████████▍| 310/327 [00:08<00:00, 42.32it/s]
Loading 0:  96%|█████████▋| 315/327 [00:08<00:00, 43.65it/s]
Loading 0:  98%|█████████▊| 320/327 [00:08<00:00, 35.74it/s]
Loading 0: 100%|██████████| 327/327 [00:13<00:00,  3.23it/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-v5-mkmlizer: quantized model in 29.036s
mistralai-ministral-8b-47735-v5-mkmlizer: Processed model mistralai/Ministral-8B-Instruct-2410 in 66.789s
mistralai-ministral-8b-47735-v5-mkmlizer: creating bucket guanaco-mkml-models
mistralai-ministral-8b-47735-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-ministral-8b-47735-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v5
mistralai-ministral-8b-47735-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v5/config.json
mistralai-ministral-8b-47735-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v5/special_tokens_map.json
mistralai-ministral-8b-47735-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v5/tokenizer_config.json
mistralai-ministral-8b-47735-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v5/tokenizer.json
Job mistralai-ministral-8b-47735-v5-mkmlizer completed after 94.21s with status: succeeded
Stopping job with name mistralai-ministral-8b-47735-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-ministral-8b-47735-v5
Waiting for inference service mistralai-ministral-8b-47735-v5 to be ready
Inference service mistralai-ministral-8b-47735-v5 ready after 180.65671753883362s
Pipeline stage MKMLDeployer completed in 181.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.000422239303589s
Received healthy response to inference request in 1.2299532890319824s
Received healthy response to inference request in 1.269806146621704s
Received healthy response to inference request in 1.1345665454864502s
Received healthy response to inference request in 1.6419734954833984s
5 requests
0 failed requests
5th percentile: 1.1536438941955567
10th percentile: 1.1727212429046632
20th percentile: 1.210875940322876
30th percentile: 1.2379238605499268
40th percentile: 1.2538650035858154
50th percentile: 1.269806146621704
60th percentile: 1.4186730861663819
70th percentile: 1.5675400257110594
80th percentile: 1.7136632442474367
90th percentile: 1.8570427417755127
95th percentile: 1.9287324905395506
99th percentile: 1.9860842895507813
mean time: 1.4553443431854247
Pipeline stage StressChecker completed in 8.54s
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 0.62s
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 0.63s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-ministral-8b-47735-v5-profiler
Waiting for inference service mistralai-ministral-8b-47735-v5-profiler to be ready
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 2242.08s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v5 status is now inactive due to auto deactivation removed underperforming models
mistralai-ministral-8b-_47735_v5 status is now torndown due to DeploymentManager action