mistralai-ministral-8b-_47735

developer_uid: huohuo12

submission_id: mistralai-ministral-8b-_47735_v2

model_name: mistralai-ministral-8b-_47735_v2

model_group: mistralai/Ministral-8B-I

status: torndown

timestamp: 2025-02-20T06:13:56+00:00

num_battles: 5853

num_wins: 2602

celo_rating: 1212.06

family_friendly_score: 0.6024

family_friendly_standard_error: 0.006921188337272726

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': 0.8512312621357241, 'latency_mean': 1.1746885645389558, 'latency_p50': 1.1713343858718872, 'latency_p90': 1.3048477172851562}, {'batch_size': 4, 'throughput': 1.758853723123652, 'latency_mean': 2.26757866024971, 'latency_p50': 2.284309506416321, 'latency_p90': 2.50104877948761}, {'batch_size': 5, 'throughput': 1.8887792904894702, 'latency_mean': 2.6393538451194765, 'latency_p50': 2.6643853187561035, 'latency_p90': 2.9549542903900146}, {'batch_size': 8, 'throughput': 2.092789078895663, 'latency_mean': 3.7996906065940856, 'latency_p50': 3.7818914651870728, 'latency_p90': 4.239985966682434}, {'batch_size': 10, 'throughput': 2.1356493323252073, 'latency_mean': 4.652568124532699, 'latency_p50': 4.627969861030579, 'latency_p90': 5.252770519256591}, {'batch_size': 12, 'throughput': 2.1609313763518223, 'latency_mean': 5.500002514123917, 'latency_p50': 5.5098090171813965, 'latency_p90': 6.200310397148132}, {'batch_size': 15, 'throughput': 2.1544991107684917, 'latency_mean': 6.861856125593185, 'latency_p50': 6.912763714790344, 'latency_p90': 7.665611910820007}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: mistralai-ministral-8b-_47735_v2

is_internal_developer: False

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

model_size: 8B

ranking_group: single

throughput_3p7s: 2.09

us_pacific_date: 2025-02-19

win_ratio: 0.4445583461472749

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-v2-mkmlizer
Waiting for job on mistralai-ministral-8b-47735-v2-mkmlizer to finish
mistralai-ministral-8b-47735-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-ministral-8b-47735-v2-mkmlizer: ║     _____            __           __                                ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║       /___/                                                         ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  belonging to:                                                      ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
mistralai-ministral-8b-47735-v2-mkmlizer: ║                                                                     ║
mistralai-ministral-8b-47735-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-ministral-8b-47735-v2-mkmlizer: Downloaded to shared memory in 44.861s
mistralai-ministral-8b-47735-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_3iaht3g, device:0
mistralai-ministral-8b-47735-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-ministral-8b-47735-v2-mkmlizer: 
Loading 0:   0%|          | 0/327 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/327 [00:00<00:09, 34.22it/s]
Loading 0:   4%|▎         | 12/327 [00:00<00:06, 46.85it/s]
Loading 0:   5%|▌         | 17/327 [00:00<00:06, 45.45it/s]
Loading 0:   7%|▋         | 22/327 [00:00<00:08, 37.48it/s]
Loading 0:   8%|▊         | 26/327 [00:00<00:08, 36.07it/s]
Loading 0:  10%|█         | 33/327 [00:00<00:06, 44.25it/s]
Loading 0:  12%|█▏        | 38/327 [00:00<00:06, 44.19it/s]
Loading 0:  13%|█▎        | 43/327 [00:01<00:06, 43.72it/s]
Loading 0:  15%|█▍        | 48/327 [00:01<00:06, 44.45it/s]
Loading 0:  16%|█▌        | 53/327 [00:01<00:07, 35.82it/s]
Loading 0:  18%|█▊        | 60/327 [00:01<00:06, 41.86it/s]
Loading 0:  20%|█▉        | 65/327 [00:01<00:06, 42.43it/s]
Loading 0:  21%|██▏       | 70/327 [00:01<00:05, 43.02it/s]
Loading 0:  23%|██▎       | 75/327 [00:01<00:05, 43.95it/s]
Loading 0:  24%|██▍       | 80/327 [00:01<00:06, 36.12it/s]
Loading 0:  27%|██▋       | 87/327 [00:02<00:05, 42.59it/s]
Loading 0:  28%|██▊       | 92/327 [00:02<00:05, 42.23it/s]
Loading 0:  30%|██▉       | 97/327 [00:02<00:07, 29.17it/s]
Loading 0:  31%|███       | 101/327 [00:02<00:07, 30.56it/s]
Loading 0:  32%|███▏      | 105/327 [00:02<00:07, 30.36it/s]
Loading 0:  34%|███▍      | 111/327 [00:02<00:06, 35.51it/s]
Loading 0:  35%|███▌      | 115/327 [00:02<00:05, 35.60it/s]
Loading 0:  37%|███▋      | 120/327 [00:03<00:05, 38.08it/s]
Loading 0:  38%|███▊      | 125/327 [00:03<00:05, 38.35it/s]
Loading 0:  40%|███▉      | 130/327 [00:03<00:04, 40.19it/s]
Loading 0:  41%|████▏     | 135/327 [00:03<00:04, 42.66it/s]
Loading 0:  43%|████▎     | 140/327 [00:03<00:05, 34.56it/s]
Loading 0:  45%|████▍     | 147/327 [00:03<00:04, 41.59it/s]
Loading 0:  46%|████▋     | 152/327 [00:03<00:04, 42.19it/s]
Loading 0:  48%|████▊     | 157/327 [00:03<00:03, 42.63it/s]
Loading 0:  50%|████▉     | 162/327 [00:04<00:03, 42.86it/s]
Loading 0:  51%|█████     | 167/327 [00:04<00:04, 33.45it/s]
Loading 0:  53%|█████▎    | 174/327 [00:04<00:03, 39.90it/s]
Loading 0:  55%|█████▍    | 179/327 [00:04<00:03, 40.70it/s]
Loading 0:  56%|█████▋    | 184/327 [00:04<00:03, 41.71it/s]
Loading 0:  58%|█████▊    | 189/327 [00:04<00:03, 42.98it/s]
Loading 0:  59%|█████▉    | 194/327 [00:05<00:03, 35.08it/s]
Loading 0:  61%|██████▏   | 201/327 [00:05<00:03, 41.67it/s]
Loading 0:  63%|██████▎   | 206/327 [00:05<00:02, 42.14it/s]
Loading 0:  65%|██████▍   | 211/327 [00:05<00:03, 30.10it/s]
Loading 0:  66%|██████▌   | 215/327 [00:05<00:03, 31.09it/s]
Loading 0:  67%|██████▋   | 219/327 [00:05<00:03, 32.65it/s]
Loading 0:  68%|██████▊   | 223/327 [00:05<00:03, 33.19it/s]
Loading 0:  70%|██████▉   | 228/327 [00:05<00:02, 36.36it/s]
Loading 0:  71%|███████   | 232/327 [00:06<00:02, 36.15it/s]
Loading 0:  72%|███████▏  | 237/327 [00:06<00:02, 38.74it/s]
Loading 0:  74%|███████▍  | 242/327 [00:06<00:02, 39.69it/s]
Loading 0:  76%|███████▌  | 247/327 [00:06<00:01, 40.35it/s]
Loading 0:  77%|███████▋  | 252/327 [00:06<00:01, 41.71it/s]
Loading 0:  79%|███████▊  | 257/327 [00:06<00:02, 33.14it/s]
Loading 0:  80%|████████  | 262/327 [00:06<00:01, 36.83it/s]
Loading 0:  82%|████████▏ | 267/327 [00:06<00:01, 37.47it/s]
Loading 0:  83%|████████▎ | 273/327 [00:07<00:01, 41.11it/s]
Loading 0:  85%|████████▌ | 278/327 [00:07<00:01, 41.01it/s]
Loading 0:  87%|████████▋ | 283/327 [00:07<00:01, 41.21it/s]
Loading 0:  88%|████████▊ | 288/327 [00:07<00:00, 41.92it/s]
Loading 0:  90%|████████▉ | 293/327 [00:07<00:01, 33.27it/s]
Loading 0:  92%|█████████▏| 300/327 [00:07<00:00, 40.09it/s]
Loading 0:  93%|█████████▎| 305/327 [00:07<00:00, 40.78it/s]
Loading 0:  95%|█████████▍| 310/327 [00:08<00:00, 40.85it/s]
Loading 0:  96%|█████████▋| 315/327 [00:08<00:00, 41.86it/s]
Loading 0:  98%|█████████▊| 320/327 [00:08<00:00, 34.60it/s]
Loading 0: 100%|██████████| 327/327 [00:13<00:00,  3.24it/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-v2-mkmlizer: creating bucket guanaco-mkml-models
mistralai-ministral-8b-47735-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-ministral-8b-47735-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2
mistralai-ministral-8b-47735-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2/config.json
mistralai-ministral-8b-47735-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2/special_tokens_map.json
mistralai-ministral-8b-47735-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2/tokenizer_config.json
mistralai-ministral-8b-47735-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2/tokenizer.json
mistralai-ministral-8b-47735-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-ministral-8b-47735-v2/flywheel_model.0.safetensors
Job mistralai-ministral-8b-47735-v2-mkmlizer completed after 93.82s with status: succeeded
Stopping job with name mistralai-ministral-8b-47735-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.28s
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-v2
Waiting for inference service mistralai-ministral-8b-47735-v2 to be ready
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service mistralai-ministral-8b-47735-v2 ready after 190.65171885490417s
Pipeline stage MKMLDeployer completed in 191.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.393049478530884s
Received healthy response to inference request in 1.1817042827606201s
Received healthy response to inference request in 1.1511971950531006s
Received healthy response to inference request in 1.3674001693725586s
Received healthy response to inference request in 1.101853609085083s
5 requests
0 failed requests
5th percentile: 1.1117223262786866
10th percentile: 1.12159104347229
20th percentile: 1.141328477859497
30th percentile: 1.1572986125946045
40th percentile: 1.1695014476776122
50th percentile: 1.1817042827606201
60th percentile: 1.2559826374053955
70th percentile: 1.330260992050171
80th percentile: 1.9725300312042242
90th percentile: 3.182789754867554
95th percentile: 3.7879196166992184
99th percentile: 4.272023506164551
mean time: 1.8390409469604492
Pipeline stage StressChecker completed in 10.36s
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 0.60s
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 0.59s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v2 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 2333.27s
Shutdown handler de-registered
mistralai-ministral-8b-_47735_v2 status is now inactive due to auto deactivation removed underperforming models
mistralai-ministral-8b-_47735_v2 status is now torndown due to DeploymentManager action
mistralai-ministral-8b-_47735_v2 status is now torndown due to DeploymentManager action
mistralai-ministral-8b-_47735_v2 status is now torndown due to DeploymentManager action