mistralai-mistral-small_5341

submission_id: mistralai-mistral-small_5341_v23

developer_uid: zonemercy

best_of: 8

celo_rating: 1234.95

display_name: mistralai-mistral-small_5341_v23

family_friendly_score: 0.0

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}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A6000': 1}

is_internal_developer: True

language_model: mistralai/Mistral-Small-Instruct-2409

latencies: [{'batch_size': 1, 'throughput': 0.3803115542866938, 'latency_mean': 2.62932914018631, 'latency_p50': 2.6253589391708374, 'latency_p90': 2.881956768035889}, {'batch_size': 2, 'throughput': 0.5978830889136271, 'latency_mean': 3.335660126209259, 'latency_p50': 3.329607367515564, 'latency_p90': 3.6557939767837526}, {'batch_size': 3, 'throughput': 0.7631613379599793, 'latency_mean': 3.911045877933502, 'latency_p50': 3.8938045501708984, 'latency_p90': 4.3184565782546995}, {'batch_size': 4, 'throughput': 0.8887120200933183, 'latency_mean': 4.480204763412476, 'latency_p50': 4.478554844856262, 'latency_p90': 5.057108330726623}, {'batch_size': 5, 'throughput': 0.9811806305101938, 'latency_mean': 5.080611883401871, 'latency_p50': 5.030601620674133, 'latency_p90': 5.7135010957717896}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: mistralai/Mistral-Small-

model_name: mistralai-mistral-small_5341_v23

model_num_parameters: 22247282688.0

model_repo: mistralai/Mistral-Small-Instruct-2409

model_size: 22B

num_battles: 357032

num_wins: 172570

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.71

timestamp: 2024-09-21T16:31:13+00:00

us_pacific_date: 2024-09-21

win_ratio: 0.4833460306079007

Download Preference Data

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-mistral-small-5341-v23-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v23-mkmlizer to finish
mistralai-mistral-small-5341-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v23-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v23-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v23-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v23-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v23-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v23-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v23-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v23-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v23-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-small-5341-v23-mkmlizer: Downloaded to shared memory in 82.142s
mistralai-mistral-small-5341-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvxq36gsf, device:0
mistralai-mistral-small-5341-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-small-5341-v23-mkmlizer: quantized model in 44.130s
mistralai-mistral-small-5341-v23-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 126.273s
mistralai-mistral-small-5341-v23-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/config.json
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/special_tokens_map.json
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/tokenizer_config.json
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/tokenizer.model
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/tokenizer.json
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/flywheel_model.1.safetensors
mistralai-mistral-small-5341-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v23/flywheel_model.0.safetensors
mistralai-mistral-small-5341-v23-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.95it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:10, 45.29it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:11, 42.51it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 41.42it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.81it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 33.97it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 40.85it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 38.81it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 33.04it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 25.86it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:18, 24.07it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.74it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.85it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:13, 32.66it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:12, 34.31it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 34.52it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.64it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.99it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 39.22it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 40.90it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:12, 32.73it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 28.58it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:14, 27.21it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 27.16it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:12, 30.85it/s]
Loading 0:  26%|██▌       | 131/507 [00:03<00:13, 27.80it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:11, 31.76it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 29.31it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 35.27it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 33.67it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:10, 34.61it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:10, 33.31it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:10, 32.27it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:13, 25.46it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 25.14it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 24.24it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:11, 29.39it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 27.10it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:09, 33.98it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:09, 33.00it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 34.15it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:09, 33.11it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 34.23it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 32.86it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:09, 31.42it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:09, 31.52it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 23.56it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 23.63it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.20it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 30.63it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:08, 32.03it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:08, 31.19it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 33.38it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 32.21it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:07, 33.79it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:07, 32.02it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 34.02it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 33.11it/s]
Loading 0:  55%|█████▌    | 281/507 [00:08<00:06, 34.06it/s]
Loading 0:  56%|█████▌    | 285/507 [00:09<00:09, 23.22it/s]
Loading 0:  57%|█████▋    | 288/507 [00:09<00:09, 22.99it/s]
Loading 0:  58%|█████▊    | 293/507 [00:09<00:08, 24.34it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:07, 29.25it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 29.25it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<04:06,  1.19s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:21,  1.02it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:59,  1.67it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:30,  2.17it/s]
Loading 0:  62%|██████▏   | 315/507 [00:24<00:56,  3.39it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:40,  4.67it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:26,  6.84it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:20,  8.89it/s]
Loading 0:  66%|██████▌   | 333/507 [00:24<00:14, 12.25it/s]
Loading 0:  67%|██████▋   | 338/507 [00:24<00:10, 15.98it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:10, 15.81it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:09, 17.61it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 24.60it/s]
Loading 0:  71%|███████   | 359/507 [00:25<00:05, 27.15it/s]
Loading 0:  72%|███████▏  | 364/507 [00:25<00:04, 29.85it/s]
Loading 0:  73%|███████▎  | 369/507 [00:25<00:04, 33.30it/s]
Loading 0:  74%|███████▍  | 374/507 [00:26<00:04, 31.18it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 38.18it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 38.43it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 34.19it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:03, 28.11it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.66it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 36.32it/s]
Loading 0:  81%|████████▏ | 413/507 [00:27<00:02, 37.11it/s]
Loading 0:  82%|████████▏ | 418/507 [00:27<00:02, 37.52it/s]
Loading 0:  83%|████████▎ | 422/507 [00:27<00:02, 37.52it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.76it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.42it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.77it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.81it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 37.87it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 36.05it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 38.60it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:07,  6.25it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.52it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.56it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.91it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.65it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 22.11it/s]
Loading 0:  96%|█████████▌| 486/507 [00:31<00:00, 25.70it/s]
Loading 0:  97%|█████████▋| 491/507 [00:31<00:00, 29.00it/s]
Loading 0:  98%|█████████▊| 496/507 [00:31<00:00, 33.16it/s]
Loading 0:  99%|█████████▉| 501/507 [00:31<00:00, 31.45it/s]
                                                            
Job mistralai-mistral-small-5341-v23-mkmlizer completed after 173.99s with status: succeeded
Stopping job with name mistralai-mistral-small-5341-v23-mkmlizer
Pipeline stage MKMLizer completed in 174.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v23
Waiting for inference service mistralai-mistral-small-5341-v23 to be ready
Inference service mistralai-mistral-small-5341-v23 ready after 180.48950672149658s
Pipeline stage MKMLDeployer completed in 180.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.487304210662842s
Received healthy response to inference request in 2.2497098445892334s
Received healthy response to inference request in 3.1742610931396484s
Received healthy response to inference request in 3.0309808254241943s
Received healthy response to inference request in 3.3922622203826904s
5 requests
0 failed requests
5th percentile: 2.4059640407562255
10th percentile: 2.5622182369232176
20th percentile: 2.8747266292572022
30th percentile: 3.059636878967285
40th percentile: 3.1169489860534667
50th percentile: 3.1742610931396484
60th percentile: 3.261461544036865
70th percentile: 3.348661994934082
80th percentile: 3.4112706184387207
90th percentile: 3.4492874145507812
95th percentile: 3.4682958126068115
99th percentile: 3.4835025310516357
mean time: 3.0669036388397215
Pipeline stage StressChecker completed in 15.98s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.08s
Shutdown handler de-registered
mistralai-mistral-small_5341_v23 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v23-profiler
Waiting for inference service mistralai-mistral-small-5341-v23-profiler to be ready
Inference service mistralai-mistral-small-5341-v23-profiler ready after 180.41963362693787s
Pipeline stage MKMLProfilerDeployer completed in 180.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sme4dbdcb228b2d159c64cd8d3b860f559-deplopsqk5:/code/chaiverse_profiler_1726936876 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sme4dbdcb228b2d159c64cd8d3b860f559-deplopsqk5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726936876 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726936876/summary.json'
kubectl exec -it mistralai-mistral-sme4dbdcb228b2d159c64cd8d3b860f559-deplopsqk5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726936876/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1556.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v23-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v23-profiler
Service mistralai-mistral-small-5341-v23-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.39s
Shutdown handler de-registered
mistralai-mistral-small_5341_v23 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v23 status is now torndown due to DeploymentManager action