mistralai-mistral-small_5341

submission_id: mistralai-mistral-small_5341_v22

developer_uid: zonemercy

best_of: 8

celo_rating: 1234.36

display_name: mistralai-mistral-small_5341_v22

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': 0.05, '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': 0.3820390952694728, 'latency_mean': 2.6174679040908813, 'latency_p50': 2.63224720954895, 'latency_p90': 2.9185481548309324}, {'batch_size': 2, 'throughput': 0.6051261779104425, 'latency_mean': 3.302837380170822, 'latency_p50': 3.316306233406067, 'latency_p90': 3.642865753173828}, {'batch_size': 3, 'throughput': 0.7670522606765854, 'latency_mean': 3.9028817915916445, 'latency_p50': 3.90010142326355, 'latency_p90': 4.3486165523529055}, {'batch_size': 4, 'throughput': 0.89722413539393, 'latency_mean': 4.445675727128982, 'latency_p50': 4.438347220420837, 'latency_p90': 5.024551558494568}, {'batch_size': 5, 'throughput': 0.9737345076986381, 'latency_mean': 5.106246894598007, 'latency_p50': 5.089763641357422, 'latency_p90': 5.7169819355010985}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: mistralai/Mistral-Small-

model_name: mistralai-mistral-small_5341_v22

model_num_parameters: 22247282688.0

model_repo: mistralai/Mistral-Small-Instruct-2409

model_size: 22B

num_battles: 356679

num_wins: 172094

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.72

timestamp: 2024-09-21T16:29:47+00:00

us_pacific_date: 2024-09-21

win_ratio: 0.48248985782734616

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-v22-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v22-mkmlizer to finish
mistralai-mistral-small-5341-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v22-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v22-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v22-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v22-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v22-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v22-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v22-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v22-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v22-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-small-5341-v22-mkmlizer: Downloaded to shared memory in 80.589s
mistralai-mistral-small-5341-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmjvtctrt, device:0
mistralai-mistral-small-5341-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-small-5341-v22-mkmlizer: quantized model in 45.281s
mistralai-mistral-small-5341-v22-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 125.870s
mistralai-mistral-small-5341-v22-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-small-5341-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-small-5341-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/config.json
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/special_tokens_map.json
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/tokenizer_config.json
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/tokenizer.model
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/tokenizer.json
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/flywheel_model.1.safetensors
mistralai-mistral-small-5341-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v22/flywheel_model.0.safetensors
mistralai-mistral-small-5341-v22-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.59it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:10, 45.42it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:11, 42.44it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 40.24it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.78it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 33.14it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:11, 40.09it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.36it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 35.19it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 28.25it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 27.47it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.86it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 33.69it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 35.94it/s]
Loading 0:  16%|█▌        | 79/507 [00:02<00:10, 41.34it/s]
Loading 0:  17%|█▋        | 84/507 [00:02<00:09, 42.40it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:11, 36.04it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:09, 41.79it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:09, 40.80it/s]
Loading 0:  21%|██        | 106/507 [00:02<00:09, 40.32it/s]
Loading 0:  22%|██▏       | 111/507 [00:02<00:09, 42.11it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:14, 26.31it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 29.22it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.50it/s]
Loading 0:  26%|██▋       | 134/507 [00:03<00:10, 35.73it/s]
Loading 0:  27%|██▋       | 139/507 [00:03<00:10, 35.60it/s]
Loading 0:  28%|██▊       | 144/507 [00:03<00:09, 38.13it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:10, 34.00it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:08, 39.50it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 39.19it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:08, 40.95it/s]
Loading 0:  34%|███▎      | 171/507 [00:04<00:12, 26.70it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:11, 28.42it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 35.02it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:08, 36.12it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 36.32it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 38.76it/s]
Loading 0:  40%|████      | 203/507 [00:05<00:08, 34.40it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:07, 39.56it/s]
Loading 0:  42%|████▏     | 215/507 [00:05<00:07, 39.17it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 35.39it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:09, 28.43it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 29.38it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 36.17it/s]
Loading 0:  48%|████▊     | 242/507 [00:06<00:07, 37.06it/s]
Loading 0:  49%|████▊     | 247/507 [00:06<00:06, 37.25it/s]
Loading 0:  50%|████▉     | 252/507 [00:07<00:06, 39.22it/s]
Loading 0:  51%|█████     | 257/507 [00:07<00:07, 34.30it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 40.43it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 38.90it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:06, 38.42it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:06, 38.09it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 38.17it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.41it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.03it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 28.03it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:43,  1.26it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:23,  1.43it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.06it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.55it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<00:59,  3.24it/s]
Loading 0:  62%|██████▏   | 316/507 [00:23<00:45,  4.17it/s]
Loading 0:  63%|██████▎   | 320/507 [00:23<00:33,  5.65it/s]
Loading 0:  64%|██████▍   | 325/507 [00:23<00:21,  8.30it/s]
Loading 0:  65%|██████▍   | 329/507 [00:24<00:17, 10.18it/s]
Loading 0:  66%|██████▌   | 334/507 [00:24<00:12, 13.90it/s]
Loading 0:  67%|██████▋   | 339/507 [00:24<00:09, 17.16it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:10, 15.29it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:09, 16.59it/s]
Loading 0:  69%|██████▉   | 352/507 [00:24<00:07, 20.93it/s]
Loading 0:  70%|███████   | 356/507 [00:25<00:07, 21.49it/s]
Loading 0:  71%|███████   | 361/507 [00:25<00:05, 25.99it/s]
Loading 0:  72%|███████▏  | 365/507 [00:25<00:05, 24.50it/s]
Loading 0:  73%|███████▎  | 370/507 [00:25<00:04, 28.56it/s]
Loading 0:  74%|███████▍  | 374/507 [00:25<00:04, 26.83it/s]
Loading 0:  75%|███████▍  | 379/507 [00:25<00:04, 29.88it/s]
Loading 0:  76%|███████▌  | 383/507 [00:26<00:04, 25.21it/s]
Loading 0:  77%|███████▋  | 388/507 [00:26<00:04, 27.84it/s]
Loading 0:  77%|███████▋  | 392/507 [00:26<00:04, 26.64it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:05, 19.63it/s]
Loading 0:  79%|███████▉  | 400/507 [00:26<00:04, 24.75it/s]
Loading 0:  80%|███████▉  | 404/507 [00:26<00:03, 26.32it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:03, 27.40it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:03, 27.62it/s]
Loading 0:  82%|████████▏ | 415/507 [00:27<00:03, 27.44it/s]
Loading 0:  83%|████████▎ | 419/507 [00:27<00:03, 25.33it/s]
Loading 0:  84%|████████▎ | 424/507 [00:27<00:02, 29.74it/s]
Loading 0:  84%|████████▍ | 428/507 [00:27<00:02, 26.92it/s]
Loading 0:  85%|████████▌ | 433/507 [00:27<00:02, 31.17it/s]
Loading 0:  86%|████████▌ | 437/507 [00:28<00:02, 28.02it/s]
Loading 0:  87%|████████▋ | 442/507 [00:28<00:02, 31.36it/s]
Loading 0:  88%|████████▊ | 446/507 [00:28<00:02, 28.62it/s]
Loading 0:  89%|████████▉ | 451/507 [00:28<00:01, 32.28it/s]
Loading 0:  90%|████████▉ | 455/507 [00:30<00:09,  5.58it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  7.10it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:04, 10.03it/s]
Loading 0:  93%|█████████▎| 470/507 [00:31<00:02, 13.13it/s]
Loading 0:  93%|█████████▎| 474/507 [00:31<00:02, 14.71it/s]
Loading 0:  94%|█████████▍| 479/507 [00:31<00:01, 18.71it/s]
Loading 0:  95%|█████████▌| 483/507 [00:31<00:01, 19.72it/s]
Loading 0:  96%|█████████▋| 488/507 [00:31<00:00, 23.76it/s]
Loading 0:  97%|█████████▋| 492/507 [00:31<00:00, 23.10it/s]
Loading 0:  98%|█████████▊| 497/507 [00:32<00:00, 26.08it/s]
Loading 0:  99%|█████████▉| 501/507 [00:32<00:00, 24.91it/s]
Loading 0: 100%|█████████▉| 506/507 [00:32<00:00, 28.79it/s]
                                                            
Job mistralai-mistral-small-5341-v22-mkmlizer completed after 194.22s with status: succeeded
Stopping job with name mistralai-mistral-small-5341-v22-mkmlizer
Pipeline stage MKMLizer completed in 195.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v22
Waiting for inference service mistralai-mistral-small-5341-v22 to be ready
Inference service mistralai-mistral-small-5341-v22 ready after 191.1138083934784s
Pipeline stage MKMLDeployer completed in 191.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.698737144470215s
Received healthy response to inference request in 3.2960808277130127s
Received healthy response to inference request in 3.1403534412384033s
Received healthy response to inference request in 3.1742172241210938s
Received healthy response to inference request in 2.8443784713745117s
5 requests
0 failed requests
5th percentile: 2.90357346534729
10th percentile: 2.9627684593200683
20th percentile: 3.081158447265625
30th percentile: 3.1471261978149414
40th percentile: 3.1606717109680176
50th percentile: 3.1742172241210938
60th percentile: 3.222962665557861
70th percentile: 3.271708106994629
80th percentile: 3.376612091064453
90th percentile: 3.537674617767334
95th percentile: 3.6182058811187745
99th percentile: 3.682630891799927
mean time: 3.2307534217834473
Pipeline stage StressChecker completed in 16.80s
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 4.39s
Shutdown handler de-registered
mistralai-mistral-small_5341_v22 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v22-profiler
Waiting for inference service mistralai-mistral-small-5341-v22-profiler to be ready
Inference service mistralai-mistral-small-5341-v22-profiler ready after 190.45179533958435s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sm6c9efd56175b43f8421549f9770262dd-deplo4x4sl:/code/chaiverse_profiler_1726936827 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sm6c9efd56175b43f8421549f9770262dd-deplo4x4sl --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726936827 && 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_1726936827/summary.json'
kubectl exec -it mistralai-mistral-sm6c9efd56175b43f8421549f9770262dd-deplo4x4sl --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726936827/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1548.43s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v22-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v22-profiler
Service mistralai-mistral-small-5341-v22-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
mistralai-mistral-small_5341_v22 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v22 status is now torndown due to DeploymentManager action