mistralai-mistral-small_5341

submission_id: mistralai-mistral-small_5341_v15
developer_uid: chai_backend_admin
best_of: 1
celo_rating: 1199.63
display_name: temp-0
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': 100, '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': 1, 'max_output_tokens': 128}
gpu_counts: {'NVIDIA RTX A6000': 1}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: mistralai/Mistral-Small-Instruct-2409
latencies: [{'batch_size': 1, 'throughput': 0.22038263268771527, 'latency_mean': 4.5374842190742495, 'latency_p50': 4.524754762649536, 'latency_p90': 4.797590613365173}, {'batch_size': 2, 'throughput': 0.3840235083726817, 'latency_mean': 5.188633241653442, 'latency_p50': 5.177011132240295, 'latency_p90': 5.480624055862426}, {'batch_size': 5, 'throughput': 0.7833184623488376, 'latency_mean': 6.362347110509872, 'latency_p50': 6.358771085739136, 'latency_p90': 6.815939712524414}]
max_input_tokens: 1024
max_output_tokens: 128
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Small-
model_name: temp-0
model_num_parameters: 22247282688.0
model_repo: mistralai/Mistral-Small-Instruct-2409
model_size: 22B
num_battles: 13400
num_wins: 6363
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-09-20T20:19:21+00:00
us_pacific_date: 2024-09-20
win_ratio: 0.4748507462686567
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-v15-mkmlizer
Waiting for job on mistralai-mistral-small-5341-v15-mkmlizer to finish
mistralai-mistral-small-5341-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-small-5341-v15-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-small-5341-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-small-5341-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-small-5341-v15-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-small-5341-v15-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-small-5341-v15-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-small-5341-v15-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-small-5341-v15-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-small-5341-v15-mkmlizer: ║                                                                     ║
mistralai-mistral-small-5341-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-small-5341-v15-mkmlizer: Downloaded to shared memory in 95.190s
mistralai-mistral-small-5341-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuf4xwifd, device:0
mistralai-mistral-small-5341-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-small-5341-v15-mkmlizer: quantized model in 43.003s
mistralai-mistral-small-5341-v15-mkmlizer: Processed model mistralai/Mistral-Small-Instruct-2409 in 138.194s
mistralai-mistral-small-5341-v15-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-small-5341-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v15/flywheel_model.1.safetensors
mistralai-mistral-small-5341-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-small-5341-v15/flywheel_model.0.safetensors
mistralai-mistral-small-5341-v15-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.96it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 42.80it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 38.96it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 37.86it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.88it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 38.46it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:12, 36.51it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 38.06it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.63it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 35.46it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 35.56it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:17, 25.33it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:16, 27.70it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.08it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.71it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 33.80it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 38.28it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 36.46it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 35.40it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:12, 34.09it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 35.63it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 34.28it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:11, 36.14it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 34.60it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.77it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.53it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.76it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 33.60it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.24it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.20it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.25it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.08it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 34.64it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.98it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.47it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 34.45it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.40it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.59it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 27.55it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:10, 30.22it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 28.60it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 36.33it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 34.82it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 36.16it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 33.71it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 35.69it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 33.52it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 33.31it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 33.64it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 26.50it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 26.85it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 34.94it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 33.09it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.58it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.85it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.22it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 34.84it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 37.63it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 36.22it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.85it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.64it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 38.84it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 25.28it/s]
Loading 0:  57%|█████▋    | 290/507 [00:08<00:07, 27.78it/s]
Loading 0:  58%|█████▊    | 294/507 [00:08<00:07, 27.63it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.63it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<03:09,  1.09it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:41,  1.27it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:43,  1.93it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:21,  2.43it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:56,  3.41it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:37,  5.05it/s]
Loading 0:  64%|██████▎   | 323/507 [00:23<00:27,  6.73it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.37it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:14, 11.75it/s]
Loading 0:  66%|██████▋   | 336/507 [00:24<00:11, 14.54it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 15.01it/s]
Loading 0:  68%|██████▊   | 343/507 [00:24<00:09, 16.68it/s]
Loading 0:  68%|██████▊   | 347/507 [00:24<00:08, 18.73it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 26.82it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 28.97it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.38it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 33.23it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 36.82it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 36.70it/s]
Loading 0:  75%|███████▌  | 382/507 [00:25<00:03, 37.71it/s]
Loading 0:  77%|███████▋  | 388/507 [00:25<00:03, 39.13it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:02, 38.46it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:03, 30.43it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 29.67it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.82it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.87it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.06it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 34.28it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 36.32it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 36.25it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 39.03it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 37.55it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.72it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 39.54it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 39.81it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:07,  6.26it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  8.75it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 12.70it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:02, 14.82it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 18.22it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:01, 20.88it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 24.35it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 25.49it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 28.51it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 29.15it/s]
                                                            
Job mistralai-mistral-small-5341-v15-mkmlizer completed after 170.92s with status: succeeded
Connection pool is full, discarding connection: %s. Connection pool size: %s
Stopping job with name mistralai-mistral-small-5341-v15-mkmlizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLizer completed in 180.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 3.39s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-small-5341-v15
Waiting for inference service mistralai-mistral-small-5341-v15 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service mistralai-mistral-small-5341-v15 ready after 191.7352831363678s
Pipeline stage MKMLDeployer completed in 205.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7617876529693604s
Received healthy response to inference request in 1.3093867301940918s
Received healthy response to inference request in 6.552147626876831s
Received healthy response to inference request in 1.2556798458099365s
Received healthy response to inference request in 1.247185468673706s
5 requests
0 failed requests
5th percentile: 1.248884344100952
10th percentile: 1.2505832195281983
20th percentile: 1.2539809703826905
30th percentile: 1.2664212226867675
40th percentile: 1.2879039764404296
50th percentile: 1.3093867301940918
60th percentile: 1.890347099304199
70th percentile: 2.4713074684143064
80th percentile: 3.519859647750855
90th percentile: 5.0360036373138435
95th percentile: 5.794075632095336
99th percentile: 6.4005332279205325
mean time: 2.625237464904785
Pipeline stage StressChecker completed in 17.05s
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 6.32s
Shutdown handler de-registered
mistralai-mistral-small_5341_v15 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 8.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-small-5341-v15-profiler
Waiting for inference service mistralai-mistral-small-5341-v15-profiler to be ready
Inference service mistralai-mistral-small-5341-v15-profiler ready after 200.44909930229187s
Pipeline stage MKMLProfilerDeployer completed in 205.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-sm3bb9f256eed3a26f5d608670d5ee0e71-deplo8fggz:/code/chaiverse_profiler_1726864256 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-sm3bb9f256eed3a26f5d608670d5ee0e71-deplo8fggz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726864256 && python profiles.py profile --best_of_n 1 --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 128 --summary /code/chaiverse_profiler_1726864256/summary.json'
kubectl exec -it mistralai-mistral-sm3bb9f256eed3a26f5d608670d5ee0e71-deplo8fggz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726864256/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1692.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-small-5341-v15-profiler is running
Tearing down inference service mistralai-mistral-small-5341-v15-profiler
Service mistralai-mistral-small-5341-v15-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.07s
Shutdown handler de-registered
mistralai-mistral-small_5341_v15 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-small_5341_v15 status is now torndown due to DeploymentManager action