mistralai-mistral-nemo-_9330

developer_uid: azuruce

submission_id: mistralai-mistral-nemo-_9330_v99

model_name: mistralai-mistral-nemo-_9330_v99

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-20T00:38:47+00:00

num_battles: 14608

num_wins: 6857

celo_rating: 1230.77

family_friendly_score: 0.0

submission_type: basic

model_repo: mistralai/Mistral-Nemo-Instruct-2407

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6151490259389264, 'latency_mean': 1.6255266308784484, 'latency_p50': 1.6270549297332764, 'latency_p90': 1.7862840175628663}, {'batch_size': 3, 'throughput': 1.0743113706028498, 'latency_mean': 2.785674749612808, 'latency_p50': 2.7961771488189697, 'latency_p90': 3.086840796470642}, {'batch_size': 5, 'throughput': 1.2276863056866, 'latency_mean': 4.058730032444, 'latency_p50': 4.0094510316848755, 'latency_p90': 4.636245155334473}, {'batch_size': 6, 'throughput': 1.2343018571347535, 'latency_mean': 4.833306314945221, 'latency_p50': 4.909175276756287, 'latency_p90': 5.340740489959717}, {'batch_size': 8, 'throughput': 1.2196906557689942, 'latency_mean': 6.5167296230793, 'latency_p50': 6.588060736656189, 'latency_p90': 7.417089629173279}, {'batch_size': 10, 'throughput': 1.1979795844942744, 'latency_mean': 8.315454152822495, 'latency_p50': 8.228701949119568, 'latency_p90': 9.422351098060608}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: mistralai-mistral-nemo-_9330_v99

is_internal_developer: True

language_model: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-19

win_ratio: 0.4694003285870756

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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-mistral-nemo-9330-v99-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v99-mkmlizer to finish
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-nemo-9330-v99-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v99-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v99-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v99-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
mistralai-mistral-nemo-9330-v99-mkmlizer: Downloaded to shared memory in 68.913s
mistralai-mistral-nemo-9330-v99-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7yz1qbfz, device:0
mistralai-mistral-nemo-9330-v99-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v99-mkmlizer: quantized model in 35.889s
mistralai-mistral-nemo-9330-v99-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 104.802s
mistralai-mistral-nemo-9330-v99-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v99-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v99-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v99
mistralai-mistral-nemo-9330-v99-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v99/tokenizer.json
mistralai-mistral-nemo-9330-v99-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v99/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v99-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.58it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:06, 51.91it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 55.08it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.27it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:06, 48.47it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 50.00it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.31it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.46it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.44it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.25it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.69it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 43.86it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:06, 40.16it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 47.67it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 44.94it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.46it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.39it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.33it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 41.02it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.24it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 43.83it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.21it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.40it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.55it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.03it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.02it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:05, 37.31it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 37.56it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.35it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 43.65it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.34it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 46.95it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 44.48it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 43.39it/s]
Loading 0:  57%|█████▋    | 207/363 [00:04<00:03, 43.74it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 35.26it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 40.20it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 31.05it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.16it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.24it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:03, 35.33it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.32it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 38.32it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 38.05it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 36.53it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 38.77it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:02, 37.10it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 38.20it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:02, 37.41it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 42.31it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 43.94it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 36.87it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 44.72it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.56it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.31it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.78it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.32it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.85it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.68it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.57it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.79it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.51it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.71it/s]
                                                            
Job mistralai-mistral-nemo-9330-v99-mkmlizer completed after 124.28s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v99-mkmlizer
Pipeline stage MKMLizer completed in 125.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v99
Waiting for inference service mistralai-mistral-nemo-9330-v99 to be ready
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_masal_2024-09-19: ('http://chaiml-chaiml-sft-horror-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49048->127.0.0.1:8080: read: connection reset by peer\n')
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
Inference service mistralai-mistral-nemo-9330-v99 ready after 202.1833758354187s
Pipeline stage MKMLDeployer completed in 202.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6219947338104248s
Received healthy response to inference request in 1.0664987564086914s
Received healthy response to inference request in 1.804161787033081s
Received healthy response to inference request in 1.7254607677459717s
Received healthy response to inference request in 1.6881718635559082s
5 requests
0 failed requests
5th percentile: 1.177597951889038
10th percentile: 1.2886971473693847
20th percentile: 1.5108955383300782
30th percentile: 1.6352301597595216
40th percentile: 1.6617010116577149
50th percentile: 1.6881718635559082
60th percentile: 1.7030874252319337
70th percentile: 1.718002986907959
80th percentile: 1.7412009716033936
90th percentile: 1.7726813793182372
95th percentile: 1.7884215831756591
99th percentile: 1.8010137462615967
mean time: 1.5812575817108154
Pipeline stage StressChecker completed in 8.55s
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 5.40s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v99 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-nemo-9330-v99-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v99-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v99-profiler ready after 200.4954252243042s
Pipeline stage MKMLProfilerDeployer completed in 200.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne5cd82f4d1212d0a37a201439a5c03e05-deploqd9rr:/code/chaiverse_profiler_1726793311 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne5cd82f4d1212d0a37a201439a5c03e05-deploqd9rr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726793311 && 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_1726793311/summary.json'
kubectl exec -it mistralai-mistral-ne5cd82f4d1212d0a37a201439a5c03e05-deploqd9rr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726793311/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1171.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v99-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v99-profiler
Service mistralai-mistral-nemo-9330-v99-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v99 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v99 status is now torndown due to DeploymentManager action