mistralai-mistral-nemo-_9330

developer_uid: azuruce

submission_id: mistralai-mistral-nemo-_9330_v83

model_name: ebony-horror-baseline-no-memory

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-17T17:25:56+00:00

num_battles: 11130

num_wins: 5084

celo_rating: 1219.96

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: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6352009697328617, 'latency_mean': 1.574249495267868, 'latency_p50': 1.569117784500122, 'latency_p90': 1.7322673559188841}, {'batch_size': 3, 'throughput': 1.2470579118359113, 'latency_mean': 2.397320042848587, 'latency_p50': 2.427701473236084, 'latency_p90': 2.640677881240845}, {'batch_size': 5, 'throughput': 1.5231813228536273, 'latency_mean': 3.2756270241737364, 'latency_p50': 3.291092038154602, 'latency_p90': 3.665569806098938}, {'batch_size': 6, 'throughput': 1.628085294237048, 'latency_mean': 3.667135012149811, 'latency_p50': 3.675144672393799, 'latency_p90': 4.129885625839234}, {'batch_size': 8, 'throughput': 1.7126012208348824, 'latency_mean': 4.649748432636261, 'latency_p50': 4.660555124282837, 'latency_p90': 5.245224165916443}, {'batch_size': 10, 'throughput': 1.7868470625433641, 'latency_mean': 5.549065113067627, 'latency_p50': 5.536844491958618, 'latency_p90': 6.29308488368988}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: ebony-horror-baseline-no-memory

is_internal_developer: True

language_model: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

ranking_group: single

throughput_3p7s: 1.64

us_pacific_date: 2024-09-17

win_ratio: 0.4567834681042228

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': 'Try to make the conversation scary while stay in character', '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-v83-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v83-mkmlizer to finish
mistralai-mistral-nemo-9330-v83-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v83-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v83-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
mistralai-mistral-nemo-9330-v83-mkmlizer: Downloaded to shared memory in 51.278s
mistralai-mistral-nemo-9330-v83-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp2mtglxw, device:0
mistralai-mistral-nemo-9330-v83-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v83-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v83-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v83-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83
mistralai-mistral-nemo-9330-v83-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83/config.json
mistralai-mistral-nemo-9330-v83-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83/special_tokens_map.json
mistralai-mistral-nemo-9330-v83-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83/tokenizer_config.json
mistralai-mistral-nemo-9330-v83-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83/tokenizer.json
mistralai-mistral-nemo-9330-v83-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v83/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v83-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.47it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.79it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.66it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.55it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.83it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.33it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 48.93it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 49.79it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.88it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 36.95it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.14it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 39.65it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 41.56it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 36.01it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.88it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 44.56it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.88it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 37.80it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 45.01it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 45.15it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 45.23it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.11it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 28.05it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.74it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.56it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 37.06it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.24it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:05, 37.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 37.55it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.58it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.92it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.02it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.55it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.30it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.41it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.86it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 47.41it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 27.96it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 28.93it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.42it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.35it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.02it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.32it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 32.91it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 39.89it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.38it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 42.44it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 43.41it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.06it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.27it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.61it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.59it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:22,  2.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.22it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.29it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  8.50it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.75it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.31it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 19.88it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.23it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.74it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 33.23it/s]
                                                            
Job mistralai-mistral-nemo-9330-v83-mkmlizer completed after 116.26s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v83-mkmlizer
Pipeline stage MKMLizer completed in 118.61s
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-v83
Waiting for inference service mistralai-mistral-nemo-9330-v83 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
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-v83 ready after 182.21992254257202s
Pipeline stage MKMLDeployer completed in 182.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.933016538619995s
Received healthy response to inference request in 1.4025487899780273s
Received healthy response to inference request in 1.7588682174682617s
Received healthy response to inference request in 1.4985992908477783s
Received healthy response to inference request in 2.8442065715789795s
5 requests
0 failed requests
5th percentile: 1.4217588901519775
10th percentile: 1.4409689903259277
20th percentile: 1.4793891906738281
30th percentile: 1.550653076171875
40th percentile: 1.6547606468200684
50th percentile: 1.7588682174682617
60th percentile: 2.1930035591125487
70th percentile: 2.6271389007568358
80th percentile: 2.8619685649871824
90th percentile: 2.897492551803589
95th percentile: 2.915254545211792
99th percentile: 2.9294641399383545
mean time: 2.0874478816986084
Pipeline stage StressChecker completed in 12.88s
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 5.04s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v83 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v83-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v83-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v83-profiler ready after 180.42272806167603s
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-ne4e8c3d589f6f6de929ff83d724100a84-deploc6q4h:/code/chaiverse_profiler_1726594501 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne4e8c3d589f6f6de929ff83d724100a84-deploc6q4h --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726594501 && python profiles.py profile --best_of_n 4 --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_1726594501/summary.json'
kubectl exec -it mistralai-mistral-ne4e8c3d589f6f6de929ff83d724100a84-deploc6q4h --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726594501/summary.json'
Pipeline stage MKMLProfilerRunner completed in 963.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v83-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v83-profiler
Service mistralai-mistral-nemo-9330-v83-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v83 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v83 status is now torndown due to DeploymentManager action