mistralai-mistral-nemo-_9330

submission_id: mistralai-mistral-nemo-_9330_v93

developer_uid: ug0ug

best_of: 4

celo_rating: 1229.05

display_name: ebony-horror-baseline-no-memory

family_friendly_score: 0.0

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}

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}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: mistralai/Mistral-Nemo-Instruct-2407

latencies: [{'batch_size': 1, 'throughput': 0.633623157603784, 'latency_mean': 1.5781302011013032, 'latency_p50': 1.5795402526855469, 'latency_p90': 1.7364537477493287}, {'batch_size': 3, 'throughput': 1.2396936963728264, 'latency_mean': 2.415117799043655, 'latency_p50': 2.44098961353302, 'latency_p90': 2.648021101951599}, {'batch_size': 5, 'throughput': 1.5345977575524599, 'latency_mean': 3.2421018481254578, 'latency_p50': 3.2393606901168823, 'latency_p90': 3.66903703212738}, {'batch_size': 6, 'throughput': 1.624287366526192, 'latency_mean': 3.6745034766197207, 'latency_p50': 3.6748207807540894, 'latency_p90': 4.124864459037781}, {'batch_size': 8, 'throughput': 1.7209888745948796, 'latency_mean': 4.606835412979126, 'latency_p50': 4.664640188217163, 'latency_p90': 5.217132306098938}, {'batch_size': 10, 'throughput': 1.7738274281510285, 'latency_mean': 5.595918974876404, 'latency_p50': 5.619800686836243, 'latency_p90': 6.441442990303039}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: mistralai/Mistral-Nemo-I

model_name: ebony-horror-baseline-no-memory

model_num_parameters: 12772070400.0

model_repo: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

num_battles: 13686

num_wins: 6548

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.64

timestamp: 2024-09-19T10:56:10+00:00

us_pacific_date: 2024-09-19

win_ratio: 0.47844512640654685

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-v93-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v93-mkmlizer to finish
mistralai-mistral-nemo-9330-v93-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v93-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v93-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v93-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
mistralai-mistral-nemo-9330-v93-mkmlizer: Downloaded to shared memory in 48.925s
mistralai-mistral-nemo-9330-v93-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuif0ffhs, device:0
mistralai-mistral-nemo-9330-v93-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v93-mkmlizer: quantized model in 36.510s
mistralai-mistral-nemo-9330-v93-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 85.435s
mistralai-mistral-nemo-9330-v93-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v93-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v93-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v93
mistralai-mistral-nemo-9330-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v93/tokenizer_config.json
mistralai-mistral-nemo-9330-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v93/tokenizer.json
mistralai-mistral-nemo-9330-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v93/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v93-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.56it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.82it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.67it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 38.91it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.84it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.36it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 42.93it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.16it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.83it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:07, 43.61it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:09, 31.03it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:09, 32.74it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.73it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.57it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 39.80it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 45.54it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.36it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 39.02it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 50.46it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 46.17it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 44.60it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 47.01it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 45.05it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.82it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.20it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.21it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.83it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.03it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.13it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 39.36it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.07it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 38.75it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.99it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 38.86it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:04, 37.56it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 39.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:04, 37.73it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.97it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 37.49it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.61it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:03, 37.67it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 36.91it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:05, 27.11it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 28.74it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 28.74it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.05it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.93it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.91it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.64it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 39.63it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.27it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.75it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 42.50it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 42.17it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 46.03it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 44.20it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 44.65it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 43.66it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:22,  2.65it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.38it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.36it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:06,  6.82it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:04,  8.95it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:02, 11.63it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:01, 14.95it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 17.14it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 24.54it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 27.70it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 29.78it/s]
                                                            
Job mistralai-mistral-nemo-9330-v93-mkmlizer completed after 114.35s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v93-mkmlizer
Pipeline stage MKMLizer completed in 115.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v93
Waiting for inference service mistralai-mistral-nemo-9330-v93 to be ready
Failed to get response for submission chaiml-virgo-edit-v1-1e5_v1: ('http://chaiml-virgo-edit-v1-1e5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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 zonemercy-lexical-nemov8_5966_v2: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Failed to get response for submission chaiml-0919-quad-dataset_3078_v2: ('http://chaiml-0919-quad-dataset-3078-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57524->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission chaiml-virgo-edit-v1-1e5_v1: ('http://chaiml-virgo-edit-v1-1e5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service mistralai-mistral-nemo-9330-v93 ready after 191.1032154560089s
Pipeline stage MKMLDeployer completed in 191.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4572362899780273s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.0035479068756104s
Received healthy response to inference request in 0.8138225078582764s
Received healthy response to inference request in 0.6095750331878662s
Received healthy response to inference request in 1.9708645343780518s
5 requests
0 failed requests
5th percentile: 0.6504245281219483
10th percentile: 0.6912740230560303
20th percentile: 0.7729730129241943
30th percentile: 0.8517675876617432
40th percentile: 0.9276577472686768
50th percentile: 1.0035479068756104
60th percentile: 1.185023260116577
70th percentile: 1.3664986133575439
80th percentile: 1.5599619388580324
90th percentile: 1.765413236618042
95th percentile: 1.8681388854980467
99th percentile: 1.9503194046020507
mean time: 1.1710092544555664
Pipeline stage StressChecker completed in 6.65s
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 4.83s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v93 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 0.11s
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-v93-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v93-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v93-profiler ready after 200.45313477516174s
Pipeline stage MKMLProfilerDeployer completed in 200.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-nea401e9d18b6c38d38fa84a66c41c913e-deplofbscn:/code/chaiverse_profiler_1726743934 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-nea401e9d18b6c38d38fa84a66c41c913e-deplofbscn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726743934 && 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_1726743934/summary.json'
kubectl exec -it mistralai-mistral-nea401e9d18b6c38d38fa84a66c41c913e-deplofbscn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726743934/summary.json'
Pipeline stage MKMLProfilerRunner completed in 964.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v93-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v93-profiler
Service mistralai-mistral-nemo-9330-v93-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.56s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v93 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v93 status is now torndown due to DeploymentManager action