mistralai-mistral-nemo-_9330

submission_id: mistralai-mistral-nemo-_9330_v90

developer_uid: mistycat

best_of: 4

celo_rating: 1216.63

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': 0.6425832068470199, 'latency_mean': 1.5561581552028656, 'latency_p50': 1.550196886062622, 'latency_p90': 1.7202038049697876}, {'batch_size': 3, 'throughput': 1.2726481094027506, 'latency_mean': 2.343389050960541, 'latency_p50': 2.350891590118408, 'latency_p90': 2.574914979934692}, {'batch_size': 5, 'throughput': 1.573109175947424, 'latency_mean': 3.164714757204056, 'latency_p50': 3.176886558532715, 'latency_p90': 3.528103804588318}, {'batch_size': 6, 'throughput': 1.6627450920072715, 'latency_mean': 3.5865509295463562, 'latency_p50': 3.589862585067749, 'latency_p90': 4.072820663452148}, {'batch_size': 8, 'throughput': 1.7806897308271374, 'latency_mean': 4.46149573802948, 'latency_p50': 4.42228639125824, 'latency_p90': 5.074016571044922}, {'batch_size': 10, 'throughput': 1.832367762477798, 'latency_mean': 5.413103227615356, 'latency_p50': 5.434775352478027, 'latency_p90': 6.159926724433899}]

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: 9397

num_wins: 4264

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.69

timestamp: 2024-09-18T13:51:55+00:00

us_pacific_date: 2024-09-18

win_ratio: 0.45376183888475047

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-nemo-9330-v90-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v90-mkmlizer to finish
Failed to get response for submission mistralai-mistral-small-_5341_v1: ('http://mistralai-mistral-small-5341-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
mistralai-mistral-nemo-9330-v90-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v90-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v90-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-small-_5341_v1: ('http://mistralai-mistral-small-5341-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
mistralai-mistral-nemo-9330-v90-mkmlizer: Downloaded to shared memory in 46.185s
mistralai-mistral-nemo-9330-v90-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzj7pqgzn, device:0
mistralai-mistral-nemo-9330-v90-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-small-_5341_v1: ('http://mistralai-mistral-small-5341-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
mistralai-mistral-nemo-9330-v90-mkmlizer: quantized model in 36.276s
mistralai-mistral-nemo-9330-v90-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 82.462s
mistralai-mistral-nemo-9330-v90-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v90-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v90-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90
mistralai-mistral-nemo-9330-v90-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90/config.json
mistralai-mistral-nemo-9330-v90-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90/special_tokens_map.json
mistralai-mistral-nemo-9330-v90-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90/tokenizer_config.json
mistralai-mistral-nemo-9330-v90-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90/tokenizer.json
mistralai-mistral-nemo-9330-v90-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v90/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v90-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.60it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.34it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 46.66it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.45it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.90it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.32it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.50it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:05, 51.35it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:07, 39.11it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 39.17it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 43.44it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 43.97it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 44.17it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 49.28it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 47.49it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.58it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.89it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 49.17it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 47.34it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.95it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.13it/s]
Loading 0:  38%|███▊      | 137/363 [00:02<00:04, 45.60it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.15it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.57it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.29it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.96it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.18it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.88it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:04, 46.50it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.55it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.69it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 48.40it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 48.24it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 48.56it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 46.76it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 40.43it/s]
Loading 0:  60%|██████    | 218/363 [00:04<00:03, 41.57it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 32.79it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.02it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.68it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.94it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 40.18it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 40.37it/s]
Loading 0:  69%|██████▉   | 252/363 [00:05<00:02, 42.63it/s]
Loading 0:  71%|███████   | 257/363 [00:05<00:03, 35.17it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.61it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 40.67it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 41.24it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 42.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 34.20it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 40.89it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 40.63it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 41.21it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:23,  2.47it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:16,  3.21it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.22it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.30it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.88it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.51it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.47it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.48it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.83it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.58it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 33.20it/s]
                                                            
Job mistralai-mistral-nemo-9330-v90-mkmlizer completed after 104.54s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v90-mkmlizer
Pipeline stage MKMLizer completed in 106.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v90
Waiting for inference service mistralai-mistral-nemo-9330-v90 to be ready
Failed to get response for submission mistralai-mistral-small-_5341_v1: ('http://mistralai-mistral-small-5341-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
Inference service mistralai-mistral-nemo-9330-v90 ready after 190.5189929008484s
Pipeline stage MKMLDeployer completed in 190.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.364638090133667s
Received healthy response to inference request in 0.8302850723266602s
Received healthy response to inference request in 1.1481523513793945s
Received healthy response to inference request in 1.3547346591949463s
Received healthy response to inference request in 0.7857406139373779s
5 requests
0 failed requests
5th percentile: 0.7946495056152344
10th percentile: 0.8035583972930909
20th percentile: 0.8213761806488037
30th percentile: 0.893858528137207
40th percentile: 1.0210054397583008
50th percentile: 1.1481523513793945
60th percentile: 1.2307852745056151
70th percentile: 1.313418197631836
80th percentile: 1.3567153453826903
90th percentile: 1.3606767177581787
95th percentile: 1.362657403945923
99th percentile: 1.3642419528961183
mean time: 1.0967101573944091
Pipeline stage StressChecker completed in 6.14s
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 5.63s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v90 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v90-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v90-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v90-profiler ready after 200.5200319290161s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ned312130759af645385c64dca4481ab5e-deplok77kp:/code/chaiverse_profiler_1726668071 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ned312130759af645385c64dca4481ab5e-deplok77kp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726668071 && 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_1726668071/summary.json'
kubectl exec -it mistralai-mistral-ned312130759af645385c64dca4481ab5e-deplok77kp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726668071/summary.json'
Pipeline stage MKMLProfilerRunner completed in 941.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v90-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v90-profiler
Service mistralai-mistral-nemo-9330-v90-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.84s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v90 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v90 status is now torndown due to DeploymentManager action