submission_id: mistralai-mistral-nemo_9330_v101
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1203.26
display_name: mistralai-mistral-nemo_9330_v101
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': 0.8, 'top_p': 0.8, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 128}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
latencies: [{'batch_size': 1, 'throughput': 0.35830951167088604, 'latency_mean': 2.790813602209091, 'latency_p50': 2.779158115386963, 'latency_p90': 2.9596907615661623}, {'batch_size': 3, 'throughput': 0.8085006085034477, 'latency_mean': 3.69851380109787, 'latency_p50': 3.702687621116638, 'latency_p90': 3.891402077674866}, {'batch_size': 5, 'throughput': 1.0597646534368859, 'latency_mean': 4.707834759950638, 'latency_p50': 4.705141067504883, 'latency_p90': 5.039975810050964}, {'batch_size': 6, 'throughput': 1.1485013467536622, 'latency_mean': 5.193857493400574, 'latency_p50': 5.196372747421265, 'latency_p90': 5.634696412086487}, {'batch_size': 10, 'throughput': 1.3347000936077555, 'latency_mean': 7.428420157432556, 'latency_p50': 7.492366552352905, 'latency_p90': 7.990451502799988}]
max_input_tokens: 1024
max_output_tokens: 128
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Nemo-I
model_name: mistralai-mistral-nemo_9330_v101
model_num_parameters: 12772070400.0
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
num_battles: 28142
num_wins: 12574
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.81
timestamp: 2024-09-24T02:39:19+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.4468054864615166
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-v101-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v101-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
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-nemo-9330-v101-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v101-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v101-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-nemo-9330-v101-mkmlizer: Downloaded to shared memory in 65.382s
mistralai-mistral-nemo-9330-v101-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbqy7r5m1, device:0
mistralai-mistral-nemo-9330-v101-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-v101-mkmlizer: quantized model in 35.092s
mistralai-mistral-nemo-9330-v101-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 100.474s
mistralai-mistral-nemo-9330-v101-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v101-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101
mistralai-mistral-nemo-9330-v101-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101/config.json
mistralai-mistral-nemo-9330-v101-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101/special_tokens_map.json
mistralai-mistral-nemo-9330-v101-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101/tokenizer_config.json
mistralai-mistral-nemo-9330-v101-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101/tokenizer.json
mistralai-mistral-nemo-9330-v101-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v101/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v101-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:09, 35.82it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 56.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 51.00it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.93it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.67it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 47.82it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.99it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.63it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.05it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.44it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.04it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.41it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 46.97it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.67it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.35it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:04, 51.61it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.82it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 45.74it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 49.36it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 50.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:02<00:05, 44.85it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.80it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.12it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 39.35it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.25it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 42.46it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 36.50it/s]
Loading 0:  48%|████▊     | 174/363 [00:03<00:04, 44.18it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 44.74it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.64it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.65it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 43.95it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 48.10it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 48.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.01it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 45.90it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:03, 46.94it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.77it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.65it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.66it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.92it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 42.78it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 42.14it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 41.71it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 45.52it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 45.94it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 45.86it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 46.41it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 38.87it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 46.16it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 46.63it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 46.76it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:20,  2.70it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.44it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:07,  5.55it/s]
Loading 0:  90%|████████▉ | 326/363 [00:13<00:04,  7.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.63it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.64it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 17.18it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 20.49it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.83it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 30.42it/s]
                                                            

Job mistralai-mistral-nemo-9330-v101-mkmlizer completed after 128.02s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v101-mkmlizer
Pipeline stage MKMLizer completed in 129.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v101
Waiting for inference service mistralai-mistral-nemo-9330-v101 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
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-v101 ready after 292.86261916160583s
Pipeline stage MKMLDeployer completed in 293.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.051048994064331s
Received healthy response to inference request in 2.8384811878204346s
Received healthy response to inference request in 2.804218292236328s
Received healthy response to inference request in 4.058844566345215s
Received healthy response to inference request in 3.967316150665283s
5 requests
0 failed requests
5th percentile: 2.8110708713531496
10th percentile: 2.8179234504699706
20th percentile: 2.831628608703613
30th percentile: 3.0642481803894044
40th percentile: 3.515782165527344
50th percentile: 3.967316150665283
60th percentile: 4.000809288024902
70th percentile: 4.034302425384522
80th percentile: 4.0526081085205075
90th percentile: 4.055726337432861
95th percentile: 4.057285451889038
99th percentile: 4.05853274345398
mean time: 3.543981838226318
%s, retrying in %s seconds...
Received healthy response to inference request in 4.2825164794921875s
Received healthy response to inference request in 4.102833986282349s
Received healthy response to inference request in 5.533581495285034s
Received healthy response to inference request in 3.1645376682281494s
Received healthy response to inference request in 5.750331878662109s
5 requests
0 failed requests
5th percentile: 3.3521969318389893
10th percentile: 3.539856195449829
20th percentile: 3.915174722671509
30th percentile: 4.138770484924317
40th percentile: 4.210643482208252
50th percentile: 4.2825164794921875
60th percentile: 4.782942485809326
70th percentile: 5.283368492126464
80th percentile: 5.576931571960449
90th percentile: 5.663631725311279
95th percentile: 5.706981801986695
99th percentile: 5.741661863327026
mean time: 4.566760301589966
%s, retrying in %s seconds...
Received healthy response to inference request in 3.010173797607422s
Received healthy response to inference request in 3.179006338119507s
Received healthy response to inference request in 3.3318769931793213s
Received healthy response to inference request in 3.2698066234588623s
Received healthy response to inference request in 3.287468433380127s
5 requests
0 failed requests
5th percentile: 3.043940305709839
10th percentile: 3.077706813812256
20th percentile: 3.14523983001709
30th percentile: 3.197166395187378
40th percentile: 3.23348650932312
50th percentile: 3.2698066234588623
60th percentile: 3.276871347427368
70th percentile: 3.283936071395874
80th percentile: 3.2963501453399657
90th percentile: 3.3141135692596437
95th percentile: 3.3229952812194825
99th percentile: 3.3301006507873536
mean time: 3.2156664371490478
Pipeline stage StressChecker completed in 60.34s
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 5.67s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v101 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v101-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v101-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v101-profiler ready after 200.46225380897522s
Pipeline stage MKMLProfilerDeployer completed in 200.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-neff0f0f30f8464983b05806c1ff3d92e4-deplom6qxr:/code/chaiverse_profiler_1727146296 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-neff0f0f30f8464983b05806c1ff3d92e4-deplom6qxr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727146296 && 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 128 --summary /code/chaiverse_profiler_1727146296/summary.json'
kubectl exec -it mistralai-mistral-neff0f0f30f8464983b05806c1ff3d92e4-deplom6qxr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727146296/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1325.69s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v101-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v101-profiler
Service mistralai-mistral-nemo-9330-v101-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.03s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v101 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo_9330_v101 status is now torndown due to DeploymentManager action