mistralai-mistral-nemo-_9330

developer_uid: mistycat

submission_id: mistralai-mistral-nemo-_9330_v95

model_name: reward_blend_default_full_bon

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-19T22:11:31+00:00

num_battles: 13140

num_wins: 5903

celo_rating: 1213.75

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: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.7217716291498574, 'latency_mean': 1.3853821873664856, 'latency_p50': 1.3741401433944702, 'latency_p90': 1.5557486772537232}, {'batch_size': 4, 'throughput': 1.8484578431138867, 'latency_mean': 2.1549661636352537, 'latency_p50': 2.1590486764907837, 'latency_p90': 2.365516424179077}, {'batch_size': 5, 'throughput': 2.030452532773632, 'latency_mean': 2.4494434547424317, 'latency_p50': 2.4447919130325317, 'latency_p90': 2.7811043500900268}, {'batch_size': 8, 'throughput': 2.447530134416502, 'latency_mean': 3.2460283493995665, 'latency_p50': 3.2213943004608154, 'latency_p90': 3.6858831882476806}, {'batch_size': 10, 'throughput': 2.5091940054842254, 'latency_mean': 3.9499395656585694, 'latency_p50': 3.98317813873291, 'latency_p90': 4.462197637557983}, {'batch_size': 12, 'throughput': 2.5614223601503765, 'latency_mean': 4.629092167615891, 'latency_p50': 4.667586922645569, 'latency_p90': 5.213723087310791}, {'batch_size': 15, 'throughput': 2.5533320071254835, 'latency_mean': 5.797599490880966, 'latency_p50': 5.7930673360824585, 'latency_p90': 6.6196445465087885}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: reward_blend_default_full_bon

is_internal_developer: False

language_model: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

ranking_group: single

throughput_3p7s: 2.51

us_pacific_date: 2024-09-19

win_ratio: 0.44923896499238963

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

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}

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-v95-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v95-mkmlizer to finish
mistralai-mistral-nemo-9330-v95-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v95-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v95-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v95-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-v95-mkmlizer: Downloaded to shared memory in 57.907s
mistralai-mistral-nemo-9330-v95-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsqftwmo8, device:0
mistralai-mistral-nemo-9330-v95-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v95-mkmlizer: quantized model in 34.892s
mistralai-mistral-nemo-9330-v95-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 92.800s
mistralai-mistral-nemo-9330-v95-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v95-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v95-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95
mistralai-mistral-nemo-9330-v95-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95/config.json
mistralai-mistral-nemo-9330-v95-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95/special_tokens_map.json
mistralai-mistral-nemo-9330-v95-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95/tokenizer_config.json
mistralai-mistral-nemo-9330-v95-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95/tokenizer.json
mistralai-mistral-nemo-9330-v95-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v95/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v95-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 35.38it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.74it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 51.52it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 53.21it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:06, 53.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 59.59it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:05, 52.17it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:07, 42.00it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 43.39it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 41.64it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 49.75it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 49.13it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 50.42it/s]
Loading 0:  27%|██▋       | 99/363 [00:01<00:05, 52.48it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:05, 49.22it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 52.40it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 43.32it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 50.37it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 48.93it/s]
Loading 0:  38%|███▊      | 138/363 [00:02<00:05, 43.16it/s]
Loading 0:  39%|███▉      | 143/363 [00:03<00:06, 34.17it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:06, 34.95it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 37.40it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.97it/s]
Loading 0:  45%|████▍     | 162/363 [00:03<00:04, 41.61it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 36.31it/s]
Loading 0:  48%|████▊     | 174/363 [00:03<00:04, 43.54it/s]
Loading 0:  49%|████▉     | 179/363 [00:03<00:04, 45.02it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 41.98it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 49.48it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.05it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 46.58it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 50.53it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 46.53it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 37.98it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 37.95it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 40.09it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 42.37it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 43.18it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 42.55it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 48.05it/s]
Loading 0:  72%|███████▏  | 262/363 [00:05<00:02, 46.21it/s]
Loading 0:  74%|███████▎  | 267/363 [00:05<00:02, 45.26it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 49.99it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 48.81it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 45.72it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 49.43it/s]
Loading 0:  82%|████████▏ | 297/363 [00:06<00:01, 49.33it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:01, 49.12it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:22,  2.53it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.46it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:07,  5.73it/s]
Loading 0:  91%|█████████ | 330/363 [00:13<00:03,  8.63it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:02, 12.13it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 14.93it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 18.62it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 22.68it/s]
                                                            
Job mistralai-mistral-nemo-9330-v95-mkmlizer completed after 115.7s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v95-mkmlizer
Pipeline stage MKMLizer completed in 116.54s
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-v95
Waiting for inference service mistralai-mistral-nemo-9330-v95 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
Inference service mistralai-mistral-nemo-9330-v95 ready after 202.44400930404663s
Pipeline stage MKMLDeployer completed in 203.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.046243667602539s
Received healthy response to inference request in 1.9220826625823975s
Received healthy response to inference request in 1.3180954456329346s
Received healthy response to inference request in 1.3601577281951904s
Received healthy response to inference request in 1.967503547668457s
5 requests
0 failed requests
5th percentile: 1.3265079021453858
10th percentile: 1.3349203586578369
20th percentile: 1.3517452716827392
30th percentile: 1.4725427150726318
40th percentile: 1.6973126888275147
50th percentile: 1.9220826625823975
60th percentile: 1.9402510166168212
70th percentile: 1.9584193706512452
80th percentile: 1.9832515716552734
90th percentile: 2.0147476196289062
95th percentile: 2.0304956436157227
99th percentile: 2.0430940628051757
mean time: 1.7228166103363036
Pipeline stage StressChecker completed in 9.65s
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 4.60s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v95 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-v95-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v95-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v95-profiler ready after 200.4393458366394s
Pipeline stage MKMLProfilerDeployer completed in 200.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-nec6b0ac365d2f3518b9c9438b6e3d64ef-deplostm7p:/code/chaiverse_profiler_1726784475 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-nec6b0ac365d2f3518b9c9438b6e3d64ef-deplostm7p --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726784475 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726784475/summary.json'
kubectl exec -it mistralai-mistral-nec6b0ac365d2f3518b9c9438b6e3d64ef-deplostm7p --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726784475/summary.json'
Pipeline stage MKMLProfilerRunner completed in 806.00s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v95-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v95-profiler
Service mistralai-mistral-nemo-9330-v95-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v95 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v95 status is now torndown due to DeploymentManager action