mistralai-mistral-nemo-_9330

developer_uid: mistycat

submission_id: mistralai-mistral-nemo-_9330_v98

model_name: reward_blend_default_full_bon

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-19T22:11:56+00:00

num_battles: 13077

num_wins: 5817

celo_rating: 1210.63

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': 0.7118133966371183, 'latency_mean': 1.404790816307068, 'latency_p50': 1.4143558740615845, 'latency_p90': 1.557269287109375}, {'batch_size': 4, 'throughput': 1.8550174283813938, 'latency_mean': 2.149512468576431, 'latency_p50': 2.122596502304077, 'latency_p90': 2.4030139446258545}, {'batch_size': 5, 'throughput': 2.021194125101745, 'latency_mean': 2.4553180968761446, 'latency_p50': 2.4773662090301514, 'latency_p90': 2.726866126060486}, {'batch_size': 8, 'throughput': 2.3997380618859547, 'latency_mean': 3.312570357322693, 'latency_p50': 3.3247724771499634, 'latency_p90': 3.7595335245132446}, {'batch_size': 10, 'throughput': 2.4677870635575383, 'latency_mean': 4.024446326494217, 'latency_p50': 4.06706690788269, 'latency_p90': 4.489967322349548}, {'batch_size': 12, 'throughput': 2.566121744670145, 'latency_mean': 4.627860922813415, 'latency_p50': 4.585321664810181, 'latency_p90': 5.244090461730957}, {'batch_size': 15, 'throughput': 2.501933996773801, 'latency_mean': 5.934702605009079, 'latency_p50': 5.9582200050354, 'latency_p90': 6.766656231880188}]

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: 2.46

us_pacific_date: 2024-09-19

win_ratio: 0.4448267951364992

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-v98-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v98-mkmlizer to finish
mistralai-mistral-nemo-9330-v98-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v98-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v98-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v98-mkmlizer: Downloaded to shared memory in 49.787s
mistralai-mistral-nemo-9330-v98-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphv7t9txw, device:0
mistralai-mistral-nemo-9330-v98-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v98-mkmlizer: quantized model in 35.978s
mistralai-mistral-nemo-9330-v98-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 85.765s
mistralai-mistral-nemo-9330-v98-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v98-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v98-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98
mistralai-mistral-nemo-9330-v98-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98/config.json
mistralai-mistral-nemo-9330-v98-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98/special_tokens_map.json
mistralai-mistral-nemo-9330-v98-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98/tokenizer_config.json
mistralai-mistral-nemo-9330-v98-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98/tokenizer.json
mistralai-mistral-nemo-9330-v98-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v98/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v98-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.79it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.28it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.24it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.15it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.86it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.35it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.98it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.36it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.30it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.76it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.73it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.02it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.48it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.38it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.26it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.84it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.70it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.45it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.57it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.60it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.34it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 43.00it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.56it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.82it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.02it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 29.70it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 29.95it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 34.85it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 33.95it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.54it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.03it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 39.87it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 41.21it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 35.18it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 42.83it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 43.06it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 44.56it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 43.70it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 42.64it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 41.89it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.01it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.29it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.74it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.93it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 39.36it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.48it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 43.34it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.76it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.23it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 41.26it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 39.92it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.39it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 45.34it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 44.62it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 45.76it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.54it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.27it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.04it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.85it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.67it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.74it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 24.17it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 31.10it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 34.35it/s]
                                                            
Job mistralai-mistral-nemo-9330-v98-mkmlizer completed after 106.3s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v98-mkmlizer
Pipeline stage MKMLizer completed in 106.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v98
Waiting for inference service mistralai-mistral-nemo-9330-v98 to be ready
Inference service mistralai-mistral-nemo-9330-v98 ready after 192.46448636054993s
Pipeline stage MKMLDeployer completed in 192.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3254215717315674s
Received healthy response to inference request in 1.0989723205566406s
Received healthy response to inference request in 1.7348072528839111s
Received healthy response to inference request in 1.995011329650879s
Received healthy response to inference request in 1.7694156169891357s
5 requests
0 failed requests
5th percentile: 1.2261393070220947
10th percentile: 1.3533062934875488
20th percentile: 1.607640266418457
30th percentile: 1.741728925704956
40th percentile: 1.7555722713470459
50th percentile: 1.7694156169891357
60th percentile: 1.859653902053833
70th percentile: 1.9498921871185302
80th percentile: 2.061093378067017
90th percentile: 2.193257474899292
95th percentile: 2.2593395233154294
99th percentile: 2.3122051620483397
mean time: 1.7847256183624267
Pipeline stage StressChecker completed in 9.64s
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 5.08s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v98 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 0.12s
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-v98-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v98-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v98-profiler ready after 210.58061742782593s
Pipeline stage MKMLProfilerDeployer completed in 210.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-nefae7855f39b2ac46c4c63a98e8bdb0e3-deplocxmxn:/code/chaiverse_profiler_1726784486 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-nefae7855f39b2ac46c4c63a98e8bdb0e3-deplocxmxn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726784486 && 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_1726784486/summary.json'
kubectl exec -it mistralai-mistral-nefae7855f39b2ac46c4c63a98e8bdb0e3-deplocxmxn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726784486/summary.json'
Pipeline stage MKMLProfilerRunner completed in 814.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v98-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v98-profiler
Service mistralai-mistral-nemo-9330-v98-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.13s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v98 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v98 status is now torndown due to DeploymentManager action