mistralai-mistral-nemo-_9330

developer_uid: mistycat

submission_id: mistralai-mistral-nemo-_9330_v96

model_name: reward_blend_default_full_bon

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-19T22:11:51+00:00

num_battles: 13103

num_wins: 5806

celo_rating: 1209.53

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': 0.7171822428147546, 'latency_mean': 1.394282797574997, 'latency_p50': 1.3984317779541016, 'latency_p90': 1.5441705226898192}, {'batch_size': 4, 'throughput': 1.8434149873727974, 'latency_mean': 2.162128611803055, 'latency_p50': 2.163925528526306, 'latency_p90': 2.3479621410369873}, {'batch_size': 5, 'throughput': 2.019815160964314, 'latency_mean': 2.4539916932582857, 'latency_p50': 2.4541960954666138, 'latency_p90': 2.7613829612731933}, {'batch_size': 8, 'throughput': 2.4347192361809555, 'latency_mean': 3.2592156982421874, 'latency_p50': 3.272735595703125, 'latency_p90': 3.7210533380508424}, {'batch_size': 10, 'throughput': 2.5092261894034427, 'latency_mean': 3.955594749450684, 'latency_p50': 3.94899320602417, 'latency_p90': 4.491292190551758}, {'batch_size': 12, 'throughput': 2.5770560086274124, 'latency_mean': 4.622175599336624, 'latency_p50': 4.671836256980896, 'latency_p90': 5.186347126960754}, {'batch_size': 15, 'throughput': 2.531363181498561, 'latency_mean': 5.870650289058685, 'latency_p50': 5.865198254585266, 'latency_p90': 6.728760552406311}]

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: 2.5

us_pacific_date: 2024-09-19

win_ratio: 0.44310463252690224

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-v96-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v96-mkmlizer to finish
mistralai-mistral-nemo-9330-v96-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v96-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v96-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v96-mkmlizer: Downloaded to shared memory in 50.249s
mistralai-mistral-nemo-9330-v96-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4oohi4nb, device:0
mistralai-mistral-nemo-9330-v96-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v96-mkmlizer: quantized model in 37.484s
mistralai-mistral-nemo-9330-v96-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 87.733s
mistralai-mistral-nemo-9330-v96-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v96-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v96-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96
mistralai-mistral-nemo-9330-v96-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96/config.json
mistralai-mistral-nemo-9330-v96-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96/special_tokens_map.json
mistralai-mistral-nemo-9330-v96-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96/tokenizer_config.json
mistralai-mistral-nemo-9330-v96-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96/tokenizer.json
mistralai-mistral-nemo-9330-v96-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v96/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v96-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 29.86it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.15it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.27it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.65it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.15it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.51it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.01it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 43.94it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.04it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.43it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.60it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.43it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:07, 36.88it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.27it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.13it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.72it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.49it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 34.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.92it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.94it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.68it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 39.97it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.70it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 25.51it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.14it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.30it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.48it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.42it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.06it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 38.07it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 38.70it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 38.97it/s]
Loading 0:  52%|█████▏    | 189/363 [00:05<00:04, 40.19it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 32.95it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 39.41it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 39.41it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 39.59it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 40.67it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 41.12it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.93it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 26.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.23it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 33.27it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 35.67it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 35.12it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 37.61it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.42it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.72it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 37.00it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.65it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 37.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.38it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 37.79it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 39.44it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 37.83it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 37.12it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:27,  2.13it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.66it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:12,  3.93it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.38it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:04,  8.51it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 11.17it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:01, 14.51it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.63it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 23.20it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 26.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.73it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 33.31it/s]
                                                            
Job mistralai-mistral-nemo-9330-v96-mkmlizer completed after 114.95s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v96-mkmlizer
Pipeline stage MKMLizer completed in 116.68s
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-v96
Waiting for inference service mistralai-mistral-nemo-9330-v96 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
Inference service mistralai-mistral-nemo-9330-v96 ready after 203.00016474723816s
Pipeline stage MKMLDeployer completed in 203.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.383753776550293s
Received healthy response to inference request in 1.7564575672149658s
Received healthy response to inference request in 2.2335128784179688s
Received healthy response to inference request in 1.5059175491333008s
Received healthy response to inference request in 1.3968408107757568s
5 requests
0 failed requests
5th percentile: 1.4186561584472657
10th percentile: 1.4404715061187745
20th percentile: 1.484102201461792
30th percentile: 1.5560255527496338
40th percentile: 1.6562415599822997
50th percentile: 1.7564575672149658
60th percentile: 1.947279691696167
70th percentile: 2.138101816177368
80th percentile: 2.2635610580444334
90th percentile: 2.323657417297363
95th percentile: 2.3537055969238283
99th percentile: 2.377744140625
mean time: 1.855296516418457
Pipeline stage StressChecker completed in 10.04s
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 5.23s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v96 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v96-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v96-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v96-profiler ready after 200.46240901947021s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne70861834de5bf84858add828be60ed85-deplodb75v:/code/chaiverse_profiler_1726784493 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne70861834de5bf84858add828be60ed85-deplodb75v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726784493 && 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_1726784493/summary.json'
kubectl exec -it mistralai-mistral-ne70861834de5bf84858add828be60ed85-deplodb75v --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726784493/summary.json'
Pipeline stage MKMLProfilerRunner completed in 809.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v96-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v96-profiler
Service mistralai-mistral-nemo-9330-v96-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v96 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v96 status is now torndown due to DeploymentManager action