mistralai-mistral-nemo-_9330

developer_uid: mistycat

submission_id: mistralai-mistral-nemo-_9330_v97

model_name: reward_blend_default_full_bon

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-19T22:11:54+00:00

num_battles: 13112

num_wins: 5922

celo_rating: 1215.59

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': 0.7274746596265035, 'latency_mean': 1.3745497035980225, 'latency_p50': 1.3655070066452026, 'latency_p90': 1.5415493488311767}, {'batch_size': 4, 'throughput': 1.8665258112920708, 'latency_mean': 2.129636188745499, 'latency_p50': 2.1296876668930054, 'latency_p90': 2.403493881225586}, {'batch_size': 5, 'throughput': 2.053771800732843, 'latency_mean': 2.4167827415466308, 'latency_p50': 2.4345974922180176, 'latency_p90': 2.7181880235672}, {'batch_size': 8, 'throughput': 2.453358858894591, 'latency_mean': 3.227259443998337, 'latency_p50': 3.2090542316436768, 'latency_p90': 3.662074398994446}, {'batch_size': 10, 'throughput': 2.5667863644443583, 'latency_mean': 3.8550372529029846, 'latency_p50': 3.8493951559066772, 'latency_p90': 4.419678950309753}, {'batch_size': 12, 'throughput': 2.5984452214159064, 'latency_mean': 4.5681197905540465, 'latency_p50': 4.610278606414795, 'latency_p90': 5.1752286195755}, {'batch_size': 15, 'throughput': 2.5700375857911144, 'latency_mean': 5.779988602399826, 'latency_p50': 5.814953446388245, 'latency_p90': 6.513716435432434}]

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: 2.57

us_pacific_date: 2024-09-19

win_ratio: 0.45164734594264794

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-v97-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v97-mkmlizer to finish
mistralai-mistral-nemo-9330-v97-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v97-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v97-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v97-mkmlizer: Downloaded to shared memory in 48.756s
mistralai-mistral-nemo-9330-v97-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpovhdcv_q, device:0
mistralai-mistral-nemo-9330-v97-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v97-mkmlizer: quantized model in 37.103s
mistralai-mistral-nemo-9330-v97-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 85.859s
mistralai-mistral-nemo-9330-v97-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v97-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v97-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97
mistralai-mistral-nemo-9330-v97-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97/config.json
mistralai-mistral-nemo-9330-v97-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97/special_tokens_map.json
mistralai-mistral-nemo-9330-v97-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97/tokenizer_config.json
mistralai-mistral-nemo-9330-v97-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97/tokenizer.json
mistralai-mistral-nemo-9330-v97-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v97/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v97-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.45it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.32it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.20it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.22it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.75it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.68it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.29it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.30it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.62it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.37it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.03it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.86it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.04it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.45it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.96it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.94it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 42.65it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 35.95it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.97it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.59it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.79it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.35it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.65it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.73it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.38it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.48it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.11it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.39it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.95it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.89it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.91it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 39.84it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.76it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.34it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.35it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.69it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.47it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 40.56it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.87it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.77it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.04it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.95it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.44it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.55it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 40.33it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 40.28it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.49it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.04it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.73it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.80it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.94it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.26it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.19it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:11,  4.19it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  5.89it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.58it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 10.97it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 14.32it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.50it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 23.14it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 26.57it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.83it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 33.29it/s]
                                                            
Job mistralai-mistral-nemo-9330-v97-mkmlizer completed after 114.39s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v97-mkmlizer
Pipeline stage MKMLizer completed in 115.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v97
Waiting for inference service mistralai-mistral-nemo-9330-v97 to be ready
Inference service mistralai-mistral-nemo-9330-v97 ready after 212.249826669693s
Pipeline stage MKMLDeployer completed in 212.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2889630794525146s
Received healthy response to inference request in 1.868250846862793s
Received healthy response to inference request in 1.55659818649292s
Received healthy response to inference request in 0.8661909103393555s
Received healthy response to inference request in 1.4792206287384033s
5 requests
0 failed requests
5th percentile: 0.9887968540191651
10th percentile: 1.1114027976989747
20th percentile: 1.3566146850585938
30th percentile: 1.4946961402893066
40th percentile: 1.5256471633911133
50th percentile: 1.55659818649292
60th percentile: 1.6812592506408692
70th percentile: 1.8059203147888183
80th percentile: 1.9523932933807373
90th percentile: 2.120678186416626
95th percentile: 2.2048206329345703
99th percentile: 2.2721345901489256
mean time: 1.6118447303771972
Pipeline stage StressChecker completed in 8.66s
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 4.08s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v97 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-v97-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v97-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v97-profiler ready after 200.45919251441956s
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-nebbdc2e490e2057ec73dfd199b3c4e4d6-deplorv76b:/code/chaiverse_profiler_1726784505 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-nebbdc2e490e2057ec73dfd199b3c4e4d6-deplorv76b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726784505 && 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_1726784505/summary.json'
kubectl exec -it mistralai-mistral-nebbdc2e490e2057ec73dfd199b3c4e4d6-deplorv76b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726784505/summary.json'
Pipeline stage MKMLProfilerRunner completed in 797.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v97-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v97-profiler
Service mistralai-mistral-nemo-9330-v97-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.49s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v97 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v97 status is now torndown due to DeploymentManager action