mistralai-mistral-nemo-_9330

developer_uid: azuruce

submission_id: mistralai-mistral-nemo-_9330_v94

model_name: 0919-nemo-baseline

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-19T19:29:05+00:00

num_battles: 13680

num_wins: 6260

celo_rating: 1225.61

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: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6248872148409331, 'latency_mean': 1.6002237010002136, 'latency_p50': 1.5870935916900635, 'latency_p90': 1.7766345500946046}, {'batch_size': 3, 'throughput': 1.1991479593428362, 'latency_mean': 2.4885959470272065, 'latency_p50': 2.4975444078445435, 'latency_p90': 2.728569984436035}, {'batch_size': 5, 'throughput': 1.4872259748287944, 'latency_mean': 3.3487844681739807, 'latency_p50': 3.3461211919784546, 'latency_p90': 3.8007490396499635}, {'batch_size': 6, 'throughput': 1.5723642309082992, 'latency_mean': 3.797008899450302, 'latency_p50': 3.828596353530884, 'latency_p90': 4.310397720336914}, {'batch_size': 8, 'throughput': 1.6816084799301614, 'latency_mean': 4.725969462394715, 'latency_p50': 4.7480268478393555, 'latency_p90': 5.306912279129028}, {'batch_size': 10, 'throughput': 1.6990524904151159, 'latency_mean': 5.854412159919739, 'latency_p50': 5.880236029624939, 'latency_p90': 6.547261929512024}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 0919-nemo-baseline

is_internal_developer: True

language_model: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

ranking_group: single

throughput_3p7s: 1.56

us_pacific_date: 2024-09-19

win_ratio: 0.45760233918128657

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n##Try to make the conversation scary while stay in character##\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-v94-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v94-mkmlizer to finish
mistralai-mistral-nemo-9330-v94-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v94-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v94-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
mistralai-mistral-nemo-9330-v94-mkmlizer: Downloaded to shared memory in 77.117s
mistralai-mistral-nemo-9330-v94-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx91p0zoj, device:0
mistralai-mistral-nemo-9330-v94-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v94-mkmlizer: quantized model in 36.044s
mistralai-mistral-nemo-9330-v94-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 113.161s
mistralai-mistral-nemo-9330-v94-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v94-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v94-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94
mistralai-mistral-nemo-9330-v94-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94/config.json
mistralai-mistral-nemo-9330-v94-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94/special_tokens_map.json
mistralai-mistral-nemo-9330-v94-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94/tokenizer_config.json
mistralai-mistral-nemo-9330-v94-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94/tokenizer.json
mistralai-mistral-nemo-9330-v94-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v94/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v94-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 32.63it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 54.26it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.57it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.67it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.79it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.08it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.07it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.50it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.80it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:07, 38.72it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.73it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.88it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 43.87it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.40it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.47it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 43.37it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 42.71it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.31it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 41.39it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 43.80it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:05, 45.00it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 37.69it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.51it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.01it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.70it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 37.63it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 41.39it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.11it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.62it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.63it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 43.88it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 41.51it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:04, 39.32it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 44.29it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.45it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.46it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.40it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.82it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.02it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.57it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.27it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.70it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 35.09it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.45it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.77it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.19it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 44.51it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 36.93it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 44.41it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.17it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.80it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:22,  2.50it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.24it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.32it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  8.82it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.71it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:01, 15.74it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:01, 19.24it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 22.33it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.39it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.55it/s]
                                                            
Job mistralai-mistral-nemo-9330-v94-mkmlizer completed after 148.06s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v94-mkmlizer
Pipeline stage MKMLizer completed in 149.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v94
Waiting for inference service mistralai-mistral-nemo-9330-v94 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
Inference service mistralai-mistral-nemo-9330-v94 ready after 201.42538833618164s
Pipeline stage MKMLDeployer completed in 202.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.282198667526245s
Received healthy response to inference request in 2.117079734802246s
Received healthy response to inference request in 1.5120036602020264s
Received healthy response to inference request in 1.201887845993042s
Received healthy response to inference request in 2.1639294624328613s
5 requests
0 failed requests
5th percentile: 1.2639110088348389
10th percentile: 1.3259341716766357
20th percentile: 1.4499804973602295
30th percentile: 1.6330188751220702
40th percentile: 1.8750493049621584
50th percentile: 2.117079734802246
60th percentile: 2.1358196258544924
70th percentile: 2.154559516906738
80th percentile: 2.187583303451538
90th percentile: 2.2348909854888914
95th percentile: 2.2585448265075683
99th percentile: 2.27746789932251
mean time: 1.8554198741912842
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
Pipeline stage StressChecker completed in 10.84s
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 5.09s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v94 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v94-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v94-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v94-profiler ready after 190.45737862586975s
Pipeline stage MKMLProfilerDeployer completed in 190.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne56bd9f08e47cb34bf6b34db5aeaddd5d-deploxkrsp:/code/chaiverse_profiler_1726774753 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne56bd9f08e47cb34bf6b34db5aeaddd5d-deploxkrsp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726774753 && 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 64 --summary /code/chaiverse_profiler_1726774753/summary.json'
kubectl exec -it mistralai-mistral-ne56bd9f08e47cb34bf6b34db5aeaddd5d-deploxkrsp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726774753/summary.json'
Pipeline stage MKMLProfilerRunner completed in 993.26s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v94-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v94-profiler
Service mistralai-mistral-nemo-9330-v94-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.34s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v94 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v94 status is now torndown due to DeploymentManager action