mistralai-mistral-nemo-_9330

developer_uid: azuruce

submission_id: mistralai-mistral-nemo-_9330_v74

model_name: ebony-horror-baseline

model_group: mistralai/Mistral-Nemo-I

status: torndown

timestamp: 2024-09-17T01:03:58+00:00

num_battles: 10490

num_wins: 4708

celo_rating: 1213.72

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': 0.6357954205438067, 'latency_mean': 1.5727707016468049, 'latency_p50': 1.5592639446258545, 'latency_p90': 1.7359828233718873}, {'batch_size': 3, 'throughput': 1.2405920674815187, 'latency_mean': 2.4046344435214997, 'latency_p50': 2.419453740119934, 'latency_p90': 2.671514797210693}, {'batch_size': 5, 'throughput': 1.5472068601057158, 'latency_mean': 3.22553480386734, 'latency_p50': 3.220875382423401, 'latency_p90': 3.6303227901458737}, {'batch_size': 6, 'throughput': 1.6378960942287757, 'latency_mean': 3.6395238924026487, 'latency_p50': 3.63076114654541, 'latency_p90': 4.123572897911071}, {'batch_size': 8, 'throughput': 1.7337723662023021, 'latency_mean': 4.574505461454391, 'latency_p50': 4.5984046459198, 'latency_p90': 5.185623002052307}, {'batch_size': 10, 'throughput': 1.768899932648555, 'latency_mean': 5.617831139564514, 'latency_p50': 5.62177848815918, 'latency_p90': 6.355032014846802}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: ebony-horror-baseline

is_internal_developer: True

language_model: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

ranking_group: single

throughput_3p7s: 1.66

us_pacific_date: 2024-09-16

win_ratio: 0.4488083889418494

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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Starting job with name mistralai-mistral-nemo-9330-v74-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v74-mkmlizer to finish
mistralai-mistral-nemo-9330-v74-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v74-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v74-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v74-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
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
mistralai-mistral-nemo-9330-v74-mkmlizer: Downloaded to shared memory in 59.179s
mistralai-mistral-nemo-9330-v74-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplmznh6ec, device:0
mistralai-mistral-nemo-9330-v74-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v74-mkmlizer: quantized model in 43.397s
mistralai-mistral-nemo-9330-v74-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 102.577s
mistralai-mistral-nemo-9330-v74-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v74-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v74-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74
mistralai-mistral-nemo-9330-v74-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74/special_tokens_map.json
mistralai-mistral-nemo-9330-v74-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74/config.json
mistralai-mistral-nemo-9330-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74/tokenizer_config.json
mistralai-mistral-nemo-9330-v74-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74/tokenizer.json
mistralai-mistral-nemo-9330-v74-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v74/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v74-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.15it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.25it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.19it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.78it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.91it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 40.37it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 43.93it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 42.24it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 43.14it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:10, 28.37it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:09, 30.27it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 32.25it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 32.13it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.38it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.79it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.52it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.49it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.25it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.40it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:06, 37.01it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 36.22it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 41.55it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 41.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 39.96it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.00it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.73it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 30.88it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.27it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.78it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.89it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.34it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.04it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.77it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 43.06it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 43.16it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.60it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.44it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.23it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.76it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 44.79it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:04, 27.92it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.45it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.66it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 35.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.58it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 38.90it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.29it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.87it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 42.99it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 43.32it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.73it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.59it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.47it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.45it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.37it/s]
Loading 0:  84%|████████▍ | 306/363 [00:15<00:25,  2.25it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:18,  2.92it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:12,  3.85it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:08,  5.43it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.01it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 10.15it/s]
Loading 0:  92%|█████████▏| 334/363 [00:16<00:02, 13.23it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 15.82it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 23.03it/s]
Loading 0:  97%|█████████▋| 353/363 [00:16<00:00, 26.51it/s]
Loading 0:  99%|█████████▊| 358/363 [00:16<00:00, 28.64it/s]
                                                            
Job mistralai-mistral-nemo-9330-v74-mkmlizer completed after 127.29s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v74-mkmlizer
Pipeline stage MKMLizer completed in 128.20s
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-v74
Waiting for inference service mistralai-mistral-nemo-9330-v74 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
Inference service mistralai-mistral-nemo-9330-v74 ready after 170.9450604915619s
Pipeline stage MKMLDeployer completed in 171.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3362157344818115s
Received healthy response to inference request in 2.334597587585449s
Received healthy response to inference request in 3.0865914821624756s
Received healthy response to inference request in 2.1049604415893555s
Received healthy response to inference request in 2.190826654434204s
5 requests
0 failed requests
5th percentile: 2.1221336841583254
10th percentile: 2.139306926727295
20th percentile: 2.173653411865234
30th percentile: 2.2195808410644533
40th percentile: 2.2770892143249513
50th percentile: 2.334597587585449
60th percentile: 2.3352448463439943
70th percentile: 2.335892105102539
80th percentile: 2.4862908840179445
90th percentile: 2.78644118309021
95th percentile: 2.9365163326263426
99th percentile: 3.056576452255249
mean time: 2.410638380050659
Pipeline stage StressChecker completed in 14.13s
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 6.08s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v74 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-v74-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v74-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v74-profiler ready after 170.4385952949524s
Pipeline stage MKMLProfilerDeployer completed in 170.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne1206b64095068849d315019949f7a684-deploc7rlr:/code/chaiverse_profiler_1726535574 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne1206b64095068849d315019949f7a684-deploc7rlr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726535574 && 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_1726535574/summary.json'
kubectl exec -it mistralai-mistral-ne1206b64095068849d315019949f7a684-deploc7rlr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726535574/summary.json'
Pipeline stage MKMLProfilerRunner completed in 962.66s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v74-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v74-profiler
Service mistralai-mistral-nemo-9330-v74-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
mistralai-mistral-nemo-_9330_v74 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo-_9330_v74 status is now torndown due to DeploymentManager action