mistralai-mistral-nemo_9330

submission_id: mistralai-mistral-nemo_9330_v108

developer_uid: robert_irvine

best_of: 8

display_name: mistralai-mistral-nemo_9330_v108

family_friendly_score: 0.0

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: mistralai/Mistral-Nemo-Instruct-2407

latencies: [{'batch_size': 1, 'throughput': 0.616660729875036, 'latency_mean': 1.6215764379501343, 'latency_p50': 1.6228872537612915, 'latency_p90': 1.7812722444534301}, {'batch_size': 3, 'throughput': 1.0912821454492332, 'latency_mean': 2.738562686443329, 'latency_p50': 2.735382318496704, 'latency_p90': 2.991406202316284}, {'batch_size': 5, 'throughput': 1.2443173709611328, 'latency_mean': 4.003398753404618, 'latency_p50': 4.015395402908325, 'latency_p90': 4.453152775764465}, {'batch_size': 6, 'throughput': 1.2529749613074932, 'latency_mean': 4.771621632575989, 'latency_p50': 4.775731563568115, 'latency_p90': 5.314825963973998}, {'batch_size': 8, 'throughput': 1.2436588558680937, 'latency_mean': 6.40552995800972, 'latency_p50': 6.408303260803223, 'latency_p90': 7.198904609680175}, {'batch_size': 10, 'throughput': 1.2146761367372798, 'latency_mean': 8.174488326311112, 'latency_p50': 8.242400527000427, 'latency_p90': 9.251984286308288}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: mistralai/Mistral-Nemo-I

model_name: mistralai-mistral-nemo_9330_v108

model_num_parameters: 12772070400.0

model_repo: mistralai/Mistral-Nemo-Instruct-2407

model_size: 13B

num_battles: 47

num_wins: 25

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.22

timestamp: 2024-09-24T18:12:09+00:00

us_pacific_date: 2024-09-24

win_ratio: 0.5319148936170213

Download Preference Data

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 zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Starting job with name mistralai-mistral-nemo-9330-v108-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v108-mkmlizer to finish
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
mistralai-mistral-nemo-9330-v108-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v108-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v108-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
mistralai-mistral-nemo-9330-v108-mkmlizer: Downloaded to shared memory in 47.988s
mistralai-mistral-nemo-9330-v108-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa1p6kl77, device:0
mistralai-mistral-nemo-9330-v108-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
mistralai-mistral-nemo-9330-v108-mkmlizer: quantized model in 35.465s
mistralai-mistral-nemo-9330-v108-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 83.454s
mistralai-mistral-nemo-9330-v108-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v108-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v108-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108
mistralai-mistral-nemo-9330-v108-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108/config.json
mistralai-mistral-nemo-9330-v108-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108/special_tokens_map.json
mistralai-mistral-nemo-9330-v108-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108/tokenizer_config.json
mistralai-mistral-nemo-9330-v108-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108/tokenizer.json
mistralai-mistral-nemo-9330-v108-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v108/flywheel_model.0.safetensors
mistralai-mistral-nemo-9330-v108-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.67it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 56.83it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:06, 54.23it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:06, 50.72it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 45.75it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:05, 54.92it/s]
Loading 0:  13%|█▎        | 46/363 [00:00<00:06, 52.82it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:05, 53.34it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 55.07it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.40it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.72it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 43.32it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 38.01it/s]
Loading 0:  25%|██▍       | 89/363 [00:01<00:06, 44.14it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 44.68it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 45.57it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 46.29it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 42.50it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.35it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 40.30it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 43.48it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 43.71it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.77it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.34it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.82it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.87it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:06, 33.70it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:06, 30.69it/s]
Loading 0:  45%|████▌     | 165/363 [00:03<00:05, 39.43it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.84it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 40.78it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 42.55it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 37.55it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.99it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.65it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.03it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 47.49it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 47.83it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.49it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.41it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.28it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.78it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 41.74it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 41.30it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.70it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.13it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 43.10it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 42.35it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 47.43it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 46.67it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 44.21it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 48.03it/s]
Loading 0:  84%|████████▍ | 305/363 [00:13<00:21,  2.66it/s]
Loading 0:  85%|████████▌ | 309/363 [00:13<00:15,  3.39it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.37it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:06,  6.47it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:04,  8.61it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03, 11.28it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 14.60it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 16.87it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 24.35it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 27.82it/s]
Loading 0:  99%|█████████▊| 358/363 [00:15<00:00, 30.45it/s]
                                                            
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Job mistralai-mistral-nemo-9330-v108-mkmlizer completed after 118.6s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v108-mkmlizer
Pipeline stage MKMLizer completed in 122.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v108
Waiting for inference service mistralai-mistral-nemo-9330-v108 to be ready
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v11: ('http://zonemercy-vingt-deux-v2-1e5-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service mistralai-mistral-nemo-9330-v108 ready after 216.3771252632141s
Pipeline stage MKMLDeployer completed in 216.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8569755554199219s
Received healthy response to inference request in 1.6503791809082031s
Received healthy response to inference request in 1.6169002056121826s
Received healthy response to inference request in 2.611536741256714s
Received healthy response to inference request in 2.223762035369873s
5 requests
0 failed requests
5th percentile: 1.6235960006713868
10th percentile: 1.630291795730591
20th percentile: 1.643683385848999
30th percentile: 1.6916984558105468
40th percentile: 1.7743370056152343
50th percentile: 1.8569755554199219
60th percentile: 2.0036901473999023
70th percentile: 2.1504047393798826
80th percentile: 2.301316976547241
90th percentile: 2.4564268589019775
95th percentile: 2.5339818000793457
99th percentile: 2.59602575302124
mean time: 1.991910743713379
Pipeline stage StressChecker completed in 11.92s
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 5.99s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v108 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 0.15s
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-v108-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v108-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v108-profiler ready after 210.52866864204407s
Pipeline stage MKMLProfilerDeployer completed in 210.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-ne2d2b3e87ecc9d2e32295c1c9d8139704-deploqzbfj:/code/chaiverse_profiler_1727202150 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-ne2d2b3e87ecc9d2e32295c1c9d8139704-deploqzbfj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727202150 && python profiles.py profile --best_of_n 8 --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_1727202150/summary.json'
kubectl exec -it mistralai-mistral-ne2d2b3e87ecc9d2e32295c1c9d8139704-deploqzbfj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727202150/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1158.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v108-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v108-profiler
Service mistralai-mistral-nemo-9330-v108-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.23s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v108 status is now torndown due to DeploymentManager action