chaiml-mistralnemo-nis-_16053

developer_uid: NischayDnk

submission_id: chaiml-mistralnemo-nis-_16053_v1

model_name: chaiml-mistralnemo-nis-_16053_v1

model_group: ChaiML/mistralnemo_nis_d

status: torndown

timestamp: 2025-07-08T16:22:49+00:00

num_battles: 7914

num_wins: 4081

celo_rating: 1305.34

family_friendly_score: 0.5472

family_friendly_standard_error: 0.0070394908906823645

submission_type: basic

model_repo: ChaiML/mistralnemo_nis_deepseek_sfttop10klex_sfts2_sftexp1_1300_v3_pubpref

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.47745322089139897, 'latency_mean': 2.09429257273674, 'latency_p50': 2.0985515117645264, 'latency_p90': 2.282950925827026}, {'batch_size': 2, 'throughput': 0.6590502126473144, 'latency_mean': 3.0278329837322233, 'latency_p50': 3.030847191810608, 'latency_p90': 3.313607692718506}, {'batch_size': 3, 'throughput': 0.754798375096989, 'latency_mean': 3.9659880447387694, 'latency_p50': 3.958251953125, 'latency_p90': 4.297351336479187}, {'batch_size': 4, 'throughput': 0.8202701353127417, 'latency_mean': 4.856522462368011, 'latency_p50': 4.8714141845703125, 'latency_p90': 5.401762223243713}, {'batch_size': 5, 'throughput': 0.8549040455864251, 'latency_mean': 5.8333616483211514, 'latency_p50': 5.822508454322815, 'latency_p90': 6.435571026802063}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistralnemo-nis-_16053_v1

is_internal_developer: False

language_model: ChaiML/mistralnemo_nis_deepseek_sfttop10klex_sfts2_sftexp1_1300_v3_pubpref

model_size: 13B

ranking_group: single

throughput_3p7s: 0.73

us_pacific_date: 2025-07-08

win_ratio: 0.5156684356835987

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['<|im_end|>', '</s>', '###', '\n', '<|im_start|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}

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 chaiml-mistralnemo-nis-16053-v1-mkmlizer
Waiting for job on chaiml-mistralnemo-nis-16053-v1-mkmlizer to finish
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-nis-16053-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistralnemo-nis-16053-v1-mkmlizer: Downloaded to shared memory in 42.333s
chaiml-mistralnemo-nis-16053-v1-mkmlizer: Checking if ChaiML/mistralnemo_nis_deepseek_sfttop10klex_sfts2_sftexp1_1300_v3_pubpref already exists in ChaiML
chaiml-mistralnemo-nis-16053-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0frhv1hb, device:0
chaiml-mistralnemo-nis-16053-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistralnemo-nis-16053-v1-mkmlizer: quantized model in 31.442s
chaiml-mistralnemo-nis-16053-v1-mkmlizer: Processed model ChaiML/mistralnemo_nis_deepseek_sfttop10klex_sfts2_sftexp1_1300_v3_pubpref in 73.776s
chaiml-mistralnemo-nis-16053-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistralnemo-nis-16053-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistralnemo-nis-16053-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia
chaiml-mistralnemo-nis-16053-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia/config.json
chaiml-mistralnemo-nis-16053-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia/special_tokens_map.json
chaiml-mistralnemo-nis-16053-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia/tokenizer_config.json
chaiml-mistralnemo-nis-16053-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia/tokenizer.json
chaiml-mistralnemo-nis-16053-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistralnemo-nis-16053-v1/nvidia/flywheel_model.0.safetensors
chaiml-mistralnemo-nis-16053-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:37,  3.10s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:57,  1.20it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:36,  3.61it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:58,  5.83it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:44,  7.55it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:26, 12.57it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:20, 16.18it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:20, 15.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:15, 20.06it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:14, 21.83it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:11, 25.55it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:11, 27.03it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:09, 31.00it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 30.94it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.25it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 33.96it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 38.31it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 40.12it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:08, 33.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 40.48it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 39.11it/s]
Loading 0:  31%|███       | 113/363 [00:09<00:06, 39.56it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 40.89it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 24.12it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 31.75it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 33.56it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:06, 36.21it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:05, 39.22it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 33.88it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 40.70it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 39.17it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 38.79it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 40.56it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:05, 34.22it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 40.51it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 38.95it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 39.71it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 42.11it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 25.04it/s]
Loading 0:  58%|█████▊    | 209/363 [00:12<00:05, 29.18it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:05, 27.62it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.78it/s]
Loading 0:  62%|██████▏   | 225/363 [00:12<00:03, 35.96it/s]
Loading 0:  63%|██████▎   | 230/363 [00:12<00:03, 36.98it/s]
Loading 0:  65%|██████▍   | 235/363 [00:12<00:03, 38.43it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 33.79it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 41.29it/s]
Loading 0:  69%|██████▉   | 252/363 [00:13<00:02, 41.12it/s]
Loading 0:  71%|███████   | 257/363 [00:13<00:02, 41.97it/s]
Loading 0:  72%|███████▏  | 262/363 [00:13<00:02, 43.86it/s]
Loading 0:  74%|███████▎  | 267/363 [00:13<00:02, 35.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 42.55it/s]
Loading 0:  77%|███████▋  | 279/363 [00:13<00:01, 42.63it/s]
Loading 0:  78%|███████▊  | 284/363 [00:14<00:02, 29.20it/s]
Loading 0:  79%|███████▉  | 288/363 [00:14<00:02, 30.41it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:02, 33.38it/s]
Loading 0:  82%|████████▏ | 298/363 [00:14<00:01, 36.70it/s]
Loading 0:  83%|████████▎ | 303/363 [00:14<00:01, 31.76it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 39.59it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 40.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 40.06it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:00, 41.29it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:00, 35.92it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 41.99it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 40.99it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 41.58it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 41.91it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 33.39it/s]
                                                            
Job chaiml-mistralnemo-nis-16053-v1-mkmlizer completed after 95.48s with status: succeeded
Stopping job with name chaiml-mistralnemo-nis-16053-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistralnemo-nis-16053-v1
Waiting for inference service chaiml-mistralnemo-nis-16053-v1 to be ready
Inference service chaiml-mistralnemo-nis-16053-v1 ready after 190.82659006118774s
Pipeline stage MKMLDeployer completed in 191.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.177748680114746s
Received healthy response to inference request in 1.6561481952667236s
Received healthy response to inference request in 1.622241735458374s
Received healthy response to inference request in 2.1666300296783447s
Received healthy response to inference request in 1.56597900390625s
5 requests
0 failed requests
5th percentile: 1.5772315502166747
10th percentile: 1.5884840965270997
20th percentile: 1.6109891891479493
30th percentile: 1.629023027420044
40th percentile: 1.6425856113433839
50th percentile: 1.6561481952667236
60th percentile: 1.860340929031372
70th percentile: 2.0645336627960202
80th percentile: 2.168853759765625
90th percentile: 2.1733012199401855
95th percentile: 2.175524950027466
99th percentile: 2.17730393409729
mean time: 1.8377495288848877
Pipeline stage StressChecker completed in 10.45s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.87s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.64s
Shutdown handler de-registered
chaiml-mistralnemo-nis-_16053_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3389.52s
Shutdown handler de-registered
chaiml-mistralnemo-nis-_16053_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistralnemo-nis-_16053_v1 status is now torndown due to DeploymentManager action