chaiml-mistralnemo-12b-s_9408

developer_uid: NischayDnk

submission_id: chaiml-mistralnemo-12b-s_9408_v1

model_name: chaiml-mistralnemo-12b-s_9408_v1

model_group: ChaiML/mistralnemo-12b-s

status: torndown

timestamp: 2025-06-30T01:56:14+00:00

num_battles: 6818

num_wins: 3632

celo_rating: 1291.02

family_friendly_score: 0.5378000000000001

family_friendly_standard_error: 0.007050832007642786

submission_type: basic

model_repo: ChaiML/mistralnemo-12b-sfts1-exp1-manualhighqualityjun27-s32-fullft-4096

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': 0.47331877295224073, 'latency_mean': 2.1126250684261323, 'latency_p50': 2.119653820991516, 'latency_p90': 2.2860456466674806}, {'batch_size': 2, 'throughput': 0.6374278997381596, 'latency_mean': 3.1323917543888093, 'latency_p50': 3.126074194908142, 'latency_p90': 3.346680736541748}, {'batch_size': 3, 'throughput': 0.7436022870991832, 'latency_mean': 4.023618615865708, 'latency_p50': 4.027038931846619, 'latency_p90': 4.473671126365661}, {'batch_size': 4, 'throughput': 0.8030303933053516, 'latency_mean': 4.9728974437713624, 'latency_p50': 4.971143841743469, 'latency_p90': 5.60879807472229}, {'batch_size': 5, 'throughput': 0.8359734205351591, 'latency_mean': 5.963222690820694, 'latency_p50': 5.955172300338745, 'latency_p90': 6.7565409421920775}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistralnemo-12b-s_9408_v1

is_internal_developer: False

language_model: ChaiML/mistralnemo-12b-sfts1-exp1-manualhighqualityjun27-s32-fullft-4096

model_size: 13B

ranking_group: single

throughput_3p7s: 0.71

us_pacific_date: 2025-06-29

win_ratio: 0.5327075388677032

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_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '<|system|>Family Friendly{prompt}\n', '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-12b-s-9408-v1-mkmlizer
Waiting for job on chaiml-mistralnemo-12b-s-9408-v1-mkmlizer to finish
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: Downloaded to shared memory in 45.385s
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: Checking if ChaiML/mistralnemo-12b-sfts1-exp1-manualhighqualityjun27-s32-fullft-4096 already exists in ChaiML
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2kr_tr9j, device:0
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: quantized model in 30.721s
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: Processed model ChaiML/mistralnemo-12b-sfts1-exp1-manualhighqualityjun27-s32-fullft-4096 in 76.107s
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1/config.json
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1/special_tokens_map.json
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1/tokenizer_config.json
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1/tokenizer.json
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistralnemo-12b-s-9408-v1/flywheel_model.0.safetensors
chaiml-mistralnemo-12b-s-9408-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.04it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 49.27it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 49.29it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.22it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.83it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.65it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.84it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.67it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.42it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 43.88it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 29.92it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.58it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.11it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.03it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 41.34it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.03it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.02it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 43.37it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 37.02it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 37.48it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:05, 40.14it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 38.39it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 42.27it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 41.69it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 26.69it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.91it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.08it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.32it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.73it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.06it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.11it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 38.75it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 39.28it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.19it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 40.23it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.11it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 41.11it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.21it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.70it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 27.01it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.85it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:03, 32.61it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 31.60it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.61it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 39.26it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.23it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 42.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 34.66it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 41.73it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 41.75it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.33it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 43.19it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 35.81it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 39.07it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 22.40it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 24.71it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 25.08it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.12it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:01, 36.95it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 33.50it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 40.89it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 40.74it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 41.09it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 43.03it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 36.41it/s]
                                                            
Job chaiml-mistralnemo-12b-s-9408-v1-mkmlizer completed after 104.64s with status: succeeded
Stopping job with name chaiml-mistralnemo-12b-s-9408-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.13s
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-12b-s-9408-v1
Waiting for inference service chaiml-mistralnemo-12b-s-9408-v1 to be ready
Inference service chaiml-mistralnemo-12b-s-9408-v1 ready after 210.92009162902832s
Pipeline stage MKMLDeployer completed in 211.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3317861557006836s
Received healthy response to inference request in 1.576639175415039s
Received healthy response to inference request in 2.258690118789673s
Received healthy response to inference request in 1.8453927040100098s
Received healthy response to inference request in 1.7541635036468506s
5 requests
0 failed requests
5th percentile: 1.6121440410614014
10th percentile: 1.6476489067077638
20th percentile: 1.7186586380004882
30th percentile: 1.7724093437194823
40th percentile: 1.808901023864746
50th percentile: 1.8453927040100098
60th percentile: 2.010711669921875
70th percentile: 2.1760306358337402
80th percentile: 2.273309326171875
90th percentile: 2.302547740936279
95th percentile: 2.3171669483184814
99th percentile: 2.328862314224243
mean time: 1.9533343315124512
Pipeline stage StressChecker completed in 11.09s
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 0.68s
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 0.67s
Shutdown handler de-registered
chaiml-mistralnemo-12b-s_9408_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistralnemo-12b-s-9408-v1-profiler
Waiting for inference service chaiml-mistralnemo-12b-s-9408-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5635.03s
Shutdown handler de-registered
chaiml-mistralnemo-12b-s_9408_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistralnemo-12b-s_9408_v1 status is now torndown due to DeploymentManager action