chaiml-mistralnemo-12b-_86110

developer_uid: NischayDnk

submission_id: chaiml-mistralnemo-12b-_86110_v2

model_name: chaiml-mistralnemo-12b-_86110_v2

model_group: ChaiML/mistralnemo-12b-s

status: torndown

timestamp: 2025-06-29T22:10:08+00:00

num_battles: 6160

num_wins: 3566

celo_rating: 1299.99

family_friendly_score: 0.5304

family_friendly_standard_error: 0.007057986115033097

submission_type: basic

model_repo: ChaiML/mistralnemo-12b-sfts1-exp1-highqualityjun27-s400-fullft-4096-1-1

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': 0.4829862581535643, 'latency_mean': 2.070339673757553, 'latency_p50': 2.0704067945480347, 'latency_p90': 2.2361522674560548}, {'batch_size': 2, 'throughput': 0.6582242799239337, 'latency_mean': 3.0357841837406156, 'latency_p50': 3.0603151321411133, 'latency_p90': 3.2561501264572144}, {'batch_size': 3, 'throughput': 0.7607290164607624, 'latency_mean': 3.937013421058655, 'latency_p50': 3.960175395011902, 'latency_p90': 4.331152725219726}, {'batch_size': 4, 'throughput': 0.8332823529571401, 'latency_mean': 4.787033046483994, 'latency_p50': 4.796554923057556, 'latency_p90': 5.406183767318725}, {'batch_size': 5, 'throughput': 0.8658063775984622, 'latency_mean': 5.756478776931763, 'latency_p50': 5.7935638427734375, 'latency_p90': 6.446917557716369}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistralnemo-12b-_86110_v2

is_internal_developer: False

language_model: ChaiML/mistralnemo-12b-sfts1-exp1-highqualityjun27-s400-fullft-4096-1-1

model_size: 13B

ranking_group: single

throughput_3p7s: 0.74

us_pacific_date: 2025-06-29

win_ratio: 0.5788961038961039

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': ['\n', '<|im_end|>', '<|im_start|>'], '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-86110-v2-mkmlizer
Waiting for job on chaiml-mistralnemo-12b-86110-v2-mkmlizer to finish
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-86110-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistralnemo-12b-86110-v2-mkmlizer: Downloaded to shared memory in 33.539s
chaiml-mistralnemo-12b-86110-v2-mkmlizer: Checking if ChaiML/mistralnemo-12b-sfts1-exp1-highqualityjun27-s400-fullft-4096-1-1 already exists in ChaiML
chaiml-mistralnemo-12b-86110-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_6gwx439, device:0
chaiml-mistralnemo-12b-86110-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistralnemo-12b-86110-v2-mkmlizer: quantized model in 32.675s
chaiml-mistralnemo-12b-86110-v2-mkmlizer: Processed model ChaiML/mistralnemo-12b-sfts1-exp1-highqualityjun27-s400-fullft-4096-1-1 in 66.214s
chaiml-mistralnemo-12b-86110-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistralnemo-12b-86110-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistralnemo-12b-86110-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2
chaiml-mistralnemo-12b-86110-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2/special_tokens_map.json
chaiml-mistralnemo-12b-86110-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2/config.json
chaiml-mistralnemo-12b-86110-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2/tokenizer_config.json
chaiml-mistralnemo-12b-86110-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2/tokenizer.json
chaiml-mistralnemo-12b-86110-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistralnemo-12b-86110-v2/flywheel_model.0.safetensors
chaiml-mistralnemo-12b-86110-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.82it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.12it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.20it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.17it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 46.42it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 44.75it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.85it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.78it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 35.61it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 40.06it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 27.66it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 27.29it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 32.38it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 32.00it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.74it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.99it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 37.00it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 35.27it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.59it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 35.96it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 36.01it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 39.72it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 37.68it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 37.34it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.69it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 35.64it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:06, 36.33it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:06, 33.15it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.99it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.09it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.98it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 33.92it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.04it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.64it/s]
Loading 0:  48%|████▊     | 173/363 [00:04<00:05, 36.21it/s]
Loading 0:  49%|████▉     | 177/363 [00:05<00:05, 31.35it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 33.10it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 29.75it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 36.66it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 34.74it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.92it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 33.43it/s]
Loading 0:  58%|█████▊    | 210/363 [00:06<00:04, 35.30it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:04, 33.52it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 32.39it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:04, 33.33it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:06, 21.06it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:06, 21.68it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:04, 28.95it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:04, 29.61it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 32.86it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 33.67it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 36.44it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.21it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.34it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 37.06it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.35it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:02, 37.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:02, 40.45it/s]
Loading 0:  79%|███████▉  | 287/363 [00:08<00:01, 40.19it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 40.60it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 41.88it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 41.88it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:02, 19.70it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:02, 22.40it/s]
Loading 0:  88%|████████▊ | 320/363 [00:09<00:01, 30.67it/s]
Loading 0:  90%|████████▉ | 325/363 [00:09<00:01, 33.75it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:01, 30.70it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 37.66it/s]
Loading 0:  94%|█████████▍| 342/363 [00:10<00:00, 38.42it/s]
Loading 0:  96%|█████████▌| 347/363 [00:10<00:00, 39.18it/s]
Loading 0:  97%|█████████▋| 352/363 [00:10<00:00, 41.36it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 34.77it/s]
                                                            
Job chaiml-mistralnemo-12b-86110-v2-mkmlizer completed after 95.49s with status: succeeded
Stopping job with name chaiml-mistralnemo-12b-86110-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistralnemo-12b-86110-v2
Waiting for inference service chaiml-mistralnemo-12b-86110-v2 to be ready
Inference service chaiml-mistralnemo-12b-86110-v2 ready after 220.9728274345398s
Pipeline stage MKMLDeployer completed in 221.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.219644546508789s
Received healthy response to inference request in 1.591243028640747s
Received healthy response to inference request in 1.9121754169464111s
Received healthy response to inference request in 1.8212981224060059s
Received healthy response to inference request in 1.679577350616455s
5 requests
0 failed requests
5th percentile: 1.6089098930358887
10th percentile: 1.6265767574310304
20th percentile: 1.6619104862213134
30th percentile: 1.7079215049743652
40th percentile: 1.7646098136901855
50th percentile: 1.8212981224060059
60th percentile: 1.857649040222168
70th percentile: 1.89399995803833
80th percentile: 1.9736692428588867
90th percentile: 2.096656894683838
95th percentile: 2.1581507205963133
99th percentile: 2.207345781326294
mean time: 1.8447876930236817
Pipeline stage StressChecker completed in 10.80s
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 0.67s
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 0.70s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_86110_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistralnemo-12b-86110-v2-profiler
Waiting for inference service chaiml-mistralnemo-12b-86110-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3767.43s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_86110_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistralnemo-12b-_86110_v2 status is now torndown due to DeploymentManager action