developer_uid: NischayDnk
submission_id: chaiml-mistralnemo-12b-_31569_v4
model_name: chaiml-mistralnemo-12b-_31569_v4
model_group: ChaiML/mistralnemo-12b-s
status: torndown
timestamp: 2025-07-01T23:23:02+00:00
num_battles: 6438
num_wins: 3598
celo_rating: 1337.24
family_friendly_score: 0.4982
family_friendly_standard_error: 0.007071021991197595
submission_type: basic
model_repo: ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1536
max_output_tokens: 96
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.40876552494049556, 'latency_mean': 2.446267819404602, 'latency_p50': 2.438633680343628, 'latency_p90': 2.6158790588378906}, {'batch_size': 3, 'throughput': 0.8049270755437838, 'latency_mean': 3.717128784656525, 'latency_p50': 3.721401333808899, 'latency_p90': 3.966426420211792}, {'batch_size': 5, 'throughput': 0.9940421446591801, 'latency_mean': 5.00459535241127, 'latency_p50': 4.9914573431015015, 'latency_p90': 5.524037027359008}, {'batch_size': 6, 'throughput': 1.0563353895083687, 'latency_mean': 5.645563027858734, 'latency_p50': 5.639049649238586, 'latency_p90': 6.179462170600891}, {'batch_size': 10, 'throughput': 1.1825171633809397, 'latency_mean': 8.388506262302398, 'latency_p50': 8.387065291404724, 'latency_p90': 9.217010974884033}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistralnemo-12b-_31569_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2
model_size: 13B
ranking_group: single
throughput_3p7s: 0.8
us_pacific_date: 2025-07-01
win_ratio: 0.5588692140416278
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|>', '<|im_end|>', '\n'], 'max_input_tokens': 1536, 'best_of': 4, 'max_output_tokens': 96}
formatter: {'memory_template': '<|system|>{bot_name}memory: {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-12b-31569-v4-mkmlizer
Waiting for job on chaiml-mistralnemo-12b-31569-v4-mkmlizer to finish
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ║                                                                     ║
chaiml-mistralnemo-12b-31569-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistralnemo-12b-31569-v4-mkmlizer: Downloaded to shared memory in 30.756s
chaiml-mistralnemo-12b-31569-v4-mkmlizer: Checking if ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2 already exists in ChaiML
chaiml-mistralnemo-12b-31569-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmpshz058, device:0
chaiml-mistralnemo-12b-31569-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistralnemo-12b-31569-v4-mkmlizer: quantized model in 31.492s
chaiml-mistralnemo-12b-31569-v4-mkmlizer: Processed model ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2 in 62.248s
chaiml-mistralnemo-12b-31569-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistralnemo-12b-31569-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistralnemo-12b-31569-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4
chaiml-mistralnemo-12b-31569-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4/config.json
chaiml-mistralnemo-12b-31569-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4/special_tokens_map.json
chaiml-mistralnemo-12b-31569-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4/tokenizer_config.json
chaiml-mistralnemo-12b-31569-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4/tokenizer.json
chaiml-mistralnemo-12b-31569-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v4/flywheel_model.0.safetensors
chaiml-mistralnemo-12b-31569-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.35it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.53it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.37it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.55it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.03it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 42.93it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.10it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.70it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.80it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:06, 44.50it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:10, 28.43it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:09, 29.91it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.64it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 35.53it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.98it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.58it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.12it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 39.77it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.35it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 42.35it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.69it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 36.70it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.22it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.38it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.32it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 44.08it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.42it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 26.87it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.78it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.42it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.11it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.77it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.82it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.77it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 39.91it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.60it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.39it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.89it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.94it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.08it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.59it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.80it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.08it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.74it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.09it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.54it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 39.06it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 32.53it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.67it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 40.04it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.66it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 41.45it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.68it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.57it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.32it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 41.97it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 22.62it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.05it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.54it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 32.18it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:01, 34.06it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:00, 33.65it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 41.48it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 41.89it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 42.23it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 42.69it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 35.37it/s]
                                                            

Job chaiml-mistralnemo-12b-31569-v4-mkmlizer completed after 85.71s with status: succeeded
Stopping job with name chaiml-mistralnemo-12b-31569-v4-mkmlizer
Pipeline stage MKMLizer completed in 86.29s
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 chaiml-mistralnemo-12b-31569-v4
Waiting for inference service chaiml-mistralnemo-12b-31569-v4 to be ready
Inference service chaiml-mistralnemo-12b-31569-v4 ready after 211.50015878677368s
Pipeline stage MKMLDeployer completed in 212.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.718184471130371s
Received healthy response to inference request in 2.1947174072265625s
Received healthy response to inference request in 2.4381089210510254s
Received healthy response to inference request in 2.3042120933532715s
Received healthy response to inference request in 2.261990785598755s
5 requests
0 failed requests
5th percentile: 2.208172082901001
10th percentile: 2.2216267585754395
20th percentile: 2.2485361099243164
30th percentile: 2.2704350471496584
40th percentile: 2.287323570251465
50th percentile: 2.3042120933532715
60th percentile: 2.357770824432373
70th percentile: 2.4113295555114744
80th percentile: 2.4941240310668946
90th percentile: 2.6061542510986326
95th percentile: 2.662169361114502
99th percentile: 2.706981449127197
mean time: 2.383442735671997
Pipeline stage StressChecker completed in 13.21s
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 0.64s
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 0.81s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_31569_v4 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistralnemo-12b-31569-v4-profiler
Waiting for inference service chaiml-mistralnemo-12b-31569-v4-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 3270.04s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_31569_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistralnemo-12b-_31569_v4 status is now torndown due to DeploymentManager action