chaiml-cogito32-simpoex_18310

developer_uid: NischayDnk

submission_id: chaiml-cogito32-simpoex_18310_v1

model_name: chaiml-cogito32-simpoex_18310_v1

model_group: ChaiML/cogito32-simpoexp

status: torndown

timestamp: 2025-05-15T06:41:36+00:00

num_battles: 7540

num_wins: 3890

celo_rating: 1294.36

family_friendly_score: 0.5426

family_friendly_standard_error: 0.007045356484948083

submission_type: basic

model_repo: ChaiML/cogito32-simpoexp1-s1-retrysfttop20k-1285-singlegpu

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32759331840.0

best_of: 5

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3829189084276944, 'latency_mean': 2.6114639365673065, 'latency_p50': 2.6091861724853516, 'latency_p90': 2.9188698530197144}, {'batch_size': 3, 'throughput': 0.8651938165040789, 'latency_mean': 3.4449891304969786, 'latency_p50': 3.450459837913513, 'latency_p90': 3.810672974586487}, {'batch_size': 5, 'throughput': 1.1840102831264183, 'latency_mean': 4.192613104581833, 'latency_p50': 4.19278621673584, 'latency_p90': 4.66098153591156}, {'batch_size': 6, 'throughput': 1.2905782775494972, 'latency_mean': 4.614785772562027, 'latency_p50': 4.600432515144348, 'latency_p90': 5.18562228679657}, {'batch_size': 8, 'throughput': 1.4638354114214949, 'latency_mean': 5.412649388313294, 'latency_p50': 5.425313353538513, 'latency_p90': 6.118640732765198}, {'batch_size': 10, 'throughput': 1.5935125443278955, 'latency_mean': 6.2137857687473295, 'latency_p50': 6.236922383308411, 'latency_p90': 7.046928882598877}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-cogito32-simpoex_18310_v1

is_internal_developer: False

language_model: ChaiML/cogito32-simpoexp1-s1-retrysfttop20k-1285-singlegpu

model_size: 33B

ranking_group: single

throughput_3p7s: 1.0

us_pacific_date: 2025-05-14

win_ratio: 0.5159151193633952

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 5, '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': False}

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-cogito32-simpoex-18310-v1-mkmlizer
Waiting for job on chaiml-cogito32-simpoex-18310-v1-mkmlizer to finish
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32-simpoex-18310-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32-simpoex-18310-v1-mkmlizer: Downloaded to shared memory in 102.918s
chaiml-cogito32-simpoex-18310-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_gzql2ob, device:0
chaiml-cogito32-simpoex-18310-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32-simpoex-18310-v1-mkmlizer: quantized model in 62.168s
chaiml-cogito32-simpoex-18310-v1-mkmlizer: Processed model ChaiML/cogito32-simpoexp1-s1-retrysfttop20k-1285-singlegpu in 165.086s
chaiml-cogito32-simpoex-18310-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32-simpoex-18310-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32-simpoex-18310-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/added_tokens.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/config.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/special_tokens_map.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/tokenizer_config.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/merges.txt
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/vocab.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/tokenizer.json
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/flywheel_model.2.safetensors
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/flywheel_model.1.safetensors
chaiml-cogito32-simpoex-18310-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32-simpoex-18310-v1/flywheel_model.0.safetensors
chaiml-cogito32-simpoex-18310-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:18, 41.44it/s]
Loading 0:   2%|▏         | 17/771 [00:00<00:10, 69.88it/s]
Loading 0:   4%|▍         | 29/771 [00:00<00:09, 79.02it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:10, 69.40it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:12, 58.81it/s]
Loading 0:   8%|▊         | 65/771 [00:00<00:10, 65.19it/s]
Loading 0:  10%|▉         | 77/771 [00:01<00:09, 71.24it/s]
Loading 0:  12%|█▏        | 89/771 [00:01<00:08, 76.05it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:09, 72.50it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:09, 69.81it/s]
Loading 0:  16%|█▌        | 122/771 [00:01<00:09, 68.34it/s]
Loading 0:  17%|█▋        | 133/771 [00:01<00:08, 71.76it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 92.62it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 80.98it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 59.54it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 56.10it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 58.14it/s]
Loading 0:  26%|██▌       | 197/771 [00:02<00:08, 66.19it/s]
Loading 0:  27%|██▋       | 209/771 [00:03<00:07, 72.61it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:07, 69.86it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:08, 60.35it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 65.49it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 71.28it/s]
Loading 0:  35%|███▍      | 269/771 [00:03<00:06, 76.33it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 73.27it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:07, 62.95it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:07,  2.50it/s]
Loading 0:  41%|████      | 315/771 [00:18<02:05,  3.63it/s]
Loading 0:  42%|████▏     | 327/771 [00:18<01:25,  5.20it/s]
Loading 0:  44%|████▍     | 338/771 [00:18<01:00,  7.16it/s]
Loading 0:  45%|████▍     | 346/771 [00:18<00:48,  8.80it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:41, 10.12it/s]
Loading 0:  47%|████▋     | 365/771 [00:19<00:27, 14.79it/s]
Loading 0:  49%|████▉     | 377/771 [00:19<00:19, 20.58it/s]
Loading 0:  50%|█████     | 389/771 [00:19<00:13, 27.47it/s]
Loading 0:  53%|█████▎    | 406/771 [00:19<00:10, 36.23it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:09, 37.06it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:07, 44.20it/s]
Loading 0:  57%|█████▋    | 437/771 [00:20<00:06, 52.38it/s]
Loading 0:  58%|█████▊    | 449/771 [00:20<00:05, 60.17it/s]
Loading 0:  60%|██████    | 466/771 [00:20<00:04, 61.73it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 54.75it/s]
Loading 0:  63%|██████▎   | 484/771 [00:21<00:04, 62.32it/s]
Loading 0:  64%|██████▍   | 495/771 [00:21<00:03, 71.25it/s]
Loading 0:  65%|██████▌   | 505/771 [00:21<00:03, 77.20it/s]
Loading 0:  67%|██████▋   | 514/771 [00:21<00:03, 75.40it/s]
Loading 0:  68%|██████▊   | 526/771 [00:21<00:03, 64.73it/s]
Loading 0:  69%|██████▉   | 534/771 [00:21<00:04, 56.62it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 63.19it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 69.69it/s]
Loading 0:  74%|███████▍  | 569/771 [00:22<00:02, 75.59it/s]
Loading 0:  76%|███████▌  | 586/771 [00:22<00:02, 72.89it/s]
Loading 0:  77%|███████▋  | 594/771 [00:22<00:02, 62.28it/s]
Loading 0:  78%|███████▊  | 605/771 [00:22<00:02, 67.09it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 72.29it/s]
Loading 0:  81%|████████▏ | 627/771 [00:37<00:57,  2.51it/s]
Loading 0:  83%|████████▎ | 638/771 [00:37<00:37,  3.54it/s]
Loading 0:  84%|████████▍ | 646/771 [00:37<00:27,  4.48it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:21,  5.50it/s]
Loading 0:  86%|████████▋ | 665/771 [00:38<00:12,  8.28it/s]
Loading 0:  88%|████████▊ | 677/771 [00:38<00:07, 11.95it/s]
Loading 0:  89%|████████▉ | 689/771 [00:38<00:04, 16.66it/s]
Loading 0:  92%|█████████▏| 706/771 [00:38<00:02, 23.67it/s]
Loading 0:  93%|█████████▎| 714/771 [00:38<00:02, 25.92it/s]
Loading 0:  94%|█████████▍| 725/771 [00:38<00:01, 32.46it/s]
Loading 0:  96%|█████████▌| 737/771 [00:39<00:00, 40.50it/s]
Loading 0:  97%|█████████▋| 749/771 [00:39<00:00, 48.71it/s]
Loading 0:  99%|█████████▉| 766/771 [00:46<00:00,  5.37it/s]
                                                            
Job chaiml-cogito32-simpoex-18310-v1-mkmlizer completed after 196.8s with status: succeeded
Stopping job with name chaiml-cogito32-simpoex-18310-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.31s
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-cogito32-simpoex-18310-v1
Waiting for inference service chaiml-cogito32-simpoex-18310-v1 to be ready
Inference service chaiml-cogito32-simpoex-18310-v1 ready after 140.55848240852356s
Pipeline stage MKMLDeployer completed in 141.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.365885019302368s
Received healthy response to inference request in 2.565089225769043s
Received healthy response to inference request in 2.769705295562744s
Received healthy response to inference request in 2.641003370285034s
Received healthy response to inference request in 2.4896624088287354s
5 requests
0 failed requests
5th percentile: 2.504747772216797
10th percentile: 2.519833135604858
20th percentile: 2.5500038623809815
30th percentile: 2.5802720546722413
40th percentile: 2.6106377124786375
50th percentile: 2.641003370285034
60th percentile: 2.692484140396118
70th percentile: 2.743964910507202
80th percentile: 2.888941240310669
90th percentile: 3.1274131298065186
95th percentile: 3.246649074554443
99th percentile: 3.3420378303527833
mean time: 2.766269063949585
Pipeline stage StressChecker completed in 15.07s
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 0.98s
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-cogito32-simpoex_18310_v1 status is now deployed due to DeploymentManager action
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 3212.47s
Shutdown handler de-registered
chaiml-cogito32-simpoex_18310_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32-simpoex_18310_v1 status is now torndown due to DeploymentManager action