chaiml-nis-cogito-32b-s_10984

developer_uid: NischayDnk

submission_id: chaiml-nis-cogito-32b-s_10984_v3

model_name: chaiml-nis-cogito-32b-s_10984_v3

model_group: ChaiML/nis-cogito-32b-sf

status: torndown

timestamp: 2025-04-18T17:33:20+00:00

num_battles: 7117

num_wins: 3429

celo_rating: 1272.71

family_friendly_score: 0.5868

family_friendly_standard_error: 0.006963702463488802

submission_type: basic

model_repo: ChaiML/nis-cogito-32b-sft-exp1-datav1ffsys20k-1

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32759331840.0

best_of: 1

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.2729368083619666, 'latency_mean': 3.6637538862228394, 'latency_p50': 3.6574132442474365, 'latency_p90': 4.020806193351746}, {'batch_size': 2, 'throughput': 0.44426831105235376, 'latency_mean': 4.488776650428772, 'latency_p50': 4.452016234397888, 'latency_p90': 4.949472856521607}, {'batch_size': 3, 'throughput': 0.593720908333152, 'latency_mean': 5.0402797508239745, 'latency_p50': 5.055628061294556, 'latency_p90': 5.495662093162537}, {'batch_size': 5, 'throughput': 0.8098072989945704, 'latency_mean': 6.128714357614517, 'latency_p50': 6.09495997428894, 'latency_p90': 6.888783812522888}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-nis-cogito-32b-s_10984_v3

is_internal_developer: False

language_model: ChaiML/nis-cogito-32b-sft-exp1-datav1ffsys20k-1

model_size: 33B

ranking_group: single

throughput_3p7s: 0.28

us_pacific_date: 2025-04-18

win_ratio: 0.48180413095405367

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 1, '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-nis-cogito-32b-s-10984-v3-mkmlizer
Waiting for job on chaiml-nis-cogito-32b-s-10984-v3-mkmlizer to finish
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║       /___/                                                         ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║                                                                     ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║                                                                     ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║                                                                     ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ║                                                                     ║
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: Downloaded to shared memory in 98.143s
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzs35p7f7, device:0
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: quantized model in 64.324s
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: Processed model ChaiML/nis-cogito-32b-sft-exp1-datav1ffsys20k-1 in 162.468s
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/config.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/added_tokens.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/special_tokens_map.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/tokenizer_config.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/merges.txt
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/vocab.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/tokenizer.json
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/flywheel_model.2.safetensors
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/flywheel_model.0.safetensors
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito-32b-s-10984-v3/flywheel_model.1.safetensors
chaiml-nis-cogito-32b-s-10984-v3-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.39it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 74.99it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 88.57it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 90.82it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 54.15it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:13, 52.02it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 59.95it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 71.22it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 75.46it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 71.94it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 61.61it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 59.05it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:10, 59.33it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 69.56it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 76.47it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 82.11it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 77.14it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:11, 54.62it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 54.09it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 55.92it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 67.56it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.36it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.14it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 62.09it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 53.35it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 62.39it/s]
Loading 0:  33%|███▎      | 255/771 [00:03<00:07, 72.89it/s]
Loading 0:  34%|███▍      | 264/771 [00:03<00:06, 76.17it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:06, 72.76it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 63.36it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 54.27it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:44,  2.09it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:43,  2.81it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:02,  3.68it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:21,  5.45it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<00:55,  7.86it/s]
Loading 0:  45%|████▌     | 347/771 [00:20<00:43,  9.75it/s]
Loading 0:  46%|████▌     | 354/771 [00:20<00:34, 12.00it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:23, 17.01it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 23.96it/s]
Loading 0:  50%|████▉     | 384/771 [00:20<00:12, 30.30it/s]
Loading 0:  51%|█████     | 393/771 [00:20<00:10, 35.99it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:09, 40.49it/s]
Loading 0:  54%|█████▎    | 414/771 [00:21<00:08, 39.78it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 48.77it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:05, 59.18it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 64.65it/s]
Loading 0:  59%|█████▉    | 453/771 [00:21<00:04, 64.91it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:05, 58.10it/s]
Loading 0:  61%|██████▏   | 473/771 [00:22<00:05, 50.06it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 60.89it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 70.95it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 74.77it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 71.87it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 63.16it/s]
Loading 0:  69%|██████▉   | 534/771 [00:23<00:04, 54.15it/s]
Loading 0:  71%|███████   | 545/771 [00:23<00:03, 60.12it/s]
Loading 0:  72%|███████▏  | 556/771 [00:23<00:03, 70.00it/s]
Loading 0:  74%|███████▎  | 567/771 [00:23<00:02, 78.79it/s]
Loading 0:  75%|███████▍  | 576/771 [00:23<00:02, 80.77it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 61.82it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:03, 53.57it/s]
Loading 0:  78%|███████▊  | 605/771 [00:24<00:02, 59.79it/s]
Loading 0:  80%|███████▉  | 616/771 [00:24<00:02, 70.01it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:02,  2.31it/s]
Loading 0:  82%|████████▏ | 635/771 [00:39<00:44,  3.03it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:28,  4.31it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:22,  5.32it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:13,  7.85it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:08, 11.25it/s]
Loading 0:  89%|████████▉ | 685/771 [00:40<00:05, 15.28it/s]
Loading 0:  90%|█████████ | 694/771 [00:40<00:03, 19.44it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:02, 24.43it/s]
Loading 0:  93%|█████████▎| 714/771 [00:40<00:02, 26.81it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 34.14it/s]
Loading 0:  95%|█████████▌| 736/771 [00:40<00:00, 43.51it/s]
Loading 0:  97%|█████████▋| 747/771 [00:40<00:00, 53.34it/s]
Loading 0:  98%|█████████▊| 756/771 [00:41<00:00, 59.65it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.07it/s]
                                                            
Job chaiml-nis-cogito-32b-s-10984-v3-mkmlizer completed after 207.57s with status: succeeded
Stopping job with name chaiml-nis-cogito-32b-s-10984-v3-mkmlizer
Pipeline stage MKMLizer completed in 208.05s
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-nis-cogito-32b-s-10984-v3
Waiting for inference service chaiml-nis-cogito-32b-s-10984-v3 to be ready
Inference service chaiml-nis-cogito-32b-s-10984-v3 ready after 130.61424326896667s
Pipeline stage MKMLDeployer completed in 131.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7976789474487305s
Received healthy response to inference request in 3.176107406616211s
Received healthy response to inference request in 3.092473030090332s
Received healthy response to inference request in 3.0947136878967285s
Received healthy response to inference request in 3.133930206298828s
5 requests
0 failed requests
5th percentile: 3.0929211616516112
10th percentile: 3.0933692932128904
20th percentile: 3.0942655563354493
30th percentile: 3.1025569915771483
40th percentile: 3.118243598937988
50th percentile: 3.133930206298828
60th percentile: 3.150801086425781
70th percentile: 3.167671966552734
80th percentile: 3.300421714782715
90th percentile: 3.5490503311157227
95th percentile: 3.6733646392822266
99th percentile: 3.7728160858154296
mean time: 3.258980655670166
Pipeline stage StressChecker completed in 17.76s
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 0.71s
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-nis-cogito-32b-s_10984_v3 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 0.09s
run pipeline stage %s
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 6150.42s
Shutdown handler de-registered
chaiml-nis-cogito-32b-s_10984_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-cogito-32b-s_10984_v3 status is now torndown due to DeploymentManager action