chaiml-cogito32b-retryv_56788

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-retryv_56788_v1

model_name: chaiml-cogito32b-retryv_56788_v1

model_group: ChaiML/cogito32b-retryv2

status: torndown

timestamp: 2025-05-16T07:16:39+00:00

num_battles: 7680

num_wins: 3743

celo_rating: 1276.43

family_friendly_score: 0.567

family_friendly_standard_error: 0.007007296197535822

submission_type: basic

model_repo: ChaiML/cogito32b-retryv2top20k-cpoexp1-s1-pred1285sft

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': 0.3895398006046731, 'latency_mean': 2.5670777428150178, 'latency_p50': 2.5516473054885864, 'latency_p90': 2.894640493392944}, {'batch_size': 3, 'throughput': 0.8704084532258459, 'latency_mean': 3.435813889503479, 'latency_p50': 3.4243667125701904, 'latency_p90': 3.796301007270813}, {'batch_size': 5, 'throughput': 1.1951237725749986, 'latency_mean': 4.165567462444305, 'latency_p50': 4.128662824630737, 'latency_p90': 4.687777781486512}, {'batch_size': 6, 'throughput': 1.3054042247024014, 'latency_mean': 4.553759704828263, 'latency_p50': 4.514061093330383, 'latency_p90': 5.119121766090393}, {'batch_size': 8, 'throughput': 1.4889677915199433, 'latency_mean': 5.33998740196228, 'latency_p50': 5.355061411857605, 'latency_p90': 5.8999429702758786}, {'batch_size': 10, 'throughput': 1.6253882810980775, 'latency_mean': 6.094603025913239, 'latency_p50': 6.094334840774536, 'latency_p90': 6.8939286231994625}]

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

display_name: chaiml-cogito32b-retryv_56788_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-retryv2top20k-cpoexp1-s1-pred1285sft

model_size: 33B

ranking_group: single

throughput_3p7s: 1.01

us_pacific_date: 2025-05-16

win_ratio: 0.48736979166666666

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': ['<|im_start|>', '\n', '<|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-cogito32b-retryv-56788-v1-mkmlizer
Waiting for job on chaiml-cogito32b-retryv-56788-v1-mkmlizer to finish
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-56788-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-retryv-56788-v1-mkmlizer: Downloaded to shared memory in 101.028s
chaiml-cogito32b-retryv-56788-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwii30jw7, device:0
chaiml-cogito32b-retryv-56788-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-retryv-56788-v1-mkmlizer: quantized model in 62.655s
chaiml-cogito32b-retryv-56788-v1-mkmlizer: Processed model ChaiML/cogito32b-retryv2top20k-cpoexp1-s1-pred1285sft in 163.683s
chaiml-cogito32b-retryv-56788-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-retryv-56788-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-retryv-56788-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/config.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/added_tokens.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/special_tokens_map.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/tokenizer_config.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/merges.txt
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/vocab.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/tokenizer.json
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/flywheel_model.2.safetensors
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/flywheel_model.0.safetensors
chaiml-cogito32b-retryv-56788-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-56788-v1/flywheel_model.1.safetensors
chaiml-cogito32b-retryv-56788-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:18, 40.61it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 77.16it/s]
Loading 0:   4%|▎         | 28/771 [00:00<00:08, 82.74it/s]
Loading 0:   5%|▌         | 39/771 [00:00<00:07, 92.11it/s]
Loading 0:   6%|▋         | 49/771 [00:00<00:13, 55.41it/s]
Loading 0:   7%|▋         | 57/771 [00:00<00:12, 57.27it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:11, 58.96it/s]
Loading 0:  10%|▉         | 77/771 [00:01<00:10, 67.44it/s]
Loading 0:  12%|█▏        | 89/771 [00:01<00:09, 73.57it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:09, 70.23it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:09, 68.13it/s]
Loading 0:  16%|█▌        | 122/771 [00:01<00:09, 66.62it/s]
Loading 0:  17%|█▋        | 133/771 [00:01<00:09, 70.53it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 92.02it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 80.88it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 59.62it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 58.53it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:09, 59.85it/s]
Loading 0:  26%|██▌       | 197/771 [00:02<00:08, 67.38it/s]
Loading 0:  27%|██▋       | 209/771 [00:03<00:07, 73.23it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:07, 68.82it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:08, 59.81it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 64.89it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 70.71it/s]
Loading 0:  35%|███▍      | 269/771 [00:03<00:06, 75.34it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 70.69it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:07, 60.86it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:06,  2.50it/s]
Loading 0:  41%|████      | 315/771 [00:18<02:05,  3.64it/s]
Loading 0:  42%|████▏     | 327/771 [00:18<01:25,  5.22it/s]
Loading 0:  44%|████▎     | 337/771 [00:18<01:01,  7.03it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:47,  8.86it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:40, 10.20it/s]
Loading 0:  47%|████▋     | 365/771 [00:19<00:27, 14.84it/s]
Loading 0:  49%|████▉     | 377/771 [00:19<00:19, 20.62it/s]
Loading 0:  50%|█████     | 389/771 [00:19<00:13, 27.46it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 35.43it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:09, 36.29it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:07, 43.46it/s]
Loading 0:  57%|█████▋    | 437/771 [00:20<00:06, 51.77it/s]
Loading 0:  58%|█████▊    | 449/771 [00:20<00:05, 59.35it/s]
Loading 0:  60%|██████    | 466/771 [00:20<00:04, 61.55it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 55.32it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 61.09it/s]
Loading 0:  64%|██████▍   | 497/771 [00:21<00:04, 67.52it/s]
Loading 0:  66%|██████▌   | 509/771 [00:21<00:03, 72.59it/s]
Loading 0:  68%|██████▊   | 526/771 [00:21<00:03, 70.26it/s]
Loading 0:  69%|██████▉   | 534/771 [00:21<00:03, 60.34it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 65.28it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 71.00it/s]
Loading 0:  74%|███████▍  | 569/771 [00:22<00:02, 75.58it/s]
Loading 0:  76%|███████▌  | 586/771 [00:22<00:02, 70.90it/s]
Loading 0:  77%|███████▋  | 594/771 [00:22<00:02, 61.41it/s]
Loading 0:  78%|███████▊  | 605/771 [00:22<00:02, 66.21it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 71.53it/s]
Loading 0:  81%|████████▏ | 627/771 [00:37<00:57,  2.51it/s]
Loading 0:  83%|████████▎ | 638/771 [00:37<00:37,  3.52it/s]
Loading 0:  84%|████████▍ | 646/771 [00:37<00:28,  4.45it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:21,  5.46it/s]
Loading 0:  86%|████████▋ | 665/771 [00:38<00:12,  8.22it/s]
Loading 0:  88%|████████▊ | 677/771 [00:38<00:07, 11.86it/s]
Loading 0:  89%|████████▉ | 689/771 [00:38<00:04, 16.52it/s]
Loading 0:  92%|█████████▏| 706/771 [00:38<00:02, 23.64it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 25.90it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 32.38it/s]
Loading 0:  96%|█████████▌| 737/771 [00:39<00:00, 40.38it/s]
Loading 0:  97%|█████████▋| 749/771 [00:39<00:00, 48.58it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:00,  5.28it/s]
                                                            
Job chaiml-cogito32b-retryv-56788-v1-mkmlizer completed after 196.77s with status: succeeded
Stopping job with name chaiml-cogito32b-retryv-56788-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.50s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-retryv-56788-v1
Waiting for inference service chaiml-cogito32b-retryv-56788-v1 to be ready
Inference service chaiml-cogito32b-retryv-56788-v1 ready after 140.60469460487366s
Pipeline stage MKMLDeployer completed in 141.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.085577964782715s
Received healthy response to inference request in 2.699453353881836s
Received healthy response to inference request in 2.8073275089263916s
Received healthy response to inference request in 2.7215330600738525s
Received healthy response to inference request in 2.526743173599243s
5 requests
0 failed requests
5th percentile: 2.561285209655762
10th percentile: 2.59582724571228
20th percentile: 2.664911317825317
30th percentile: 2.7038692951202394
40th percentile: 2.712701177597046
50th percentile: 2.7215330600738525
60th percentile: 2.755850839614868
70th percentile: 2.790168619155884
80th percentile: 2.8629776000976563
90th percentile: 2.9742777824401854
95th percentile: 3.02992787361145
99th percentile: 3.074447946548462
mean time: 2.7681270122528074
Pipeline stage StressChecker completed in 15.18s
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 0.66s
Shutdown handler de-registered
chaiml-cogito32b-retryv_56788_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cogito32b-retryv-56788-v1-profiler
Waiting for inference service chaiml-cogito32b-retryv-56788-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3276.85s
Shutdown handler de-registered
chaiml-cogito32b-retryv_56788_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-retryv_56788_v1 status is now torndown due to DeploymentManager action