chaiml-cogito32b-sftmor_30051

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-sftmor_30051_v1

model_name: chaiml-cogito32b-sftmor_30051_v1

model_group: ChaiML/cogito32b-sftmore

status: torndown

timestamp: 2025-05-11T05:57:18+00:00

num_battles: 15840

num_wins: 7990

celo_rating: 1286.01

family_friendly_score: 0.5818

family_friendly_standard_error: 0.006975797588806602

submission_type: basic

model_repo: ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-4e

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': 0.38832931576873575, 'latency_mean': 2.5750778794288633, 'latency_p50': 2.5760715007781982, 'latency_p90': 2.854625034332275}, {'batch_size': 3, 'throughput': 0.8660018978870929, 'latency_mean': 3.44061319231987, 'latency_p50': 3.446160316467285, 'latency_p90': 3.7872054815292358}, {'batch_size': 5, 'throughput': 1.1930350705740242, 'latency_mean': 4.155862898826599, 'latency_p50': 4.143607974052429, 'latency_p90': 4.619158983230591}, {'batch_size': 6, 'throughput': 1.2976587785039084, 'latency_mean': 4.598670605421066, 'latency_p50': 4.606352806091309, 'latency_p90': 5.1403625965118405}, {'batch_size': 8, 'throughput': 1.490342471493754, 'latency_mean': 5.310248222351074, 'latency_p50': 5.325807690620422, 'latency_p90': 6.061789560317993}, {'batch_size': 10, 'throughput': 1.6134938474089169, 'latency_mean': 6.133890548944473, 'latency_p50': 6.103763103485107, 'latency_p90': 7.028999948501587}]

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

display_name: chaiml-cogito32b-sftmor_30051_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-4e

model_size: 33B

ranking_group: single

throughput_3p7s: 1.01

us_pacific_date: 2025-05-10

win_ratio: 0.5044191919191919

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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-cogito32b-sftmor-30051-v1-mkmlizer
Waiting for job on chaiml-cogito32b-sftmor-30051-v1-mkmlizer to finish
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: Downloaded to shared memory in 105.198s
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3oem3_1x, device:0
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: quantized model in 63.775s
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: Processed model ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-4e in 168.973s
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/config.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/added_tokens.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/tokenizer_config.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/special_tokens_map.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/merges.txt
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/vocab.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/tokenizer.json
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/flywheel_model.2.safetensors
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-30051-v1/flywheel_model.0.safetensors
chaiml-cogito32b-sftmor-30051-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 36.87it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 72.39it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 87.76it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 90.83it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 52.84it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:14, 50.80it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 58.86it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 70.05it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 74.81it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 72.39it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 61.21it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 57.97it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 58.86it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 69.96it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 76.91it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 82.13it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 77.27it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:11, 54.26it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:11, 53.77it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 55.73it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:08, 66.92it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 76.98it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.10it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 60.81it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.71it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.36it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 66.60it/s]
Loading 0:  35%|███▍      | 269/771 [00:04<00:06, 72.16it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 67.52it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 58.53it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:19,  2.35it/s]
Loading 0:  41%|████      | 313/771 [00:19<02:20,  3.26it/s]
Loading 0:  42%|████▏     | 321/771 [00:19<01:45,  4.26it/s]
Loading 0:  43%|████▎     | 329/771 [00:19<01:18,  5.63it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:45,  9.32it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:39, 10.63it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:27, 14.88it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:19, 20.36it/s]
Loading 0:  50%|█████     | 386/771 [00:20<00:14, 27.17it/s]
Loading 0:  51%|█████     | 395/771 [00:20<00:11, 32.19it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 35.30it/s]
Loading 0:  54%|█████▎    | 414/771 [00:21<00:09, 36.04it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 43.89it/s]
Loading 0:  57%|█████▋    | 436/771 [00:21<00:06, 54.24it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:05, 61.71it/s]
Loading 0:  59%|█████▉    | 458/771 [00:21<00:04, 68.95it/s]
Loading 0:  61%|██████    | 467/771 [00:21<00:05, 56.22it/s]
Loading 0:  62%|██████▏   | 475/771 [00:21<00:05, 54.11it/s]
Loading 0:  63%|██████▎   | 485/771 [00:22<00:04, 58.99it/s]
Loading 0:  64%|██████▍   | 496/771 [00:22<00:03, 69.24it/s]
Loading 0:  66%|██████▌   | 508/771 [00:22<00:03, 74.52it/s]
Loading 0:  67%|██████▋   | 519/771 [00:22<00:03, 82.51it/s]
Loading 0:  68%|██████▊   | 528/771 [00:22<00:04, 58.44it/s]
Loading 0:  70%|██████▉   | 536/771 [00:22<00:03, 59.69it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 61.27it/s]
Loading 0:  72%|███████▏  | 557/771 [00:23<00:03, 69.24it/s]
Loading 0:  74%|███████▍  | 569/771 [00:23<00:02, 75.06it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 74.07it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 62.12it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 66.56it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 72.12it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<00:58,  2.44it/s]
Loading 0:  83%|████████▎ | 638/771 [00:38<00:38,  3.45it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.41it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:21,  5.37it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:13,  8.10it/s]
Loading 0:  88%|████████▊ | 676/771 [00:39<00:08, 11.51it/s]
Loading 0:  89%|████████▉ | 688/771 [00:39<00:05, 16.18it/s]
Loading 0:  91%|█████████ | 698/771 [00:39<00:03, 21.22it/s]
Loading 0:  92%|█████████▏| 707/771 [00:39<00:02, 24.03it/s]
Loading 0:  93%|█████████▎| 715/771 [00:40<00:02, 27.61it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 34.18it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 43.15it/s]
Loading 0:  97%|█████████▋| 748/771 [00:40<00:00, 53.24it/s]
Loading 0:  98%|█████████▊| 759/771 [00:40<00:00, 63.23it/s]
Loading 0: 100%|█████████▉| 769/771 [00:48<00:00,  4.26it/s]
                                                            
Job chaiml-cogito32b-sftmor-30051-v1-mkmlizer completed after 206.65s with status: succeeded
Stopping job with name chaiml-cogito32b-sftmor-30051-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-sftmor-30051-v1
Waiting for inference service chaiml-cogito32b-sftmor-30051-v1 to be ready
Inference service chaiml-cogito32b-sftmor-30051-v1 ready after 120.41339898109436s
Pipeline stage MKMLDeployer completed in 120.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.214277505874634s
Received healthy response to inference request in 2.536796808242798s
Received healthy response to inference request in 3.084308385848999s
Received healthy response to inference request in 2.7477638721466064s
Received healthy response to inference request in 2.705357074737549s
5 requests
0 failed requests
5th percentile: 2.570508861541748
10th percentile: 2.604220914840698
20th percentile: 2.6716450214385987
30th percentile: 2.7138384342193604
40th percentile: 2.730801153182983
50th percentile: 2.7477638721466064
60th percentile: 2.8823816776275635
70th percentile: 3.0169994831085205
80th percentile: 3.110302209854126
90th percentile: 3.16228985786438
95th percentile: 3.188283681869507
99th percentile: 3.2090787410736086
mean time: 2.857700729370117
Pipeline stage StressChecker completed in 15.44s
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 0.70s
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 0.69s
Shutdown handler de-registered
chaiml-cogito32b-sftmor_30051_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5991.99s
Shutdown handler de-registered
chaiml-cogito32b-sftmor_30051_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-sftmor_30051_v1 status is now torndown due to DeploymentManager action