chaiml-nis-cogito32b-dp_55758

developer_uid: NischayDnk

submission_id: chaiml-nis-cogito32b-dp_55758_v1

model_name: chaiml-nis-cogito32b-dp_55758_v1

model_group: ChaiML/nis-cogito32b-dpo

status: torndown

timestamp: 2025-04-23T03:28:10+00:00

num_battles: 7714

num_wins: 4168

celo_rating: 1314.62

family_friendly_score: 0.511

family_friendly_standard_error: 0.007069356406349874

submission_type: basic

model_repo: ChaiML/nis-cogito32b-dpoexp1-s2-pref1320v2dpo

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': 0.38831481682702157, 'latency_mean': 2.575175429582596, 'latency_p50': 2.5692193508148193, 'latency_p90': 2.8435468435287476}, {'batch_size': 3, 'throughput': 0.8581046716708799, 'latency_mean': 3.482017686367035, 'latency_p50': 3.499624013900757, 'latency_p90': 3.8167233228683473}, {'batch_size': 5, 'throughput': 1.171846197192638, 'latency_mean': 4.2294179582595826, 'latency_p50': 4.231706738471985, 'latency_p90': 4.696413660049438}, {'batch_size': 6, 'throughput': 1.2870738431546116, 'latency_mean': 4.624873932600021, 'latency_p50': 4.639529585838318, 'latency_p90': 5.108466219902039}, {'batch_size': 8, 'throughput': 1.471036548836721, 'latency_mean': 5.382411688566208, 'latency_p50': 5.392105340957642, 'latency_p90': 6.034397459030151}, {'batch_size': 10, 'throughput': 1.5879009295535842, 'latency_mean': 6.225834699869156, 'latency_p50': 6.237425208091736, 'latency_p90': 7.069707870483398}]

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

display_name: chaiml-nis-cogito32b-dp_55758_v1

is_internal_developer: False

language_model: ChaiML/nis-cogito32b-dpoexp1-s2-pref1320v2dpo

model_size: 33B

ranking_group: single

throughput_3p7s: 0.97

us_pacific_date: 2025-04-22

win_ratio: 0.5403163080114078

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'], 'max_input_tokens': 768, 'best_of': 5, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', '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-cogito32b-dp-55758-v1-mkmlizer
Waiting for job on chaiml-nis-cogito32b-dp-55758-v1-mkmlizer to finish
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║                                                                     ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║                                                                     ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║                                                                     ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ║                                                                     ║
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: Downloaded to shared memory in 111.797s
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwvuc5nrl, device:0
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: quantized model in 63.022s
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: Processed model ChaiML/nis-cogito32b-dpoexp1-s2-pref1320v2dpo in 174.820s
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/added_tokens.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/config.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/special_tokens_map.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/tokenizer_config.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/merges.txt
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/vocab.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/tokenizer.json
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/flywheel_model.2.safetensors
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/flywheel_model.0.safetensors
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito32b-dp-55758-v1/flywheel_model.1.safetensors
chaiml-nis-cogito32b-dp-55758-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 40.11it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 77.36it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 91.34it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:07, 93.91it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 54.11it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:13, 52.50it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:12, 57.95it/s]
Loading 0:  10%|▉         | 77/771 [00:01<00:10, 66.79it/s]
Loading 0:  12%|█▏        | 89/771 [00:01<00:09, 73.03it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:09, 69.23it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:09, 67.34it/s]
Loading 0:  16%|█▌        | 122/771 [00:01<00:09, 65.90it/s]
Loading 0:  17%|█▋        | 133/771 [00:01<00:09, 69.70it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 90.46it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 78.97it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 57.97it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 56.71it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 58.07it/s]
Loading 0:  26%|██▌       | 197/771 [00:02<00:08, 65.78it/s]
Loading 0:  27%|██▋       | 209/771 [00:03<00:07, 71.73it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 67.80it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:09, 58.58it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 63.86it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 69.83it/s]
Loading 0:  35%|███▍      | 269/771 [00:03<00:06, 74.77it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 70.02it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:07, 60.45it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:12,  2.43it/s]
Loading 0:  41%|████      | 315/771 [00:19<02:09,  3.53it/s]
Loading 0:  42%|████▏     | 327/771 [00:19<01:27,  5.06it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<01:02,  6.97it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:49,  8.59it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:41,  9.95it/s]
Loading 0:  47%|████▋     | 365/771 [00:19<00:27, 14.53it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 20.21it/s]
Loading 0:  50%|█████     | 389/771 [00:20<00:14, 26.96it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 34.64it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:10, 35.54it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:08, 42.56it/s]
Loading 0:  57%|█████▋    | 436/771 [00:20<00:06, 51.90it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:05, 59.53it/s]
Loading 0:  60%|█████▉    | 459/771 [00:21<00:04, 68.58it/s]
Loading 0:  61%|██████    | 469/771 [00:21<00:05, 54.45it/s]
Loading 0:  62%|██████▏   | 477/771 [00:21<00:05, 56.21it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 58.08it/s]
Loading 0:  64%|██████▍   | 497/771 [00:21<00:04, 65.86it/s]
Loading 0:  66%|██████▌   | 509/771 [00:22<00:03, 72.03it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 68.45it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 59.16it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 64.67it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 70.49it/s]
Loading 0:  74%|███████▍  | 569/771 [00:22<00:02, 75.53it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 71.90it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 61.58it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 66.48it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 72.17it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<00:57,  2.51it/s]
Loading 0:  83%|████████▎ | 638/771 [00:38<00:37,  3.52it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:27,  4.49it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:21,  5.47it/s]
Loading 0:  86%|████████▋ | 665/771 [00:38<00:12,  8.23it/s]
Loading 0:  88%|████████▊ | 677/771 [00:38<00:07, 11.87it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:04, 16.54it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 23.57it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 25.73it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 32.25it/s]
Loading 0:  95%|█████████▌| 736/771 [00:39<00:00, 40.73it/s]
Loading 0:  97%|█████████▋| 748/771 [00:39<00:00, 49.20it/s]
Loading 0:  99%|█████████▊| 760/771 [00:40<00:00, 60.17it/s]
Loading 0: 100%|█████████▉| 770/771 [00:47<00:00,  4.48it/s]
                                                            
Job chaiml-nis-cogito32b-dp-55758-v1-mkmlizer completed after 207.12s with status: succeeded
Stopping job with name chaiml-nis-cogito32b-dp-55758-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-cogito32b-dp-55758-v1
Waiting for inference service chaiml-nis-cogito32b-dp-55758-v1 to be ready
Inference service chaiml-nis-cogito32b-dp-55758-v1 ready after 130.77854585647583s
Pipeline stage MKMLDeployer completed in 131.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1953117847442627s
Received healthy response to inference request in 2.58528470993042s
Received healthy response to inference request in 2.717898368835449s
Received healthy response to inference request in 2.60148024559021s
Received healthy response to inference request in 2.6235523223876953s
5 requests
0 failed requests
5th percentile: 2.588523817062378
10th percentile: 2.591762924194336
20th percentile: 2.5982411384582518
30th percentile: 2.605894660949707
40th percentile: 2.614723491668701
50th percentile: 2.6235523223876953
60th percentile: 2.661290740966797
70th percentile: 2.6990291595458986
80th percentile: 2.813381052017212
90th percentile: 3.004346418380737
95th percentile: 3.0998291015625
99th percentile: 3.1762152481079102
mean time: 2.7447054862976072
Pipeline stage StressChecker completed in 15.29s
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 0.96s
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 0.76s
Shutdown handler de-registered
chaiml-nis-cogito32b-dp_55758_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nis-cogito32b-dp-55758-v1-profiler
Waiting for inference service chaiml-nis-cogito32b-dp-55758-v1-profiler to be ready
Inference service chaiml-nis-cogito32b-dp-55758-v1-profiler ready after 130.55772376060486s
Pipeline stage MKMLProfilerDeployer completed in 130.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-cogito32b80046898ff47ff1e13886cade69c28d2-deplor6cg5:/code/chaiverse_profiler_1745379425 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-cogito32b80046898ff47ff1e13886cade69c28d2-deplor6cg5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1745379425 && python profiles.py profile --best_of_n 5 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1745379425/summary.json'
kubectl exec -it chaiml-nis-cogito32b80046898ff47ff1e13886cade69c28d2-deplor6cg5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1745379425/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1345.63s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-nis-cogito32b-dp-55758-v1-profiler is running
Tearing down inference service chaiml-nis-cogito32b-dp-55758-v1-profiler
Service chaiml-nis-cogito32b-dp-55758-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.63s
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6072.53s
Shutdown handler de-registered
chaiml-nis-cogito32b-dp_55758_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-cogito32b-dp_55758_v1 status is now torndown due to DeploymentManager action