chaiml-cogito32b-retryv_71758

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-retryv_71758_v1

model_name: chaiml-cogito32b-retryv_71758_v1

model_group: ChaiML/cogito32b-retryv2

status: torndown

timestamp: 2025-05-14T16:43:06+00:00

num_battles: 10496

num_wins: 5435

celo_rating: 1294.8

family_friendly_score: 0.5802

family_friendly_standard_error: 0.006979512303879119

submission_type: basic

model_repo: ChaiML/cogito32b-retryv2top20k-simpoexp1-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': 0.38659150324698094, 'latency_mean': 2.5866416156291963, 'latency_p50': 2.6018216609954834, 'latency_p90': 2.895850348472595}, {'batch_size': 3, 'throughput': 0.8680791011930431, 'latency_mean': 3.436259162425995, 'latency_p50': 3.430205464363098, 'latency_p90': 3.814787769317627}, {'batch_size': 5, 'throughput': 1.1960042728133644, 'latency_mean': 4.159728951454163, 'latency_p50': 4.1578110456466675, 'latency_p90': 4.59318733215332}, {'batch_size': 6, 'throughput': 1.294364838701412, 'latency_mean': 4.594048511981964, 'latency_p50': 4.572531461715698, 'latency_p90': 5.183216333389282}, {'batch_size': 8, 'throughput': 1.4670903627148792, 'latency_mean': 5.406481360197067, 'latency_p50': 5.399181365966797, 'latency_p90': 5.996361970901489}, {'batch_size': 10, 'throughput': 1.588540798824871, 'latency_mean': 6.212260221242905, 'latency_p50': 6.197607755661011, 'latency_p90': 7.079673337936401}]

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

display_name: chaiml-cogito32b-retryv_71758_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-retryv2top20k-simpoexp1-s1-pred1285sft

model_size: 33B

ranking_group: single

throughput_3p7s: 1.01

us_pacific_date: 2025-05-14

win_ratio: 0.5178163109756098

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_end|>', '\n', '<|im_start|>'], '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-71758-v1-mkmlizer
Waiting for job on chaiml-cogito32b-retryv-71758-v1-mkmlizer to finish
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-retryv-71758-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-retryv-71758-v1-mkmlizer: Downloaded to shared memory in 108.064s
chaiml-cogito32b-retryv-71758-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwr89l19x, device:0
chaiml-cogito32b-retryv-71758-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-retryv-71758-v1-mkmlizer: quantized model in 64.048s
chaiml-cogito32b-retryv-71758-v1-mkmlizer: Processed model ChaiML/cogito32b-retryv2top20k-simpoexp1-s1-pred1285sft in 172.113s
chaiml-cogito32b-retryv-71758-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-retryv-71758-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-retryv-71758-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/config.json
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/added_tokens.json
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/special_tokens_map.json
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/tokenizer_config.json
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/merges.txt
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/flywheel_model.2.safetensors
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/flywheel_model.0.safetensors
chaiml-cogito32b-retryv-71758-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-retryv-71758-v1/flywheel_model.1.safetensors
chaiml-cogito32b-retryv-71758-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 37.81it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 71.89it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 84.33it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 83.55it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:13, 53.96it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:15, 45.29it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 57.57it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 68.61it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 72.50it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 69.48it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 59.14it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 56.48it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 56.76it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 67.39it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 74.22it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 79.56it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 74.70it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:11, 51.53it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 52.06it/s]
Loading 0:  24%|██▍       | 184/771 [00:02<00:10, 57.20it/s]
Loading 0:  25%|██▌       | 195/771 [00:03<00:08, 68.59it/s]
Loading 0:  26%|██▋       | 203/771 [00:03<00:08, 70.93it/s]
Loading 0:  27%|██▋       | 211/771 [00:03<00:08, 68.11it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 61.38it/s]
Loading 0:  30%|███       | 233/771 [00:03<00:10, 51.17it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 61.96it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 71.55it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:06, 75.15it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:06, 72.13it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 62.18it/s]
Loading 0:  38%|███▊      | 293/771 [00:04<00:09, 51.41it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:41,  2.11it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:42,  2.83it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:02,  3.70it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:21,  5.46it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<00:55,  7.85it/s]
Loading 0:  45%|████▌     | 347/771 [00:20<00:43,  9.74it/s]
Loading 0:  46%|████▌     | 354/771 [00:20<00:34, 11.99it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:23, 16.98it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 23.90it/s]
Loading 0:  50%|████▉     | 384/771 [00:20<00:12, 30.25it/s]
Loading 0:  51%|█████     | 393/771 [00:20<00:10, 35.91it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:09, 40.44it/s]
Loading 0:  54%|█████▎    | 413/771 [00:21<00:09, 38.25it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 47.50it/s]
Loading 0:  57%|█████▋    | 436/771 [00:21<00:05, 57.70it/s]
Loading 0:  58%|█████▊    | 447/771 [00:21<00:04, 67.59it/s]
Loading 0:  59%|█████▉    | 456/771 [00:21<00:04, 72.04it/s]
Loading 0:  60%|██████    | 466/771 [00:22<00:05, 59.19it/s]
Loading 0:  61%|██████▏   | 474/771 [00:22<00:05, 51.61it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 60.67it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 70.60it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 75.07it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 72.34it/s]
Loading 0:  68%|██████▊   | 526/771 [00:23<00:03, 62.61it/s]
Loading 0:  69%|██████▉   | 534/771 [00:23<00:04, 53.91it/s]
Loading 0:  71%|███████   | 545/771 [00:23<00:03, 60.01it/s]
Loading 0:  72%|███████▏  | 556/771 [00:23<00:03, 69.52it/s]
Loading 0:  74%|███████▎  | 567/771 [00:23<00:02, 78.34it/s]
Loading 0:  75%|███████▍  | 576/771 [00:23<00:02, 80.76it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:03, 60.38it/s]
Loading 0:  77%|███████▋  | 594/771 [00:24<00:03, 52.14it/s]
Loading 0:  78%|███████▊  | 604/771 [00:24<00:02, 61.22it/s]
Loading 0:  80%|███████▉  | 615/771 [00:24<00:02, 71.18it/s]
Loading 0:  81%|████████  | 624/771 [00:24<00:01, 75.05it/s]
Loading 0:  82%|████████▏ | 633/771 [00:38<01:03,  2.18it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:37,  3.37it/s]
Loading 0:  85%|████████▍ | 654/771 [00:39<00:27,  4.26it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:17,  6.02it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:11,  8.67it/s]
Loading 0:  89%|████████▉ | 685/771 [00:39<00:07, 11.87it/s]
Loading 0:  90%|█████████ | 694/771 [00:39<00:05, 15.37it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:03, 20.05it/s]
Loading 0:  93%|█████████▎| 714/771 [00:40<00:02, 22.73it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 29.62it/s]
Loading 0:  95%|█████████▌| 736/771 [00:40<00:00, 38.39it/s]
Loading 0:  97%|█████████▋| 747/771 [00:40<00:00, 48.12it/s]
Loading 0:  98%|█████████▊| 756/771 [00:40<00:00, 54.84it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.06it/s]
                                                            
Job chaiml-cogito32b-retryv-71758-v1-mkmlizer completed after 206.77s with status: succeeded
Stopping job with name chaiml-cogito32b-retryv-71758-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-retryv-71758-v1
Waiting for inference service chaiml-cogito32b-retryv-71758-v1 to be ready
Inference service chaiml-cogito32b-retryv-71758-v1 ready after 130.57171440124512s
Pipeline stage MKMLDeployer completed in 131.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.108103036880493s
Received healthy response to inference request in 2.6587588787078857s
Received healthy response to inference request in 2.6868722438812256s
Received healthy response to inference request in 2.7262790203094482s
Received healthy response to inference request in 3.031053066253662s
5 requests
0 failed requests
5th percentile: 2.6643815517425535
10th percentile: 2.6700042247772218
20th percentile: 2.681249570846558
30th percentile: 2.6947535991668703
40th percentile: 2.7105163097381593
50th percentile: 2.7262790203094482
60th percentile: 2.848188638687134
70th percentile: 2.9700982570648193
80th percentile: 3.046463060379028
90th percentile: 3.0772830486297607
95th percentile: 3.092693042755127
99th percentile: 3.10502103805542
mean time: 2.842213249206543
Pipeline stage StressChecker completed in 15.97s
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 0.72s
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 0.71s
Shutdown handler de-registered
chaiml-cogito32b-retryv_71758_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-cogito32b-retryv-71758-v1-profiler
Waiting for inference service chaiml-cogito32b-retryv-71758-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 3370.17s
Shutdown handler de-registered
chaiml-cogito32b-retryv_71758_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-retryv_71758_v1 status is now torndown due to DeploymentManager action