arliai-qwq-32b-arliai-rpr-v3

developer_uid: NischayDnk

submission_id: arliai-qwq-32b-arliai-rpr-v3_v1

model_name: arliai-qwq-32b-arliai-rpr-v3_v1

model_group: ArliAI/QwQ-32B-ArliAI-Rp

status: torndown

timestamp: 2025-05-16T22:58:19+00:00

num_battles: 6388

num_wins: 1030

celo_rating: 988.23

family_friendly_score: 0.9846

family_friendly_standard_error: 0.0017414270010540206

submission_type: basic

model_repo: ArliAI/QwQ-32B-ArliAI-RpR-v3

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 5

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38777510502258994, 'latency_mean': 2.578752646446228, 'latency_p50': 2.5937384366989136, 'latency_p90': 2.8791899919509887}, {'batch_size': 3, 'throughput': 0.8742042328454207, 'latency_mean': 3.4187111377716066, 'latency_p50': 3.412423253059387, 'latency_p90': 3.8009771585464476}, {'batch_size': 5, 'throughput': 1.1952883807725478, 'latency_mean': 4.17167379617691, 'latency_p50': 4.149370193481445, 'latency_p90': 4.6699694156646725}, {'batch_size': 6, 'throughput': 1.3145933218716668, 'latency_mean': 4.534298783540725, 'latency_p50': 4.484764456748962, 'latency_p90': 5.067061972618103}, {'batch_size': 8, 'throughput': 1.4898069541048415, 'latency_mean': 5.337169640064239, 'latency_p50': 5.304886102676392, 'latency_p90': 6.0762296438217165}, {'batch_size': 10, 'throughput': 1.62039244582671, 'latency_mean': 6.113330919742584, 'latency_p50': 6.115816831588745, 'latency_p90': 6.864450144767761}]

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

display_name: arliai-qwq-32b-arliai-rpr-v3_v1

is_internal_developer: False

language_model: ArliAI/QwQ-32B-ArliAI-RpR-v3

model_size: 33B

ranking_group: single

throughput_3p7s: 1.01

us_pacific_date: 2025-05-16

win_ratio: 0.1612398246712586

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_end|>', '<|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 arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer
Waiting for job on arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer to finish
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║     _____            __           __                                ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║       /___/                                                         ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║                                                                     ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║                                                                     ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  belonging to:                                                      ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║                                                                     ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ║                                                                     ║
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: Downloaded to shared memory in 68.361s
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplplh18ev, device:0
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: quantized model in 63.936s
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: Processed model ArliAI/QwQ-32B-ArliAI-RpR-v3 in 132.298s
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: creating bucket guanaco-mkml-models
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/config.json
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/added_tokens.json
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/special_tokens_map.json
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/tokenizer_config.json
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/flywheel_model.2.safetensors
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/flywheel_model.1.safetensors
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/arliai-qwq-32b-arliai-rpr-v3-v1/flywheel_model.0.safetensors
arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.49it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 73.39it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 87.67it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 87.59it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:12, 58.07it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:14, 50.37it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 60.67it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 71.28it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 75.52it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 72.59it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 63.34it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:10, 62.23it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:10, 59.68it/s]
Loading 0:  17%|█▋        | 132/771 [00:01<00:09, 70.78it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 77.46it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 82.72it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 77.22it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 55.19it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 54.23it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 55.70it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 66.80it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 76.46it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:07, 79.23it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 61.35it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.94it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 62.06it/s]
Loading 0:  33%|███▎      | 255/771 [00:03<00:07, 71.97it/s]
Loading 0:  34%|███▍      | 264/771 [00:03<00:06, 75.75it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:06, 72.80it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 63.08it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 54.22it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:40,  2.12it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:41,  2.85it/s]
Loading 0:  41%|████      | 318/771 [00:19<02:01,  3.73it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:20,  5.52it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<00:54,  7.96it/s]
Loading 0:  45%|████▌     | 347/771 [00:19<00:43,  9.86it/s]
Loading 0:  46%|████▌     | 354/771 [00:20<00:34, 12.12it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:23, 17.17it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 24.14it/s]
Loading 0:  50%|████▉     | 384/771 [00:20<00:12, 30.49it/s]
Loading 0:  51%|█████     | 393/771 [00:20<00:10, 36.16it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:08, 40.89it/s]
Loading 0:  54%|█████▎    | 414/771 [00:21<00:08, 40.01it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 47.99it/s]
Loading 0:  57%|█████▋    | 436/771 [00:21<00:05, 58.49it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:04, 65.77it/s]
Loading 0:  60%|█████▉    | 460/771 [00:21<00:04, 76.88it/s]
Loading 0:  61%|██████    | 470/771 [00:21<00:04, 60.73it/s]
Loading 0:  62%|██████▏   | 478/771 [00:21<00:04, 60.23it/s]
Loading 0:  63%|██████▎   | 486/771 [00:22<00:04, 60.10it/s]
Loading 0:  64%|██████▍   | 496/771 [00:22<00:04, 68.22it/s]
Loading 0:  66%|██████▌   | 507/771 [00:22<00:03, 77.58it/s]
Loading 0:  67%|██████▋   | 516/771 [00:22<00:03, 80.29it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 61.53it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 52.98it/s]
Loading 0:  71%|███████   | 544/771 [00:22<00:03, 62.13it/s]
Loading 0:  72%|███████▏  | 555/771 [00:22<00:03, 71.70it/s]
Loading 0:  73%|███████▎  | 564/771 [00:23<00:02, 75.51it/s]
Loading 0:  74%|███████▍  | 573/771 [00:23<00:02, 72.63it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 62.48it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:03, 53.81it/s]
Loading 0:  78%|███████▊  | 604/771 [00:23<00:02, 62.34it/s]
Loading 0:  80%|███████▉  | 615/771 [00:23<00:02, 72.01it/s]
Loading 0:  81%|████████  | 624/771 [00:24<00:01, 75.63it/s]
Loading 0:  82%|████████▏ | 633/771 [00:38<01:05,  2.09it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:38,  3.22it/s]
Loading 0:  85%|████████▍ | 654/771 [00:39<00:28,  4.08it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:18,  5.76it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:11,  8.30it/s]
Loading 0:  89%|████████▊ | 684/771 [00:39<00:07, 11.04it/s]
Loading 0:  90%|████████▉ | 693/771 [00:40<00:05, 14.42it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:03, 19.43it/s]
Loading 0:  92%|█████████▏| 713/771 [00:40<00:02, 21.43it/s]
Loading 0:  94%|█████████▍| 724/771 [00:40<00:01, 29.17it/s]
Loading 0:  95%|█████████▌| 735/771 [00:40<00:00, 38.05it/s]
Loading 0:  96%|█████████▋| 744/771 [00:40<00:00, 44.98it/s]
Loading 0:  98%|█████████▊| 753/771 [00:40<00:00, 49.37it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.29it/s]
                                                            
Job arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer completed after 166.88s with status: succeeded
Stopping job with name arliai-qwq-32b-arliai-rpr-v3-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.43s
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 arliai-qwq-32b-arliai-rpr-v3-v1
Waiting for inference service arliai-qwq-32b-arliai-rpr-v3-v1 to be ready
Inference service arliai-qwq-32b-arliai-rpr-v3-v1 ready after 140.56635284423828s
Pipeline stage MKMLDeployer completed in 141.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.0305583477020264s
Received healthy response to inference request in 0.8930623531341553s
Received healthy response to inference request in 0.5092499256134033s
Received healthy response to inference request in 0.3321378231048584s
Received healthy response to inference request in 0.350693941116333s
5 requests
0 failed requests
5th percentile: 0.3358490467071533
10th percentile: 0.33956027030944824
20th percentile: 0.3469827175140381
30th percentile: 0.38240513801574705
40th percentile: 0.44582753181457524
50th percentile: 0.5092499256134033
60th percentile: 0.6627748966217041
70th percentile: 0.8162998676300048
80th percentile: 0.9205615520477295
90th percentile: 0.9755599498748779
95th percentile: 1.0030591487884521
99th percentile: 1.0250585079193115
mean time: 0.6231404781341553
Pipeline stage StressChecker completed in 4.41s
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 0.69s
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 0.72s
Shutdown handler de-registered
arliai-qwq-32b-arliai-rpr-v3_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 0.11s
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 arliai-qwq-32b-arliai-rpr-v3-v1-profiler
Waiting for inference service arliai-qwq-32b-arliai-rpr-v3-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 1506.32s
Shutdown handler de-registered
arliai-qwq-32b-arliai-rpr-v3_v1 status is now inactive due to auto deactivation removed underperforming models
arliai-qwq-32b-arliai-rpr-v3_v1 status is now torndown due to DeploymentManager action