arliai-qwen2-5-32b-arlia_2205

developer_uid: NischayDnk

submission_id: arliai-qwen2-5-32b-arlia_2205_v1

model_name: arliai-qwen2-5-32b-arlia_2205_v1

model_group: ArliAI/Qwen2.5-32B-ArliA

status: torndown

timestamp: 2025-05-05T03:55:38+00:00

num_battles: 8982

num_wins: 4077

celo_rating: 1253.11

family_friendly_score: 0.5902000000000001

family_friendly_standard_error: 0.006955055139968338

submission_type: basic

model_repo: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3

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': 0.3890701502445182, 'latency_mean': 2.5701686465740203, 'latency_p50': 2.5901867151260376, 'latency_p90': 2.8464431524276734}, {'batch_size': 3, 'throughput': 0.8535186383213132, 'latency_mean': 3.501607369184494, 'latency_p50': 3.5132453441619873, 'latency_p90': 3.860897946357727}, {'batch_size': 5, 'throughput': 1.1865084144555909, 'latency_mean': 4.175439778566361, 'latency_p50': 4.157182455062866, 'latency_p90': 4.7425882577896115}, {'batch_size': 6, 'throughput': 1.2904482972897389, 'latency_mean': 4.6151701974868775, 'latency_p50': 4.618889331817627, 'latency_p90': 5.148641967773438}, {'batch_size': 8, 'throughput': 1.4592394687581556, 'latency_mean': 5.427052515745163, 'latency_p50': 5.414634108543396, 'latency_p90': 6.165610814094544}, {'batch_size': 10, 'throughput': 1.604553648751728, 'latency_mean': 6.150553416013718, 'latency_p50': 6.028195261955261, 'latency_p90': 7.133005213737488}]

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

display_name: arliai-qwen2-5-32b-arlia_2205_v1

is_internal_developer: False

language_model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3

model_size: 33B

ranking_group: single

throughput_3p7s: 0.97

us_pacific_date: 2025-05-04

win_ratio: 0.45390781563126253

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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer
Waiting for job on arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer to finish
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║     _____            __           __                                ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║       /___/                                                         ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║                                                                     ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  https://mk1.ai                                                     ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║                                                                     ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  belonging to:                                                      ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║                                                                     ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  Chai Research Corp.                                                ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ║                                                                     ║
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: Downloaded to shared memory in 91.243s
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc94mco12, device:0
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: quantized model in 63.871s
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: Processed model ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3 in 155.115s
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: creating bucket guanaco-mkml-models
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/config.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/added_tokens.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/special_tokens_map.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/tokenizer_config.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/merges.txt
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/vocab.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/tokenizer.json
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/flywheel_model.2.safetensors
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/flywheel_model.1.safetensors
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/arliai-qwen2-5-32b-arlia-2205-v1/flywheel_model.0.safetensors
arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 37.18it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 71.58it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 83.77it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:08, 84.02it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:13, 52.97it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:15, 44.99it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 57.19it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 68.07it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 72.28it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 69.59it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 59.04it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 56.95it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 57.77it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 68.64it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 74.93it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 80.68it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 75.52it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:11, 51.38it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 52.05it/s]
Loading 0:  24%|██▍       | 184/771 [00:02<00:10, 57.49it/s]
Loading 0:  25%|██▌       | 195/771 [00:03<00:08, 68.85it/s]
Loading 0:  26%|██▋       | 203/771 [00:03<00:07, 71.05it/s]
Loading 0:  27%|██▋       | 211/771 [00:03<00:08, 68.32it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:08, 61.29it/s]
Loading 0:  30%|███       | 233/771 [00:03<00:10, 51.53it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 61.96it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 71.36it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:06, 74.87it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:06, 71.43it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 62.16it/s]
Loading 0:  38%|███▊      | 293/771 [00:04<00:09, 52.40it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:34,  2.18it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:37,  2.93it/s]
Loading 0:  41%|████      | 318/771 [00:19<01:58,  3.82it/s]
Loading 0:  43%|████▎     | 328/771 [00:19<01:18,  5.63it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<00:53,  8.09it/s]
Loading 0:  45%|████▌     | 347/771 [00:19<00:42,  9.99it/s]
Loading 0:  46%|████▌     | 354/771 [00:20<00:34, 12.25it/s]
Loading 0:  47%|████▋     | 364/771 [00:20<00:23, 17.32it/s]
Loading 0:  49%|████▊     | 375/771 [00:20<00:16, 24.35it/s]
Loading 0:  50%|████▉     | 384/771 [00:20<00:12, 30.71it/s]
Loading 0:  51%|█████     | 393/771 [00:20<00:10, 36.30it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:09, 40.20it/s]
Loading 0:  54%|█████▎    | 413/771 [00:20<00:09, 38.35it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 48.79it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:05, 59.23it/s]
Loading 0:  58%|█████▊    | 444/771 [00:21<00:05, 64.60it/s]
Loading 0:  59%|█████▉    | 453/771 [00:21<00:04, 64.62it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:05, 59.28it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 51.94it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 60.71it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:03, 70.83it/s]
Loading 0:  65%|██████▌   | 504/771 [00:22<00:03, 74.71it/s]
Loading 0:  67%|██████▋   | 513/771 [00:22<00:03, 71.70it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 62.22it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:04, 54.13it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 61.15it/s]
Loading 0:  72%|███████▏  | 557/771 [00:23<00:03, 68.42it/s]
Loading 0:  74%|███████▍  | 569/771 [00:23<00:02, 74.19it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 74.56it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 61.88it/s]
Loading 0:  78%|███████▊  | 604/771 [00:23<00:02, 68.93it/s]
Loading 0:  80%|███████▉  | 615/771 [00:23<00:02, 77.46it/s]
Loading 0:  81%|████████  | 624/771 [00:23<00:01, 79.56it/s]
Loading 0:  82%|████████▏ | 633/771 [00:38<01:02,  2.22it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:37,  3.37it/s]
Loading 0:  85%|████████▍ | 654/771 [00:39<00:27,  4.24it/s]
Loading 0:  86%|████████▌ | 664/771 [00:39<00:18,  5.94it/s]
Loading 0:  88%|████████▊ | 675/771 [00:39<00:11,  8.50it/s]
Loading 0:  89%|████████▊ | 683/771 [00:39<00:08, 10.91it/s]
Loading 0:  90%|████████▉ | 691/771 [00:39<00:05, 13.89it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:03, 20.02it/s]
Loading 0:  92%|█████████▏| 713/771 [00:40<00:02, 21.79it/s]
Loading 0:  94%|█████████▍| 724/771 [00:40<00:01, 29.39it/s]
Loading 0:  95%|█████████▌| 735/771 [00:40<00:00, 38.18it/s]
Loading 0:  96%|█████████▋| 744/771 [00:40<00:00, 45.09it/s]
Loading 0:  98%|█████████▊| 753/771 [00:40<00:00, 49.10it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:01,  4.28it/s]
                                                            
Job arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer completed after 186.3s with status: succeeded
Stopping job with name arliai-qwen2-5-32b-arlia-2205-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service arliai-qwen2-5-32b-arlia-2205-v1
Waiting for inference service arliai-qwen2-5-32b-arlia-2205-v1 to be ready
Inference service arliai-qwen2-5-32b-arlia-2205-v1 ready after 150.79984045028687s
Pipeline stage MKMLDeployer completed in 151.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3156042098999023s
Received healthy response to inference request in 2.243523359298706s
Received healthy response to inference request in 2.223893404006958s
Received healthy response to inference request in 2.4912757873535156s
Received healthy response to inference request in 2.885281801223755s
5 requests
0 failed requests
5th percentile: 2.227819395065308
10th percentile: 2.231745386123657
20th percentile: 2.2395973682403563
30th percentile: 2.293073844909668
40th percentile: 2.392174816131592
50th percentile: 2.4912757873535156
60th percentile: 2.6488781929016114
70th percentile: 2.8064805984497068
80th percentile: 2.9713462829589843
90th percentile: 3.1434752464294435
95th percentile: 3.229539728164673
99th percentile: 3.2983913135528566
mean time: 2.6319157123565673
Pipeline stage StressChecker completed in 14.24s
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 0.65s
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 0.63s
Shutdown handler de-registered
arliai-qwen2-5-32b-arlia_2205_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service arliai-qwen2-5-32b-arlia-2205-v1-profiler
Waiting for inference service arliai-qwen2-5-32b-arlia-2205-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5223.96s
Shutdown handler de-registered
arliai-qwen2-5-32b-arlia_2205_v1 status is now inactive due to auto deactivation removed underperforming models
arliai-qwen2-5-32b-arlia_2205_v1 status is now torndown due to DeploymentManager action