developer_uid: NischayDnk
submission_id: chaiml-qwen32b-dpoexp1-_20366_v1
model_name: chaiml-qwen32b-dpoexp1-_20366_v1
model_group: ChaiML/qwen32b-dpoexp1-s
status: torndown
timestamp: 2025-04-21T13:09:12+00:00
num_battles: 9065
num_wins: 5111
celo_rating: 1332.86
family_friendly_score: 0.47819999999999996
family_friendly_standard_error: 0.007064343706247594
submission_type: basic
model_repo: ChaiML/qwen32b-dpoexp1-s2-ftsimpoexp4-1330pref-1-1
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': 0.27701070916482545, 'latency_mean': 3.6099063289165496, 'latency_p50': 3.632620334625244, 'latency_p90': 3.9985102891921995}, {'batch_size': 2, 'throughput': 0.454351634942334, 'latency_mean': 4.389037899971008, 'latency_p50': 4.381640076637268, 'latency_p90': 4.909079575538636}, {'batch_size': 3, 'throughput': 0.6009940410178694, 'latency_mean': 4.967646604776382, 'latency_p50': 4.984857082366943, 'latency_p90': 5.558953475952149}, {'batch_size': 4, 'throughput': 0.7137712408664558, 'latency_mean': 5.577663224935532, 'latency_p50': 5.562045454978943, 'latency_p90': 6.144732022285462}, {'batch_size': 5, 'throughput': 0.7995374677396123, 'latency_mean': 6.193107203245163, 'latency_p50': 6.238940119743347, 'latency_p90': 6.862464857101441}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen32b-dpoexp1-_20366_v1
is_internal_developer: False
language_model: ChaiML/qwen32b-dpoexp1-s2-ftsimpoexp4-1330pref-1-1
model_size: 33B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-04-21
win_ratio: 0.5638168781025924
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 chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer
Waiting for job on chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer to finish
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ║                                                                     ║
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: Downloaded to shared memory in 111.021s
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ltlke0a, device:0
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: quantized model in 63.025s
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: Processed model ChaiML/qwen32b-dpoexp1-s2-ftsimpoexp4-1330pref-1-1 in 174.046s
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/config.json
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/added_tokens.json
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/special_tokens_map.json
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/flywheel_model.2.safetensors
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/flywheel_model.1.safetensors
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-dpoexp1-20366-v1/flywheel_model.0.safetensors
chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.15it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 75.27it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 89.24it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 91.40it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 52.60it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:14, 51.08it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:11, 59.23it/s]
Loading 0:  10%|▉         | 76/771 [00:01<00:10, 67.13it/s]
Loading 0:  11%|█▏        | 88/771 [00:01<00:09, 72.64it/s]
Loading 0:  13%|█▎        | 98/771 [00:01<00:08, 78.64it/s]
Loading 0:  14%|█▍        | 107/771 [00:01<00:11, 58.85it/s]
Loading 0:  15%|█▌        | 116/771 [00:01<00:10, 65.19it/s]
Loading 0:  16%|█▌        | 124/771 [00:01<00:09, 64.88it/s]
Loading 0:  17%|█▋        | 133/771 [00:02<00:09, 64.90it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:07, 87.84it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 78.19it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 56.63it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 55.51it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 57.02it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 67.87it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.52it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.58it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 60.50it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.89it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.92it/s]
Loading 0:  33%|███▎      | 256/771 [00:03<00:07, 70.10it/s]
Loading 0:  35%|███▍      | 267/771 [00:03<00:06, 79.15it/s]
Loading 0:  36%|███▌      | 276/771 [00:04<00:06, 81.57it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 62.56it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 54.23it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:40,  2.12it/s]
Loading 0:  41%|████      | 315/771 [00:18<02:20,  3.25it/s]
Loading 0:  42%|████▏     | 327/771 [00:18<01:32,  4.81it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<01:04,  6.76it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:51,  8.26it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:42,  9.81it/s]
Loading 0:  47%|████▋     | 365/771 [00:19<00:28, 14.45it/s]
Loading 0:  49%|████▉     | 377/771 [00:19<00:19, 20.19it/s]
Loading 0:  50%|█████     | 389/771 [00:20<00:14, 26.98it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 34.76it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:10, 35.15it/s]
Loading 0:  55%|█████▌    | 425/771 [00:20<00:08, 42.47it/s]
Loading 0:  57%|█████▋    | 437/771 [00:20<00:06, 50.74it/s]
Loading 0:  58%|█████▊    | 449/771 [00:21<00:05, 58.35it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:04, 61.17it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 54.68it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 60.20it/s]
Loading 0:  64%|██████▍   | 497/771 [00:21<00:04, 66.26it/s]
Loading 0:  66%|██████▌   | 509/771 [00:21<00:03, 71.71it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 68.58it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:03, 59.70it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 64.71it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 70.46it/s]
Loading 0:  74%|███████▍  | 569/771 [00:22<00:02, 75.27it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 71.70it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 61.91it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 66.59it/s]
Loading 0:  80%|███████▉  | 616/771 [00:23<00:02, 74.79it/s]
Loading 0:  81%|████████▏ | 627/771 [00:37<00:57,  2.53it/s]
Loading 0:  83%|████████▎ | 638/771 [00:38<00:37,  3.54it/s]
Loading 0:  84%|████████▍ | 647/771 [00:38<00:27,  4.52it/s]
Loading 0:  85%|████████▍ | 654/771 [00:38<00:20,  5.64it/s]
Loading 0:  86%|████████▋ | 665/771 [00:38<00:12,  8.16it/s]
Loading 0:  88%|████████▊ | 677/771 [00:38<00:07, 11.81it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:04, 16.49it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 23.32it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 25.55it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 31.94it/s]
Loading 0:  96%|█████████▌| 737/771 [00:39<00:00, 39.89it/s]
Loading 0:  97%|█████████▋| 749/771 [00:39<00:00, 48.13it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:00,  5.27it/s]
                                                            

Job chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer completed after 208.17s with status: succeeded
Stopping job with name chaiml-qwen32b-dpoexp1-20366-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.46s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-dpoexp1-20366-v1
Waiting for inference service chaiml-qwen32b-dpoexp1-20366-v1 to be ready
Inference service chaiml-qwen32b-dpoexp1-20366-v1 ready after 130.7959122657776s
Pipeline stage MKMLDeployer completed in 131.28s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.9305429458618164s
Received healthy response to inference request in 3.3428728580474854s
Received healthy response to inference request in 3.6788651943206787s
Received healthy response to inference request in 3.3061540126800537s
5 requests
1 failed requests
5th percentile: 3.31349778175354
10th percentile: 3.3208415508270264
20th percentile: 3.335529088973999
30th percentile: 3.410071325302124
40th percentile: 3.5444682598114015
50th percentile: 3.6788651943206787
60th percentile: 3.7795362949371336
70th percentile: 3.880207395553589
80th percentile: 7.175256776809695
90th percentile: 13.664684438705446
95th percentile: 16.909398269653316
99th percentile: 19.50516933441162
mean time: 6.882509422302246
%s, retrying in %s seconds...
Received healthy response to inference request in 3.975804328918457s
Received healthy response to inference request in 3.310432195663452s
Received healthy response to inference request in 3.351956844329834s
Received healthy response to inference request in 3.2979681491851807s
Received healthy response to inference request in 3.3091046810150146s
5 requests
0 failed requests
5th percentile: 3.3001954555511475
10th percentile: 3.3024227619171143
20th percentile: 3.306877374649048
30th percentile: 3.309370183944702
40th percentile: 3.3099011898040773
50th percentile: 3.310432195663452
60th percentile: 3.327042055130005
70th percentile: 3.3436519145965575
80th percentile: 3.476726341247559
90th percentile: 3.7262653350830077
95th percentile: 3.851034832000732
99th percentile: 3.950850429534912
mean time: 3.449053239822388
Pipeline stage StressChecker completed in 54.30s
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 0.67s
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 0.99s
Shutdown handler de-registered
chaiml-qwen32b-dpoexp1-_20366_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 5468.11s
Shutdown handler de-registered
chaiml-qwen32b-dpoexp1-_20366_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-dpoexp1-_20366_v1 status is now torndown due to DeploymentManager action