chaiml-qwen3-8bskywork-_99284

developer_uid: NischayDnk

submission_id: chaiml-qwen3-8bskywork-_99284_v2

model_name: chaiml-qwen3-8bskywork-_99284_v2

model_group: ChaiML/qwen3-8bskywork-v

status: torndown

timestamp: 2025-07-10T15:50:06+00:00

num_battles: 8858

num_wins: 4592

celo_rating: 1289.37

family_friendly_score: 0.5264

family_friendly_standard_error: 0.007061204429840564

submission_type: basic

model_repo: ChaiML/qwen3-8bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step250k-5575acc

model_architecture: Qwen3ForSequenceClassification

model_num_parameters: 8190726144.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 1

reward_model: default

display_name: chaiml-qwen3-8bskywork-_99284_v2

ineligible_reason: max_output_tokens!=64

is_internal_developer: False

language_model: ChaiML/qwen3-8bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step250k-5575acc

model_size: 8B

ranking_group: single

us_pacific_date: 2025-07-10

win_ratio: 0.5184014450214496

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 1}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}

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-qwen3-8bskywork-99284-v2-mkmlizer
Waiting for job on chaiml-qwen3-8bskywork-99284-v2-mkmlizer to finish
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║                                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║                                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║                                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║                                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ║                                                                     ║
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: Downloaded to shared memory in 22.252s
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: Checking if ChaiML/qwen3-8bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step250k-5575acc already exists in ChaiML
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpkvbk5biy, device:0
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: quantized model in 27.715s
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: Processed model ChaiML/qwen3-8bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step250k-5575acc in 49.968s
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen3-8bskywork-99284-v2/nvidia
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen3-8bskywork-99284-v2/nvidia/flywheel_model.0.safetensors
chaiml-qwen3-8bskywork-99284-v2-mkmlizer: 
Loading 0:   0%|          | 0/399 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/399 [00:00<00:11, 35.38it/s]
Loading 0:   4%|▎         | 14/399 [00:00<00:06, 59.43it/s]
Loading 0:   6%|▌         | 22/399 [00:00<00:05, 66.69it/s]
Loading 0:   7%|▋         | 29/399 [00:00<00:06, 54.25it/s]
Loading 0:   9%|▉         | 36/399 [00:00<00:06, 55.62it/s]
Loading 0:  11%|█         | 42/399 [00:00<00:06, 54.38it/s]
Loading 0:  12%|█▏        | 48/399 [00:00<00:06, 55.14it/s]
Loading 0:  14%|█▍        | 56/399 [00:01<00:06, 53.24it/s]
Loading 0:  16%|█▌        | 62/399 [00:01<00:06, 51.16it/s]
Loading 0:  18%|█▊        | 70/399 [00:01<00:05, 57.09it/s]
Loading 0:  20%|█▉        | 78/399 [00:01<00:05, 55.37it/s]
Loading 0:  21%|██        | 84/399 [00:01<00:05, 54.70it/s]
Loading 0:  23%|██▎       | 91/399 [00:01<00:05, 57.42it/s]
Loading 0:  24%|██▍       | 97/399 [00:01<00:05, 56.79it/s]
Loading 0:  27%|██▋       | 106/399 [00:01<00:04, 64.89it/s]
Loading 0:  28%|██▊       | 113/399 [00:02<00:07, 37.89it/s]
Loading 0:  30%|███       | 121/399 [00:02<00:06, 44.62it/s]
Loading 0:  32%|███▏      | 129/399 [00:02<00:05, 46.35it/s]
Loading 0:  34%|███▍      | 135/399 [00:02<00:05, 47.64it/s]
Loading 0:  36%|███▌      | 142/399 [00:02<00:04, 51.88it/s]
Loading 0:  37%|███▋      | 148/399 [00:02<00:04, 52.43it/s]
Loading 0:  39%|███▊      | 154/399 [00:02<00:04, 52.60it/s]
Loading 0:  41%|████      | 162/399 [00:03<00:04, 51.70it/s]
Loading 0:  42%|████▏     | 168/399 [00:03<00:04, 51.54it/s]
Loading 0:  44%|████▎     | 174/399 [00:03<00:04, 53.60it/s]
Loading 0:  45%|████▌     | 180/399 [00:03<00:04, 51.98it/s]
Loading 0:  47%|████▋     | 187/399 [00:03<00:03, 55.37it/s]
Loading 0:  49%|████▉     | 195/399 [00:03<00:03, 54.04it/s]
Loading 0:  50%|█████     | 201/399 [00:03<00:03, 52.25it/s]
Loading 0:  52%|█████▏    | 209/399 [00:03<00:03, 57.25it/s]
Loading 0:  54%|█████▍    | 217/399 [00:04<00:03, 54.91it/s]
Loading 0:  56%|█████▌    | 223/399 [00:04<00:03, 54.45it/s]
Loading 0:  58%|█████▊    | 231/399 [00:04<00:02, 58.26it/s]
Loading 0:  60%|█████▉    | 239/399 [00:04<00:02, 55.58it/s]
Loading 0:  62%|██████▏   | 247/399 [00:04<00:02, 61.41it/s]
Loading 0:  64%|██████▎   | 254/399 [00:05<00:04, 35.26it/s]
Loading 0:  65%|██████▍   | 259/399 [00:05<00:03, 36.98it/s]
Loading 0:  67%|██████▋   | 268/399 [00:05<00:02, 46.08it/s]
Loading 0:  69%|██████▉   | 276/399 [00:05<00:02, 45.73it/s]
Loading 0:  71%|███████   | 282/399 [00:05<00:02, 45.44it/s]
Loading 0:  73%|███████▎  | 290/399 [00:05<00:02, 51.30it/s]
Loading 0:  75%|███████▍  | 298/399 [00:05<00:01, 51.07it/s]
Loading 0:  76%|███████▌  | 304/399 [00:05<00:01, 50.20it/s]
Loading 0:  78%|███████▊  | 311/399 [00:06<00:01, 54.26it/s]
Loading 0:  79%|███████▉  | 317/399 [00:06<00:01, 54.54it/s]
Loading 0:  81%|████████  | 323/399 [00:06<00:01, 54.81it/s]
Loading 0:  83%|████████▎ | 331/399 [00:06<00:01, 52.00it/s]
Loading 0:  84%|████████▍ | 337/399 [00:06<00:01, 50.06it/s]
Loading 0:  86%|████████▌ | 344/399 [00:06<00:01, 53.71it/s]
Loading 0:  88%|████████▊ | 350/399 [00:06<00:00, 52.55it/s]
Loading 0:  89%|████████▉ | 356/399 [00:06<00:00, 54.44it/s]
Loading 0:  91%|█████████ | 363/399 [00:06<00:00, 58.17it/s]
Loading 0:  92%|█████████▏| 369/399 [00:07<00:00, 46.40it/s]
Loading 0:  95%|█████████▍| 378/399 [00:07<00:00, 55.76it/s]
Loading 0:  97%|█████████▋| 386/399 [00:07<00:00, 53.80it/s]
Loading 0:  98%|█████████▊| 392/399 [00:07<00:00, 38.16it/s]
Loading 0:  99%|█████████▉| 397/399 [00:07<00:00, 40.01it/s]
                                                            
Job chaiml-qwen3-8bskywork-99284-v2-mkmlizer completed after 75.52s with status: succeeded
Stopping job with name chaiml-qwen3-8bskywork-99284-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.40s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen3-8bskywork-99284-v2
Waiting for inference service chaiml-qwen3-8bskywork-99284-v2 to be ready
Inference service chaiml-qwen3-8bskywork-99284-v2 ready after 201.2186634540558s
Pipeline stage MKMLDeployer completed in 201.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.796290159225464s
Received healthy response to inference request in 3.2511520385742188s
Received healthy response to inference request in 8.278869390487671s
Received healthy response to inference request in 3.619319200515747s
Received healthy response to inference request in 4.844005584716797s
5 requests
0 failed requests
5th percentile: 2.887262535095215
10th percentile: 2.9782349109649657
20th percentile: 3.1601796627044676
30th percentile: 3.3247854709625244
40th percentile: 3.4720523357391357
50th percentile: 3.619319200515747
60th percentile: 4.109193754196167
70th percentile: 4.599068307876586
80th percentile: 5.530978345870972
90th percentile: 6.9049238681793215
95th percentile: 7.591896629333496
99th percentile: 8.141474838256835
mean time: 4.55792727470398
Pipeline stage StressChecker completed in 24.47s
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 0.66s
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 0.96s
Shutdown handler de-registered
chaiml-qwen3-8bskywork-_99284_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
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 3894.73s
Shutdown handler de-registered
chaiml-qwen3-8bskywork-_99284_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen3-8bskywork-_99284_v2 status is now torndown due to DeploymentManager action