developer_uid: NischayDnk
submission_id: pku-ds-lab-fairyr1-32b_v1
model_name: pku-ds-lab-fairyr1-32b_v1
model_group: PKU-DS-LAB/FairyR1-32B
status: torndown
timestamp: 2025-05-28T08:13:37+00:00
num_battles: 7149
num_wins: 3144
celo_rating: 1239.84
family_friendly_score: 0.6719999999999999
family_friendly_standard_error: 0.006639518054798857
submission_type: basic
model_repo: PKU-DS-LAB/FairyR1-32B
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: pku-ds-lab-fairyr1-32b_v1
is_internal_developer: False
language_model: PKU-DS-LAB/FairyR1-32B
model_size: 33B
ranking_group: single
us_pacific_date: 2025-05-28
win_ratio: 0.43978178766261017
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], '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 pku-ds-lab-fairyr1-32b-v1-mkmlizer
Waiting for job on pku-ds-lab-fairyr1-32b-v1-mkmlizer to finish
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ _____ __ __ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ /___/ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ Version: 0.12.8 ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ https://mk1.ai ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ belonging to: ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ Chai Research Corp. ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ║ ║
pku-ds-lab-fairyr1-32b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pku-ds-lab-fairyr1-32b-v1-mkmlizer: Downloaded to shared memory in 86.560s
pku-ds-lab-fairyr1-32b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi8728l6q, device:0
pku-ds-lab-fairyr1-32b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pku-ds-lab-fairyr1-32b-v1-mkmlizer: quantized model in 65.081s
pku-ds-lab-fairyr1-32b-v1-mkmlizer: Processed model PKU-DS-LAB/FairyR1-32B in 151.642s
pku-ds-lab-fairyr1-32b-v1-mkmlizer: creating bucket guanaco-mkml-models
pku-ds-lab-fairyr1-32b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pku-ds-lab-fairyr1-32b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/config.json
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/special_tokens_map.json
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/tokenizer_config.json
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/tokenizer.json
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/flywheel_model.2.safetensors
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/flywheel_model.0.safetensors
pku-ds-lab-fairyr1-32b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/pku-ds-lab-fairyr1-32b-v1/flywheel_model.1.safetensors
pku-ds-lab-fairyr1-32b-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 0%| | 2/771 [00:07<45:23, 3.54s/it] Loading 0: 1%| | 6/771 [00:07<12:01, 1.06it/s] Loading 0: 2%|▏ | 17/771 [00:07<03:07, 4.02it/s] Loading 0: 3%|▎ | 23/771 [00:07<02:11, 5.68it/s] Loading 0: 4%|▍ | 30/771 [00:07<01:26, 8.55it/s] Loading 0: 5%|▌ | 41/771 [00:07<00:49, 14.78it/s] Loading 0: 7%|▋ | 52/771 [00:07<00:32, 22.34it/s] Loading 0: 8%|▊ | 60/771 [00:08<00:25, 28.07it/s] Loading 0: 9%|▉ | 68/771 [00:08<00:21, 33.24it/s] Loading 0: 10%|▉ | 77/771 [00:08<00:16, 41.28it/s] Loading 0: 11%|█▏ | 88/771 [00:08<00:17, 38.05it/s] Loading 0: 12%|█▏ | 96/771 [00:08<00:15, 43.90it/s] Loading 0: 13%|█▎ | 103/771 [00:08<00:14, 45.70it/s] Loading 0: 15%|█▍ | 113/771 [00:09<00:11, 55.73it/s] Loading 0: 16%|█▌ | 124/771 [00:09<00:09, 66.36it/s] Loading 0: 17%|█▋ | 133/771 [00:09<00:08, 70.94it/s] Loading 0: 18%|█▊ | 142/771 [00:09<00:09, 68.65it/s] Loading 0: 19%|█▉ | 150/771 [00:09<00:13, 44.51it/s] Loading 0: 21%|██ | 161/771 [00:09<00:10, 55.64it/s] Loading 0: 22%|██▏ | 172/771 [00:09<00:09, 65.75it/s] Loading 0: 23%|██▎ | 181/771 [00:10<00:08, 70.31it/s] Loading 0: 25%|██▍ | 190/771 [00:10<00:08, 68.59it/s] Loading 0: 26%|██▌ | 198/771 [00:10<00:08, 65.49it/s] Loading 0: 27%|██▋ | 208/771 [00:10<00:10, 53.63it/s] Loading 0: 28%|██▊ | 216/771 [00:10<00:09, 58.42it/s] Loading 0: 29%|██▉ | 223/771 [00:10<00:09, 57.30it/s] Loading 0: 30%|███ | 233/771 [00:10<00:08, 64.99it/s] Loading 0: 32%|███▏ | 244/771 [00:11<00:07, 75.04it/s] Loading 0: 33%|███▎ | 253/771 [00:11<00:06, 77.85it/s] Loading 0: 34%|███▍ | 262/771 [00:11<00:06, 73.32it/s] Loading 0: 35%|███▌ | 270/771 [00:11<00:10, 46.14it/s] Loading 0: 36%|███▌ | 277/771 [00:26<04:31, 1.82it/s] Loading 0: 37%|███▋ | 282/771 [00:26<03:36, 2.26it/s] Loading 0: 38%|███▊ | 293/771 [00:26<02:10, 3.66it/s] Loading 0: 39%|███▉ | 304/771 [00:26<01:23, 5.60it/s] Loading 0: 40%|████ | 312/771 [00:26<01:01, 7.48it/s] Loading 0: 42%|████▏ | 320/771 [00:26<00:45, 9.92it/s] Loading 0: 43%|████▎ | 328/771 [00:27<00:38, 11.62it/s] Loading 0: 44%|████▎ | 336/771 [00:27<00:28, 15.41it/s] Loading 0: 44%|████▍ | 343/771 [00:27<00:22, 19.02it/s] Loading 0: 46%|████▌ | 353/771 [00:27<00:15, 26.35it/s] Loading 0: 47%|████▋ | 364/771 [00:27<00:11, 35.80it/s] Loading 0: 48%|████▊ | 372/771 [00:27<00:09, 41.76it/s] Loading 0: 49%|████▉ | 380/771 [00:28<00:08, 45.92it/s] Loading 0: 50%|█████ | 388/771 [00:28<00:09, 39.85it/s] Loading 0: 51%|█████▏ | 396/771 [00:28<00:08, 46.13it/s] Loading 0: 52%|█████▏ | 403/771 [00:28<00:07, 47.96it/s] Loading 0: 54%|█████▎ | 413/771 [00:28<00:06, 58.46it/s] Loading 0: 55%|█████▍ | 424/771 [00:28<00:04, 69.61it/s] Loading 0: 56%|█████▌ | 433/771 [00:28<00:04, 73.25it/s] Loading 0: 57%|█████▋ | 442/771 [00:29<00:04, 70.62it/s] Loading 0: 58%|█████▊ | 450/771 [00:29<00:07, 45.85it/s] Loading 0: 60%|█████▉ | 461/771 [00:29<00:05, 57.24it/s] Loading 0: 61%|██████ | 472/771 [00:29<00:04, 67.38it/s] Loading 0: 62%|██████▏ | 481/771 [00:29<00:04, 72.04it/s] Loading 0: 64%|██████▎ | 490/771 [00:29<00:04, 70.06it/s] Loading 0: 65%|██████▍ | 498/771 [00:29<00:04, 67.17it/s] Loading 0: 66%|██████▌ | 508/771 [00:30<00:04, 54.95it/s] Loading 0: 67%|██████▋ | 516/771 [00:30<00:04, 59.50it/s] Loading 0: 68%|██████▊ | 523/771 [00:30<00:04, 57.94it/s] Loading 0: 69%|██████▉ | 533/771 [00:30<00:03, 67.34it/s] Loading 0: 71%|███████ | 544/771 [00:30<00:02, 76.55it/s] Loading 0: 72%|███████▏ | 553/771 [00:30<00:02, 79.39it/s] Loading 0: 73%|███████▎ | 562/771 [00:30<00:02, 74.65it/s] Loading 0: 74%|███████▍ | 570/771 [00:31<00:04, 47.89it/s] Loading 0: 75%|███████▌ | 581/771 [00:31<00:03, 59.50it/s] Loading 0: 77%|███████▋ | 592/771 [00:31<00:02, 69.74it/s] Loading 0: 78%|███████▊ | 601/771 [00:46<01:20, 2.11it/s] Loading 0: 79%|███████▊ | 606/771 [00:46<01:04, 2.54it/s] Loading 0: 80%|████████ | 617/771 [00:46<00:39, 3.94it/s] Loading 0: 81%|████████▏ | 628/771 [00:47<00:25, 5.54it/s] Loading 0: 82%|████████▏ | 636/771 [00:47<00:18, 7.32it/s] Loading 0: 83%|████████▎ | 643/771 [00:47<00:13, 9.31it/s] Loading 0: 85%|████████▍ | 653/771 [00:47<00:08, 13.33it/s] Loading 0: 86%|████████▌ | 664/771 [00:47<00:05, 19.03it/s] Loading 0: 87%|████████▋ | 673/771 [00:47<00:03, 24.52it/s] Loading 0: 88%|████████▊ | 682/771 [00:47<00:02, 29.90it/s] Loading 0: 89%|████████▉ | 690/771 [00:48<00:02, 28.25it/s] Loading 0: 91%|█████████ | 701/771 [00:48<00:01, 37.85it/s] Loading 0: 92%|█████████▏| 712/771 [00:48<00:01, 47.74it/s] Loading 0: 94%|█████████▎| 721/771 [00:48<00:00, 54.67it/s] Loading 0: 95%|█████████▍| 730/771 [00:48<00:00, 57.11it/s] Loading 0: 96%|█████████▌| 738/771 [00:48<00:00, 57.62it/s] Loading 0: 97%|█████████▋| 748/771 [00:48<00:00, 48.96it/s] Loading 0: 98%|█████████▊| 756/771 [00:49<00:00, 54.46it/s] Loading 0: 99%|█████████▉| 763/771 [00:49<00:00, 54.85it/s]
Job pku-ds-lab-fairyr1-32b-v1-mkmlizer completed after 187.24s with status: succeeded
Stopping job with name pku-ds-lab-fairyr1-32b-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.77s
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 pku-ds-lab-fairyr1-32b-v1
Waiting for inference service pku-ds-lab-fairyr1-32b-v1 to be ready
Inference service pku-ds-lab-fairyr1-32b-v1 ready after 150.81266117095947s
Pipeline stage MKMLDeployer completed in 151.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.728209972381592s
Received healthy response to inference request in 2.0435311794281006s
Received healthy response to inference request in 2.177481174468994s
Received healthy response to inference request in 2.041825532913208s
Received healthy response to inference request in 2.632314920425415s
5 requests
0 failed requests
5th percentile: 2.0421666622161867
10th percentile: 2.042507791519165
20th percentile: 2.043190050125122
30th percentile: 2.0703211784362794
40th percentile: 2.1239011764526365
50th percentile: 2.177481174468994
60th percentile: 2.3594146728515626
70th percentile: 2.5413481712341306
80th percentile: 2.6514939308166503
90th percentile: 2.6898519515991213
95th percentile: 2.7090309619903565
99th percentile: 2.724374170303345
mean time: 2.324672555923462
Pipeline stage StressChecker completed in 12.95s
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 0.63s
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 0.68s
Shutdown handler de-registered
pku-ds-lab-fairyr1-32b_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 0.09s
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 pku-ds-lab-fairyr1-32b-v1-profiler
Waiting for inference service pku-ds-lab-fairyr1-32b-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 3141.18s
Shutdown handler de-registered
pku-ds-lab-fairyr1-32b_v1 status is now inactive due to auto deactivation removed underperforming models
pku-ds-lab-fairyr1-32b_v1 status is now torndown due to DeploymentManager action