chaiml-emperor-and-conc_55748

developer_uid: richhx

submission_id: chaiml-emperor-and-conc_55748_v2

model_name: chaiml-emperor-and-conc_55748_v2

model_group: ChaiML/Emperor-and-concu

status: torndown

timestamp: 2025-06-24T00:07:43+00:00

num_battles: 6398

num_wins: 3148

celo_rating: 1270.58

family_friendly_score: 0.5682

family_friendly_standard_error: 0.0070049805138915275

submission_type: basic

model_repo: ChaiML/Emperor-and-concubines250614093140_preference_dpo

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5132792991547733, 'latency_mean': 1.9480888152122497, 'latency_p50': 1.9502466917037964, 'latency_p90': 2.1673875570297243}, {'batch_size': 3, 'throughput': 1.019042091531958, 'latency_mean': 2.9271518540382386, 'latency_p50': 2.890548348426819, 'latency_p90': 3.2202372312545777}, {'batch_size': 5, 'throughput': 1.2938437750019636, 'latency_mean': 3.838930159807205, 'latency_p50': 3.838902473449707, 'latency_p90': 4.346111464500427}, {'batch_size': 6, 'throughput': 1.3925987139359988, 'latency_mean': 4.271147624254227, 'latency_p50': 4.23164975643158, 'latency_p90': 4.770956492424011}, {'batch_size': 8, 'throughput': 1.5315752805102847, 'latency_mean': 5.193725717067719, 'latency_p50': 5.187293291091919, 'latency_p90': 5.8174028396606445}, {'batch_size': 10, 'throughput': 1.576150537876688, 'latency_mean': 6.277155970335007, 'latency_p50': 6.242283344268799, 'latency_p90': 7.016030287742614}]

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

display_name: chaiml-emperor-and-conc_55748_v2

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/Emperor-and-concubines250614093140_preference_dpo

model_size: 24B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-06-23

win_ratio: 0.4920287589871835

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['You:', '####', '</s>', '####\n', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', '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-emperor-and-conc-55748-v2-mkmlizer
Waiting for job on chaiml-emperor-and-conc-55748-v2-mkmlizer to finish
chaiml-emperor-and-conc-55748-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║                                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║                                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║                                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║                                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ║                                                                     ║
chaiml-emperor-and-conc-55748-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-emperor-and-conc-55748-v2-mkmlizer: Downloaded to shared memory in 120.732s
chaiml-emperor-and-conc-55748-v2-mkmlizer: Checking if ChaiML/Emperor-and-concubines250614093140_preference_dpo already exists in ChaiML
chaiml-emperor-and-conc-55748-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph6bi_rsm, device:0
chaiml-emperor-and-conc-55748-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-emperor-and-conc-55748-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-emperor-and-conc-55748-v2/flywheel_model.1.safetensors
chaiml-emperor-and-conc-55748-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-emperor-and-conc-55748-v2/flywheel_model.0.safetensors
chaiml-emperor-and-conc-55748-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.81it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.90it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.13it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.69it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.06it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.01it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.30it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.02it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.27it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.39it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:13, 23.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.05it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.33it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.02it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.73it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.91it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.39it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.99it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.84it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.52it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.76it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:09, 27.51it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 21.66it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.27it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.88it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.44it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.07it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.80it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.62it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.00it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.15it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.76it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 22.90it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.32it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.21it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.73it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 27.01it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:06, 27.49it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 26.79it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.02it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.36it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.86it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.47it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:34,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.15it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.84it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.07it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.20it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.14it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.08it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.71it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.39it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.20it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.28it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.94it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.85it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.62it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.17it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.21it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.14it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.45it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.76it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.93it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.57it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.05it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.19it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.64it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.61it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.04it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 27.06it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.95it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.78it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.63it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.24it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.46it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.01it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 24.99it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.08it/s]
                                                            
Job chaiml-emperor-and-conc-55748-v2-mkmlizer completed after 204.16s with status: succeeded
Stopping job with name chaiml-emperor-and-conc-55748-v2-mkmlizer
Pipeline stage MKMLizer completed in 204.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-emperor-and-conc-55748-v2
Waiting for inference service chaiml-emperor-and-conc-55748-v2 to be ready
Inference service chaiml-emperor-and-conc-55748-v2 ready after 130.44323229789734s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9860386848449707s
Received healthy response to inference request in 2.1563844680786133s
Received healthy response to inference request in 1.8940908908843994s
Received healthy response to inference request in 2.0246145725250244s
Received healthy response to inference request in 1.8669078350067139s
5 requests
0 failed requests
5th percentile: 1.872344446182251
10th percentile: 1.877781057357788
20th percentile: 1.8886542797088623
30th percentile: 1.9201956272125245
40th percentile: 1.9724050998687743
50th percentile: 2.0246145725250244
60th percentile: 2.07732253074646
70th percentile: 2.1300304889678956
80th percentile: 2.322315311431885
90th percentile: 2.654176998138428
95th percentile: 2.820107841491699
99th percentile: 2.952852516174316
mean time: 2.1856072902679444
Pipeline stage StressChecker completed in 12.43s
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 0.71s
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 0.77s
Shutdown handler de-registered
chaiml-emperor-and-conc_55748_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3173.59s
Shutdown handler de-registered
chaiml-emperor-and-conc_55748_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-emperor-and-conc_55748_v2 status is now torndown due to DeploymentManager action