chaiml-gy-exp175-dpo3-e_37740

developer_uid: bogoconic1

submission_id: chaiml-gy-exp175-dpo3-e_37740_v1

model_name: chaiml-gy-exp175-dpo3-e_37740_v1

model_group: ChaiML/gy-exp175-dpo3-ex

status: torndown

timestamp: 2025-07-16T13:18:10+00:00

num_battles: 9650

num_wins: 5217

celo_rating: 1319.25

family_friendly_score: 0.5032

family_friendly_standard_error: 0.007070922994913747

submission_type: basic

model_repo: ChaiML/gy-exp175-dpo3-exp54ep6s2-gy-datamix-v3p1-AR-v3p2-lastmsg-gt0.6-top10krmdiff-ep2

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': 0.5183782014515236, 'latency_mean': 1.928991631269455, 'latency_p50': 1.9162235260009766, 'latency_p90': 2.132926344871521}, {'batch_size': 3, 'throughput': 1.0478353676956111, 'latency_mean': 2.8565503895282744, 'latency_p50': 2.851221203804016, 'latency_p90': 3.1704113483428955}, {'batch_size': 5, 'throughput': 1.3326390958443002, 'latency_mean': 3.7182035660743713, 'latency_p50': 3.749475359916687, 'latency_p90': 4.1710289478302}, {'batch_size': 6, 'throughput': 1.4466691012910913, 'latency_mean': 4.126753528118133, 'latency_p50': 4.092455267906189, 'latency_p90': 4.650808715820313}, {'batch_size': 8, 'throughput': 1.5757059975019883, 'latency_mean': 5.042079961299896, 'latency_p50': 5.069102644920349, 'latency_p90': 5.646808290481568}, {'batch_size': 10, 'throughput': 1.66202817156264, 'latency_mean': 5.966380933523178, 'latency_p50': 5.966791868209839, 'latency_p90': 6.672620081901551}]

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

display_name: chaiml-gy-exp175-dpo3-e_37740_v1

is_internal_developer: False

language_model: ChaiML/gy-exp175-dpo3-exp54ep6s2-gy-datamix-v3p1-AR-v3p2-lastmsg-gt0.6-top10krmdiff-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-16

win_ratio: 0.5406217616580311

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, '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': 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-gy-exp175-dpo3-e-37740-v1-mkmlizer
Waiting for job on chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer to finish
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: Downloaded to shared memory in 77.481s
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: Checking if ChaiML/gy-exp175-dpo3-exp54ep6s2-gy-datamix-v3p1-AR-v3p2-lastmsg-gt0.6-top10krmdiff-ep2 already exists in ChaiML
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiebyje7s, device:0
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: quantized model in 48.784s
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: Processed model ChaiML/gy-exp175-dpo3-exp54ep6s2-gy-datamix-v3p1-AR-v3p2-lastmsg-gt0.6-top10krmdiff-ep2 in 126.266s
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp175-dpo3-e-37740-v1/nvidia
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp175-dpo3-e-37740-v1/nvidia/special_tokens_map.json
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp175-dpo3-e-37740-v1/nvidia/tokenizer_config.json
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp175-dpo3-e-37740-v1/nvidia/tokenizer.json
chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.55it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 31.95it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.00it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.66it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.17it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.96it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.00it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.60it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.72it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.90it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:13, 23.22it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 26.55it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:11, 27.10it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.81it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.55it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.87it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.48it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.71it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.58it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.06it/s]
Loading 0:  27%|██▋       | 98/363 [00:03<00:09, 27.96it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 23.71it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.99it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 24.75it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.46it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.35it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.58it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.48it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.97it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.01it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.71it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.14it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:08, 23.62it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.53it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.47it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.08it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.59it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.26it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.72it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.68it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.69it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.37it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.07it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:06,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:34,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:33,  1.66it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.79it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.99it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:23,  5.99it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:16,  8.40it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.73it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.36it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.00it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 19.70it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.13it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.10it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 21.72it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 28.42it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 21.91it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 20.62it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.86it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.70it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.15it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.59it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.34it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.86it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.15it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.92it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.58it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.24it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.23it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.55it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.76it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.21it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.76it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.17it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.80it/s]
                                                            
Job chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer completed after 156.94s with status: succeeded
Stopping job with name chaiml-gy-exp175-dpo3-e-37740-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp175-dpo3-e-37740-v1
Waiting for inference service chaiml-gy-exp175-dpo3-e-37740-v1 to be ready
Inference service chaiml-gy-exp175-dpo3-e-37740-v1 ready after 271.4093906879425s
Pipeline stage MKMLDeployer completed in 272.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.568648099899292s
Received healthy response to inference request in 2.211885690689087s
Received healthy response to inference request in 1.948429822921753s
Received healthy response to inference request in 2.266528606414795s
Received healthy response to inference request in 2.147552490234375s
5 requests
0 failed requests
5th percentile: 1.9882543563842774
10th percentile: 2.028078889846802
20th percentile: 2.1077279567718508
30th percentile: 2.1604191303253173
40th percentile: 2.1861524105072023
50th percentile: 2.211885690689087
60th percentile: 2.23374285697937
70th percentile: 2.255600023269653
80th percentile: 2.3269525051116946
90th percentile: 2.447800302505493
95th percentile: 2.5082242012023923
99th percentile: 2.556563320159912
mean time: 2.2286089420318604
Pipeline stage StressChecker completed in 12.46s
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 1.06s
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 0.69s
Shutdown handler de-registered
chaiml-gy-exp175-dpo3-e_37740_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 5334.98s
Shutdown handler de-registered
chaiml-gy-exp175-dpo3-e_37740_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp175-dpo3-e_37740_v1 status is now torndown due to DeploymentManager action
chaiml-gy-exp175-dpo3-e_37740_v1 status is now torndown due to DeploymentManager action