chaiml-gy-exp109-dpo-ex_67242

developer_uid: bogoconic1

submission_id: chaiml-gy-exp109-dpo-ex_67242_v1

model_name: chaiml-gy-exp109-dpo-ex_67242_v1

model_group: ChaiML/gy-exp109-dpo-exp

status: torndown

timestamp: 2025-07-07T13:34:55+00:00

num_battles: 9450

num_wins: 4875

celo_rating: 1300.2

family_friendly_score: 0.5138

family_friendly_standard_error: 0.007068374070463447

submission_type: basic

model_repo: ChaiML/gy-exp109-dpo-exp106ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.75-diffgt0.005-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': 0.5222237783282636, 'latency_mean': 1.9147639274597168, 'latency_p50': 1.9068211317062378, 'latency_p90': 2.131112885475159}, {'batch_size': 3, 'throughput': 1.0521806314293434, 'latency_mean': 2.835684678554535, 'latency_p50': 2.8373762369155884, 'latency_p90': 3.138535404205322}, {'batch_size': 5, 'throughput': 1.3339693537602078, 'latency_mean': 3.72476900100708, 'latency_p50': 3.7434632778167725, 'latency_p90': 4.0969888925552365}, {'batch_size': 6, 'throughput': 1.4219930948863646, 'latency_mean': 4.182814730405807, 'latency_p50': 4.178972840309143, 'latency_p90': 4.669497871398926}, {'batch_size': 8, 'throughput': 1.5741044257695949, 'latency_mean': 5.030150390863419, 'latency_p50': 4.991302251815796, 'latency_p90': 5.655004096031189}, {'batch_size': 10, 'throughput': 1.6729111306604967, 'latency_mean': 5.916331300735473, 'latency_p50': 5.907352447509766, 'latency_p90': 6.6724494934082035}]

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

display_name: chaiml-gy-exp109-dpo-ex_67242_v1

is_internal_developer: False

language_model: ChaiML/gy-exp109-dpo-exp106ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.75-diffgt0.005-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-07

win_ratio: 0.5158730158730159

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': ['\n', '<|im_end|>', '<|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-exp109-dpo-ex-67242-v1-mkmlizer
Waiting for job on chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer to finish
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: Downloaded to shared memory in 78.577s
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: Checking if ChaiML/gy-exp109-dpo-exp106ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.75-diffgt0.005-ep2 already exists in ChaiML
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_p1rob4q, device:0
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: quantized model in 49.419s
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: Processed model ChaiML/gy-exp109-dpo-exp106ep2s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.75-diffgt0.005-ep2 in 127.997s
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/config.json
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/special_tokens_map.json
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/tokenizer_config.json
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/tokenizer.json
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp109-dpo-ex-67242-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.43it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.91it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.78it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.54it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.46it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.34it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 34.99it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.19it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.22it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.28it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 24.71it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 27.94it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.29it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.09it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.43it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.41it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.02it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.32it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.48it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.14it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.24it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.49it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.20it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.52it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 24.68it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:09, 24.92it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 24.72it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.68it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.21it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.62it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.20it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.18it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.94it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.59it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.61it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:08, 24.30it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 21.92it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:07, 26.72it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 23.92it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.17it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.60it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.87it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.62it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.04it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:06,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:34,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:32,  1.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.80it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.99it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:22,  6.07it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.55it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.83it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:09, 13.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 15.37it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 17.40it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:06, 19.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:24<00:05, 21.34it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 21.84it/s]
Loading 0:  70%|██████▉   | 254/363 [00:25<00:04, 26.05it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.25it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:03, 25.90it/s]
Loading 0:  73%|███████▎  | 266/363 [00:25<00:03, 28.89it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:05, 17.32it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 20.34it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:04, 21.19it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 23.98it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 22.03it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 26.36it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 23.76it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 26.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 23.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.29it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.28it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.44it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 25.12it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 22.73it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 27.96it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.80it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.48it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 25.78it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 20.95it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.43it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 24.80it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 23.31it/s]
                                                            
Job chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer completed after 157.15s with status: succeeded
Stopping job with name chaiml-gy-exp109-dpo-ex-67242-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.68s
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-gy-exp109-dpo-ex-67242-v1
Waiting for inference service chaiml-gy-exp109-dpo-ex-67242-v1 to be ready
Inference service chaiml-gy-exp109-dpo-ex-67242-v1 ready after 190.66136813163757s
Pipeline stage MKMLDeployer completed in 191.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4985551834106445s
Received healthy response to inference request in 2.1421849727630615s
Received healthy response to inference request in 1.859929084777832s
Received healthy response to inference request in 2.703537702560425s
Received healthy response to inference request in 2.1315412521362305s
5 requests
0 failed requests
5th percentile: 1.9142515182495117
10th percentile: 1.9685739517211913
20th percentile: 2.0772188186645506
30th percentile: 2.1336699962615966
40th percentile: 2.1379274845123293
50th percentile: 2.1421849727630615
60th percentile: 2.2847330570220947
70th percentile: 2.427281141281128
80th percentile: 2.5395516872406008
90th percentile: 2.621544694900513
95th percentile: 2.6625411987304686
99th percentile: 2.6953384017944337
mean time: 2.267149639129639
Pipeline stage StressChecker completed in 12.71s
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 0.80s
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
chaiml-gy-exp109-dpo-ex_67242_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 5385.40s
Shutdown handler de-registered
chaiml-gy-exp109-dpo-ex_67242_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp109-dpo-ex_67242_v1 status is now torndown due to DeploymentManager action