chaiml-gy-exp120-dpo-ex_31713

developer_uid: bogoconic1

submission_id: chaiml-gy-exp120-dpo-ex_31713_v4

model_name: chaiml-gy-exp120-dpo-ex_31713_v4

model_group: ChaiML/gy-exp120-dpo-exp

status: torndown

timestamp: 2025-07-12T07:40:50+00:00

num_battles: 9147

num_wins: 4886

celo_rating: 1318.3

family_friendly_score: 0.4658

family_friendly_standard_error: 0.007054507211705152

submission_type: basic

model_repo: ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-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': 0.5231141234064713, 'latency_mean': 1.9115301585197448, 'latency_p50': 1.907309651374817, 'latency_p90': 2.133798432350159}, {'batch_size': 3, 'throughput': 1.055542076321234, 'latency_mean': 2.830419720411301, 'latency_p50': 2.8285820484161377, 'latency_p90': 3.1179095983505247}, {'batch_size': 5, 'throughput': 1.3491418676389193, 'latency_mean': 3.6857489728927613, 'latency_p50': 3.6923694610595703, 'latency_p90': 4.084538006782531}, {'batch_size': 6, 'throughput': 1.4544775699741173, 'latency_mean': 4.094751229286194, 'latency_p50': 4.0751543045043945, 'latency_p90': 4.5940666675567625}, {'batch_size': 8, 'throughput': 1.5881940259610272, 'latency_mean': 4.993268966674805, 'latency_p50': 4.995826959609985, 'latency_p90': 5.681581687927246}, {'batch_size': 10, 'throughput': 1.6735988799495167, 'latency_mean': 5.9208272469043735, 'latency_p50': 5.886853456497192, 'latency_p90': 6.633281540870667}]

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

display_name: chaiml-gy-exp120-dpo-ex_31713_v4

is_internal_developer: False

language_model: ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-12

win_ratio: 0.534164206843774

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|>', '<|im_start|>', '\n'], '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-exp120-dpo-ex-31713-v4-mkmlizer
Waiting for job on chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer to finish
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: Downloaded to shared memory in 51.737s
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: Checking if ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg0jhd55w, device:0
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: quantized model in 47.751s
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: Processed model ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 99.488s
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/config.json
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/special_tokens_map.json
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/tokenizer_config.json
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/tokenizer.json
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v4/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.16it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.54it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.74it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.35it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.75it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.55it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 21.89it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.58it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.06it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.56it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 24.11it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.09it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.69it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.04it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.88it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.87it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.07it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.22it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.97it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.59it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.39it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.03it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.04it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.02it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.81it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.61it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.14it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.10it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.22it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.52it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.34it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.68it/s]
Loading 0:  40%|████      | 146/363 [00:05<00:07, 30.76it/s]
Loading 0:  41%|████▏     | 150/363 [00:05<00:08, 23.82it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:10, 20.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.72it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.29it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.40it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 26.78it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:06, 27.04it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:07, 26.36it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.43it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.35it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.17it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.50it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.01it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:07, 23.01it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:05,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.87it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.10it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.23it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.21it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.19it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.75it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:08, 15.34it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.32it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.65it/s]
Loading 0:  70%|██████▉   | 253/363 [00:24<00:04, 22.80it/s]
Loading 0:  71%|███████   | 256/363 [00:24<00:04, 23.92it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 23.53it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 28.84it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 21.39it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 20.54it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.95it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.61it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.83it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.59it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.68it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.71it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.99it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.11it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.06it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.49it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.19it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.08it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.81it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.71it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.41it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.51it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.06it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 22.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:28<00:00, 21.00it/s]
                                                            
Job chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer completed after 125.7s with status: succeeded
Stopping job with name chaiml-gy-exp120-dpo-ex-31713-v4-mkmlizer
Pipeline stage MKMLizer completed in 126.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp120-dpo-ex-31713-v4
Waiting for inference service chaiml-gy-exp120-dpo-ex-31713-v4 to be ready
Inference service chaiml-gy-exp120-dpo-ex-31713-v4 ready after 200.82676768302917s
Pipeline stage MKMLDeployer completed in 201.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.472374677658081s
Received healthy response to inference request in 1.9526851177215576s
Received healthy response to inference request in 2.126390218734741s
Received healthy response to inference request in 2.162139415740967s
Received healthy response to inference request in 1.892981767654419s
5 requests
0 failed requests
5th percentile: 1.9049224376678466
10th percentile: 1.9168631076812743
20th percentile: 1.94074444770813
30th percentile: 1.9874261379241944
40th percentile: 2.0569081783294676
50th percentile: 2.126390218734741
60th percentile: 2.1406898975372313
70th percentile: 2.1549895763397218
80th percentile: 2.22418646812439
90th percentile: 2.3482805728912353
95th percentile: 2.410327625274658
99th percentile: 2.4599652671813965
mean time: 2.1213142395019533
Pipeline stage StressChecker completed in 11.95s
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 0.70s
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 0.63s
Shutdown handler de-registered
chaiml-gy-exp120-dpo-ex_31713_v4 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 4972.96s
Shutdown handler de-registered
chaiml-gy-exp120-dpo-ex_31713_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp120-dpo-ex_31713_v4 status is now torndown due to DeploymentManager action