chaiml-gy-exp157-dpo-ex_37526

developer_uid: bogoconic1

submission_id: chaiml-gy-exp157-dpo-ex_37526_v1

model_name: chaiml-gy-exp157-dpo-ex_37526_v1

model_group: ChaiML/gy-exp157-dpo-exp

status: torndown

timestamp: 2025-07-12T16:32:14+00:00

num_battles: 10844

num_wins: 5747

celo_rating: 1309.3

family_friendly_score: 0.49160000000000004

family_friendly_standard_error: 0.007070069872356284

submission_type: basic

model_repo: ChaiML/gy-exp157-dpo-exp146ep2s3-gy-datamix-v5-bo8-head4000-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': 0.5259949044206013, 'latency_mean': 1.9010615313053132, 'latency_p50': 1.8910938501358032, 'latency_p90': 2.12440505027771}, {'batch_size': 3, 'throughput': 1.0510108189586866, 'latency_mean': 2.8410411190986635, 'latency_p50': 2.8539867401123047, 'latency_p90': 3.13198344707489}, {'batch_size': 5, 'throughput': 1.349603202782352, 'latency_mean': 3.6800830364227295, 'latency_p50': 3.6537699699401855, 'latency_p90': 4.096603035926819}, {'batch_size': 6, 'throughput': 1.4586270126002816, 'latency_mean': 4.087881591320038, 'latency_p50': 4.093137145042419, 'latency_p90': 4.653304576873779}, {'batch_size': 8, 'throughput': 1.587956054430484, 'latency_mean': 5.003625512123108, 'latency_p50': 5.042191863059998, 'latency_p90': 5.6251218795776365}, {'batch_size': 10, 'throughput': 1.6821165365238704, 'latency_mean': 5.883393559455872, 'latency_p50': 5.862265467643738, 'latency_p90': 6.6579328060150145}]

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

display_name: chaiml-gy-exp157-dpo-ex_37526_v1

is_internal_developer: False

language_model: ChaiML/gy-exp157-dpo-exp146ep2s3-gy-datamix-v5-bo8-head4000-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-12

win_ratio: 0.5299704905938768

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_start|>', '<|im_end|>', '\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-exp157-dpo-ex-37526-v1-mkmlizer
Waiting for job on chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer to finish
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: Downloaded to shared memory in 78.156s
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: Checking if ChaiML/gy-exp157-dpo-exp146ep2s3-gy-datamix-v5-bo8-head4000-ep2 already exists in ChaiML
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6wjriz8_, device:0
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: quantized model in 47.387s
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: Processed model ChaiML/gy-exp157-dpo-exp146ep2s3-gy-datamix-v5-bo8-head4000-ep2 in 125.543s
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/config.json
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/special_tokens_map.json
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/tokenizer_config.json
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/tokenizer.json
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp157-dpo-ex-37526-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.55it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.57it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.08it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.34it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.95it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.06it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.69it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.42it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.10it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.47it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.56it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.85it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.37it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.16it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.98it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.81it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.89it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.67it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.14it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.87it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.11it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 26.72it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.29it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.16it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 24.75it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.27it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.75it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.65it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.75it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.01it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.52it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:09, 23.28it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:08, 23.57it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:10, 19.76it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.80it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:09, 21.51it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 26.37it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:08, 22.68it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.39it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.62it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.82it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.52it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.49it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.49it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:55,  1.08s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:25,  1.10it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:28,  1.76it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.23it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.93it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.16it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.28it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.34it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.33it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.06it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.96it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.61it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.36it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.64it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 30.47it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 20.92it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.50it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.38it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.20it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.52it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.54it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.37it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.56it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.20it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.17it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.95it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.20it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.35it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.33it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.72it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.09it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.35it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.83it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.32it/s]
Loading 0:  95%|█████████▌| 346/363 [00:27<00:00, 20.58it/s]
Loading 0:  96%|█████████▌| 349/363 [00:27<00:00, 19.55it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 23.30it/s]
Loading 0:  98%|█████████▊| 357/363 [00:28<00:00, 21.73it/s]
                                                            
Job chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer completed after 156.93s with status: succeeded
Stopping job with name chaiml-gy-exp157-dpo-ex-37526-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.45s
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-exp157-dpo-ex-37526-v1
Waiting for inference service chaiml-gy-exp157-dpo-ex-37526-v1 to be ready
Inference service chaiml-gy-exp157-dpo-ex-37526-v1 ready after 211.00331497192383s
Pipeline stage MKMLDeployer completed in 211.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8637638092041016s
Received healthy response to inference request in 2.283475399017334s
Received healthy response to inference request in 2.0221636295318604s
Received healthy response to inference request in 1.8277137279510498s
Received healthy response to inference request in 1.968942642211914s
5 requests
0 failed requests
5th percentile: 1.8559595108032227
10th percentile: 1.8842052936553955
20th percentile: 1.9406968593597411
30th percentile: 1.9795868396759033
40th percentile: 2.000875234603882
50th percentile: 2.0221636295318604
60th percentile: 2.12668833732605
70th percentile: 2.2312130451202394
80th percentile: 2.3995330810546878
90th percentile: 2.6316484451293944
95th percentile: 2.747706127166748
99th percentile: 2.840552272796631
mean time: 2.1932118415832518
Pipeline stage StressChecker completed in 12.34s
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 0.74s
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 0.97s
Shutdown handler de-registered
chaiml-gy-exp157-dpo-ex_37526_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
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 5770.33s
Shutdown handler de-registered
chaiml-gy-exp157-dpo-ex_37526_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp157-dpo-ex_37526_v1 status is now torndown due to DeploymentManager action