chaiml-gy-exp114-dpo-ex_38865

developer_uid: bogoconic1

submission_id: chaiml-gy-exp114-dpo-ex_38865_v1

model_name: chaiml-gy-exp114-dpo-ex_38865_v1

model_group: ChaiML/gy-exp114-dpo-exp

status: torndown

timestamp: 2025-07-07T20:57:06+00:00

num_battles: 6623

num_wins: 3214

celo_rating: 1278.01

family_friendly_score: 0.602

family_friendly_standard_error: 0.006922369536509879

submission_type: basic

model_repo: ChaiML/gy-exp114-dpo-exp112ep2s3-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': 0.504961834309923, 'latency_mean': 1.9802446365356445, 'latency_p50': 1.9674246311187744, 'latency_p90': 2.2189783811569215}, {'batch_size': 3, 'throughput': 0.9823412990067235, 'latency_mean': 3.048223824501038, 'latency_p50': 3.05570650100708, 'latency_p90': 3.3925098419189452}, {'batch_size': 5, 'throughput': 1.2161443599875266, 'latency_mean': 4.094708415269852, 'latency_p50': 4.086201786994934, 'latency_p90': 4.559034967422486}, {'batch_size': 6, 'throughput': 1.3105825178460928, 'latency_mean': 4.547571240663529, 'latency_p50': 4.599775314331055, 'latency_p90': 5.006037998199463}, {'batch_size': 8, 'throughput': 1.4187979395013, 'latency_mean': 5.602613899707794, 'latency_p50': 5.653313159942627, 'latency_p90': 6.217739701271057}, {'batch_size': 10, 'throughput': 1.4625686206925248, 'latency_mean': 6.773170754909516, 'latency_p50': 6.768436908721924, 'latency_p90': 7.645680785179138}]

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

display_name: chaiml-gy-exp114-dpo-ex_38865_v1

is_internal_developer: False

language_model: ChaiML/gy-exp114-dpo-exp112ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.15

us_pacific_date: 2025-07-07

win_ratio: 0.4852785746640495

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-exp114-dpo-ex-38865-v1-mkmlizer
Waiting for job on chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer to finish
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: Downloaded to shared memory in 83.290s
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: Checking if ChaiML/gy-exp114-dpo-exp112ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpydn4q187, device:0
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: quantized model in 50.299s
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: Processed model ChaiML/gy-exp114-dpo-exp112ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 133.589s
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/config.json
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/special_tokens_map.json
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/tokenizer_config.json
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/tokenizer.json
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp114-dpo-ex-38865-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.43it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.59it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.55it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 26.78it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.24it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.30it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 32.69it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 21.78it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 20.47it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 21.52it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 21.43it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 24.99it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.72it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 27.96it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.38it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 27.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.69it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 20.06it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.02it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.86it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.33it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.75it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.67it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 25.11it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.56it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.72it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.33it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.78it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.41it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 25.85it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 23.33it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.60it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.13it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.26it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 24.76it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.59it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:08, 23.71it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:10, 19.84it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.85it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.58it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.56it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.60it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 27.22it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.34it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.67it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.70it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.79it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.64it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.56it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 22.56it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:11,  1.18s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:38,  1.01it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:35,  1.63it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:13,  2.08it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:54,  2.73it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.90it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.92it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.29it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.59it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:08, 14.26it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 14.83it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 19.75it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:06, 18.92it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 23.47it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 21.06it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 27.49it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 21.36it/s]
Loading 0:  75%|███████▍  | 271/363 [00:26<00:04, 20.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 21.36it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:04, 21.38it/s]
Loading 0:  77%|███████▋  | 280/363 [00:26<00:03, 22.33it/s]
Loading 0:  78%|███████▊  | 283/363 [00:26<00:03, 23.28it/s]
Loading 0:  79%|███████▉  | 286/363 [00:27<00:03, 23.39it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 26.66it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:02, 23.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 25.70it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 23.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 21.32it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 22.34it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 22.41it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 25.85it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 23.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.76it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.17it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 27.73it/s]
Loading 0:  93%|█████████▎| 337/363 [00:29<00:01, 22.59it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.13it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 20.24it/s]
Loading 0:  96%|█████████▌| 349/363 [00:29<00:00, 19.36it/s]
Loading 0:  97%|█████████▋| 353/363 [00:30<00:00, 22.81it/s]
Loading 0:  98%|█████████▊| 357/363 [00:30<00:00, 21.80it/s]
                                                            
Job chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer completed after 167.15s with status: succeeded
Stopping job with name chaiml-gy-exp114-dpo-ex-38865-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp114-dpo-ex-38865-v1
Waiting for inference service chaiml-gy-exp114-dpo-ex-38865-v1 to be ready
Inference service chaiml-gy-exp114-dpo-ex-38865-v1 ready after 180.7046775817871s
Pipeline stage MKMLDeployer completed in 181.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6872434616088867s
Received healthy response to inference request in 2.197849988937378s
Received healthy response to inference request in 2.2792270183563232s
Received healthy response to inference request in 2.383239507675171s
Received healthy response to inference request in 2.4078052043914795s
5 requests
0 failed requests
5th percentile: 2.214125394821167
10th percentile: 2.230400800704956
20th percentile: 2.262951612472534
30th percentile: 2.3000295162200928
40th percentile: 2.341634511947632
50th percentile: 2.383239507675171
60th percentile: 2.3930657863616944
70th percentile: 2.402892065048218
80th percentile: 2.463692855834961
90th percentile: 2.575468158721924
95th percentile: 2.631355810165405
99th percentile: 2.67606593132019
mean time: 2.3910730361938475
Pipeline stage StressChecker completed in 13.39s
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 0.65s
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-exp114-dpo-ex_38865_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp114-dpo-ex-38865-v1-profiler
Waiting for inference service chaiml-gy-exp114-dpo-ex-38865-v1-profiler to be ready
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 9379.84s
Shutdown handler de-registered
chaiml-gy-exp114-dpo-ex_38865_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp114-dpo-ex_38865_v1 status is now torndown due to DeploymentManager action