chaiml-gy-exp93-dpo-exp_94626

developer_uid: bogoconic1

submission_id: chaiml-gy-exp93-dpo-exp_94626_v1

model_name: chaiml-gy-exp93-dpo-exp_94626_v1

model_group: ChaiML/gy-exp93-dpo-exp8

status: torndown

timestamp: 2025-07-06T08:11:29+00:00

num_battles: 6591

num_wins: 3565

celo_rating: 1317.84

family_friendly_score: 0.48740000000000006

family_friendly_standard_error: 0.007068822249851809

submission_type: basic

model_repo: ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5110249413932422, 'latency_mean': 1.956723268032074, 'latency_p50': 1.9832639694213867, 'latency_p90': 2.1533394575119016}, {'batch_size': 3, 'throughput': 1.0401780277765014, 'latency_mean': 2.8716877102851868, 'latency_p50': 2.855254292488098, 'latency_p90': 3.1942140579223635}, {'batch_size': 5, 'throughput': 1.3284342241076028, 'latency_mean': 3.749876248836517, 'latency_p50': 3.7592400312423706, 'latency_p90': 4.232849740982056}, {'batch_size': 6, 'throughput': 1.4253815516833952, 'latency_mean': 4.180406532287598, 'latency_p50': 4.203160762786865, 'latency_p90': 4.627499747276306}, {'batch_size': 8, 'throughput': 1.554312878474181, 'latency_mean': 5.09680965423584, 'latency_p50': 5.118606090545654, 'latency_p90': 5.6143388748168945}, {'batch_size': 10, 'throughput': 1.6374403416291556, 'latency_mean': 6.039035141468048, 'latency_p50': 6.080843687057495, 'latency_p90': 6.787052249908447}]

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

display_name: chaiml-gy-exp93-dpo-exp_94626_v1

is_internal_developer: True

language_model: ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-06

win_ratio: 0.5408890911849492

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-exp93-dpo-exp-94626-v1-mkmlizer
Waiting for job on chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer to finish
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: Downloaded to shared memory in 74.449s
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: Checking if ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep2 already exists in ChaiML
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkt45ze52, device:0
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: quantized model in 50.495s
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: Processed model ChaiML/gy-exp93-dpo-exp86ep8s2-grok-payloads-0705-rm512-win-ep2 in 124.945s
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/config.json
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/special_tokens_map.json
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/tokenizer_config.json
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/tokenizer.json
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp93-dpo-exp-94626-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.98it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.79it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.59it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 21.70it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.94it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 25.89it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:14, 24.05it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 25.42it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.47it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:18, 17.33it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 20.22it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.41it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 22.28it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 23.28it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 22.82it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 26.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 22.33it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.93it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 28.16it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 19.64it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 20.57it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 23.00it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 22.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.27it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:13, 20.18it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 26.30it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.29it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.07it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.70it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.98it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 26.20it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 23.17it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.03it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.13it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.10it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 25.54it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 24.61it/s]
Loading 0:  40%|████      | 146/363 [00:06<00:07, 28.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 21.31it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 17.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.10it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.15it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 24.01it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:09, 21.31it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.87it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 25.06it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 24.13it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.11it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 21.60it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 20.06it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.92it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.35it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 21.35it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:18,  1.22s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:42,  1.02s/it]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:36,  1.60it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:14,  2.05it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:55,  2.71it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.88it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.94it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:23,  5.97it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.38it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.75it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:08, 14.59it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 15.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 20.36it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.42it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:04, 24.66it/s]
Loading 0:  71%|███████   | 258/363 [00:26<00:04, 21.86it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:03, 28.53it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 22.40it/s]
Loading 0:  75%|███████▍  | 272/363 [00:26<00:04, 22.50it/s]
Loading 0:  76%|███████▌  | 275/363 [00:27<00:04, 19.51it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 25.66it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 23.49it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 27.96it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 25.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 26.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 24.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 22.19it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 23.02it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 23.15it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 26.40it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 23.56it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.51it/s]
Loading 0:  91%|█████████ | 330/363 [00:29<00:01, 25.23it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 27.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:00, 26.06it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.20it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 20.32it/s]
Loading 0:  96%|█████████▌| 349/363 [00:30<00:00, 19.47it/s]
Loading 0:  97%|█████████▋| 353/363 [00:30<00:00, 22.89it/s]
Loading 0:  98%|█████████▊| 356/363 [00:30<00:00, 24.32it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 24.17it/s]
                                                            
Job chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer completed after 157.32s with status: succeeded
Stopping job with name chaiml-gy-exp93-dpo-exp-94626-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.81s
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-exp93-dpo-exp-94626-v1
Waiting for inference service chaiml-gy-exp93-dpo-exp-94626-v1 to be ready
Inference service chaiml-gy-exp93-dpo-exp-94626-v1 ready after 210.824134349823s
Pipeline stage MKMLDeployer completed in 211.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9334428310394287s
Received healthy response to inference request in 2.125023365020752s
Received healthy response to inference request in 2.006526470184326s
Received healthy response to inference request in 2.4485514163970947s
Received healthy response to inference request in 2.1018526554107666s
5 requests
0 failed requests
5th percentile: 2.0255917072296143
10th percentile: 2.0446569442749025
20th percentile: 2.0827874183654784
30th percentile: 2.1064867973327637
40th percentile: 2.115755081176758
50th percentile: 2.125023365020752
60th percentile: 2.254434585571289
70th percentile: 2.383845806121826
80th percentile: 2.5455296993255616
90th percentile: 2.739486265182495
95th percentile: 2.836464548110962
99th percentile: 2.9140471744537355
mean time: 2.3230793476104736
Pipeline stage StressChecker completed in 13.11s
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 0.55s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp93-dpo-exp_94626_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3195.22s
Shutdown handler de-registered
chaiml-gy-exp93-dpo-exp_94626_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp93-dpo-exp_94626_v1 status is now torndown due to DeploymentManager action