chaiml-gy-exp64-dpo-exp_75938

developer_uid: bogoconic1

submission_id: chaiml-gy-exp64-dpo-exp_75938_v1

model_name: chaiml-gy-exp64-dpo-exp_75938_v1

model_group: ChaiML/gy-exp64-dpo-exp3

status: torndown

timestamp: 2025-07-02T20:28:25+00:00

num_battles: 8576

num_wins: 4498

celo_rating: 1301.46

family_friendly_score: 0.5216000000000001

family_friendly_standard_error: 0.007064466575757862

submission_type: basic

model_repo: ChaiML/gy-exp64-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5163094475189514, 'latency_mean': 1.9367112565040587, 'latency_p50': 1.9411627054214478, 'latency_p90': 2.1206760168075562}, {'batch_size': 3, 'throughput': 1.0448387918761506, 'latency_mean': 2.8605804586410524, 'latency_p50': 2.8561933040618896, 'latency_p90': 3.144045329093933}, {'batch_size': 5, 'throughput': 1.3290598021188915, 'latency_mean': 3.742816607952118, 'latency_p50': 3.7321380376815796, 'latency_p90': 4.177770042419434}, {'batch_size': 6, 'throughput': 1.4232056612334338, 'latency_mean': 4.187031180858612, 'latency_p50': 4.215858697891235, 'latency_p90': 4.666751766204834}, {'batch_size': 8, 'throughput': 1.54879317054906, 'latency_mean': 5.116418002843857, 'latency_p50': 5.202956914901733, 'latency_p90': 5.7653618335723875}, {'batch_size': 10, 'throughput': 1.6423221893619093, 'latency_mean': 6.028208727836609, 'latency_p50': 6.028277635574341, 'latency_p90': 6.819667410850525}]

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

display_name: chaiml-gy-exp64-dpo-exp_75938_v1

is_internal_developer: True

language_model: ChaiML/gy-exp64-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-02

win_ratio: 0.5244869402985075

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-exp64-dpo-exp-75938-v1-mkmlizer
Waiting for job on chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer to finish
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Version: 0.29.8                                                    ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: Downloaded to shared memory in 79.006s
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: Checking if ChaiML/gy-exp64-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1 already exists in ChaiML
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi7r03znc, device:0
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: quantized model in 48.399s
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: Processed model ChaiML/gy-exp64-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1 in 127.406s
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/config.json
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/special_tokens_map.json
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/tokenizer_config.json
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/tokenizer.json
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp64-dpo-exp-75938-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 30.80it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 25.19it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.61it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.31it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 28.53it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.57it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.75it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 21.06it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 20.25it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 21.48it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.45it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.89it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.98it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.76it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.82it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.23it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.43it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 20.19it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.59it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.55it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.72it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.61it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.39it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 26.81it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 23.69it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.79it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.73it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.43it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.50it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.00it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.99it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.42it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.53it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.57it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.33it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.46it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.36it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.27it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 25.31it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.46it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.84it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.24it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:02,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.17it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.85it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.09it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.22it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.18it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.12it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.84it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.76it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.54it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.65it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.31it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.45it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.69it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 21.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 20.23it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.18it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.96it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.64it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.87it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.75it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.95it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.08it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.96it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.42it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.31it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 27.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.24it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 28.83it/s]
Loading 0:  94%|█████████▍| 342/363 [00:28<00:01, 16.33it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.25it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.42it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.92it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 24.76it/s]
                                                            
Job chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer completed after 155.63s with status: succeeded
Stopping job with name chaiml-gy-exp64-dpo-exp-75938-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.16s
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-exp64-dpo-exp-75938-v1
Waiting for inference service chaiml-gy-exp64-dpo-exp-75938-v1 to be ready
Inference service chaiml-gy-exp64-dpo-exp-75938-v1 ready after 210.8035216331482s
Pipeline stage MKMLDeployer completed in 211.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.179596662521362s
Received healthy response to inference request in 2.3116936683654785s
Received healthy response to inference request in 2.0903820991516113s
Received healthy response to inference request in 1.9043798446655273s
Received healthy response to inference request in 2.2564404010772705s
5 requests
0 failed requests
5th percentile: 1.9415802955627441
10th percentile: 1.978780746459961
20th percentile: 2.0531816482543945
30th percentile: 2.1235937595367433
40th percentile: 2.190017080307007
50th percentile: 2.2564404010772705
60th percentile: 2.2785417079925536
70th percentile: 2.3006430149078367
80th percentile: 2.6852742671966556
90th percentile: 3.432435464859009
95th percentile: 3.806016063690185
99th percentile: 4.104880542755127
mean time: 2.54849853515625
Pipeline stage StressChecker completed in 14.33s
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 0.76s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp64-dpo-exp_75938_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp64-dpo-exp-75938-v1-profiler
Waiting for inference service chaiml-gy-exp64-dpo-exp-75938-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 5477.52s
Shutdown handler de-registered
chaiml-gy-exp64-dpo-exp_75938_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp64-dpo-exp_75938_v1 status is now torndown due to DeploymentManager action