chaiml-gy-exp101-dpo-ex_11693

developer_uid: bogoconic1

submission_id: chaiml-gy-exp101-dpo-ex_11693_v1

model_name: chaiml-gy-exp101-dpo-ex_11693_v1

model_group: ChaiML/gy-exp101-dpo-exp

status: torndown

timestamp: 2025-07-06T19:18:27+00:00

num_battles: 6479

num_wins: 3357

celo_rating: 1302.25

family_friendly_score: 0.5122

family_friendly_standard_error: 0.007068962583010325

submission_type: basic

model_repo: ChaiML/gy-exp101-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-diff-gt0.05-ep1

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': 0.5226954948154593, 'latency_mean': 1.913040248155594, 'latency_p50': 1.9056408405303955, 'latency_p90': 2.1405229806900024}, {'batch_size': 3, 'throughput': 1.0618757817917857, 'latency_mean': 2.823092030286789, 'latency_p50': 2.8335788249969482, 'latency_p90': 3.123777675628662}, {'batch_size': 5, 'throughput': 1.336383361072191, 'latency_mean': 3.7197930932044985, 'latency_p50': 3.7202229499816895, 'latency_p90': 4.212533926963806}, {'batch_size': 6, 'throughput': 1.431400848644855, 'latency_mean': 4.1668298316001895, 'latency_p50': 4.189104080200195, 'latency_p90': 4.676027822494507}, {'batch_size': 8, 'throughput': 1.5607404104067242, 'latency_mean': 5.080975042581558, 'latency_p50': 5.053588032722473, 'latency_p90': 5.705024099349975}, {'batch_size': 10, 'throughput': 1.6501015273930717, 'latency_mean': 6.000669238567352, 'latency_p50': 5.99019467830658, 'latency_p90': 6.842428302764892}]

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

display_name: chaiml-gy-exp101-dpo-ex_11693_v1

is_internal_developer: False

language_model: ChaiML/gy-exp101-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-diff-gt0.05-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-06

win_ratio: 0.518135514739929

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-exp101-dpo-ex-11693-v1-mkmlizer
Waiting for job on chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer to finish
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: Downloaded to shared memory in 82.506s
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: Checking if ChaiML/gy-exp101-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-diff-gt0.05-ep1 already exists in ChaiML
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoooob6tn, device:0
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: quantized model in 47.681s
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: Processed model ChaiML/gy-exp101-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-diff-gt0.05-ep1 in 130.188s
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/config.json
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/special_tokens_map.json
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/tokenizer_config.json
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/tokenizer.json
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp101-dpo-ex-11693-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.30it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.40it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.88it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.98it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.49it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.86it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 32.74it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 23.72it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:14, 22.13it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.53it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 24.10it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.87it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:12, 24.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.10it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.09it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.38it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.06it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.32it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.85it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.86it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.75it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.42it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.23it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.46it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 26.17it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.28it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 25.05it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 23.98it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.40it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.24it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.17it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.86it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.68it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.44it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.25it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.85it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.13it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.56it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.94it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.45it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.19it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.43it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.69it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.34it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.30it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.66it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.88it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.13it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.33it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.32it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.10it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.13it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.84it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.05it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:04, 22.95it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 26.77it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:03, 26.35it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.91it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:03, 23.99it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.60it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.62it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.29it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.76it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.37it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.71it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.20it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.56it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.83it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.19it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 23.95it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.14it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.76it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.00it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.54it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.50it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 20.90it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 21.83it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.18it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.61it/s]
                                                            
Job chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer completed after 166.94s with status: succeeded
Stopping job with name chaiml-gy-exp101-dpo-ex-11693-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp101-dpo-ex-11693-v1
Waiting for inference service chaiml-gy-exp101-dpo-ex-11693-v1 to be ready
Inference service chaiml-gy-exp101-dpo-ex-11693-v1 ready after 211.13836789131165s
Pipeline stage MKMLDeployer completed in 211.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5234487056732178s
Received healthy response to inference request in 2.1974740028381348s
Received healthy response to inference request in 1.8712120056152344s
Received healthy response to inference request in 2.221290111541748s
Received healthy response to inference request in 2.410442590713501s
5 requests
0 failed requests
5th percentile: 1.9364644050598145
10th percentile: 2.0017168045043947
20th percentile: 2.1322216033935546
30th percentile: 2.2022372245788575
40th percentile: 2.2117636680603026
50th percentile: 2.221290111541748
60th percentile: 2.296951103210449
70th percentile: 2.3726120948791505
80th percentile: 2.4330438137054444
90th percentile: 2.478246259689331
95th percentile: 2.5008474826812743
99th percentile: 2.5189284610748293
mean time: 2.2447734832763673
Pipeline stage StressChecker completed in 12.45s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-gy-exp101-dpo-ex_11693_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp101-dpo-ex-11693-v1-profiler
Waiting for inference service chaiml-gy-exp101-dpo-ex-11693-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3380.32s
Shutdown handler de-registered
chaiml-gy-exp101-dpo-ex_11693_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp101-dpo-ex_11693_v1 status is now torndown due to DeploymentManager action