chaiml-gy-exp72-dpo-exp_92617

developer_uid: bogoconic1

submission_id: chaiml-gy-exp72-dpo-exp_92617_v1

model_name: chaiml-gy-exp72-dpo-exp_92617_v1

model_group: ChaiML/gy-exp72-dpo-exp3

status: torndown

timestamp: 2025-07-03T15:05:57+00:00

num_battles: 7369

num_wins: 4043

celo_rating: 1318.29

family_friendly_score: 0.4778

family_friendly_standard_error: 0.007064094563353466

submission_type: basic

model_repo: ChaiML/gy-exp72-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-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': 0.5254753591953062, 'latency_mean': 1.9029133760929107, 'latency_p50': 1.8773608207702637, 'latency_p90': 2.1280832290649414}, {'batch_size': 3, 'throughput': 1.0546107198262578, 'latency_mean': 2.8304879271984102, 'latency_p50': 2.8303020000457764, 'latency_p90': 3.134801411628723}, {'batch_size': 5, 'throughput': 1.330210348020331, 'latency_mean': 3.7361239087581635, 'latency_p50': 3.739652395248413, 'latency_p90': 4.161222815513611}, {'batch_size': 6, 'throughput': 1.4436457808101757, 'latency_mean': 4.129255095720291, 'latency_p50': 4.121601700782776, 'latency_p90': 4.6658695936203}, {'batch_size': 8, 'throughput': 1.5579639405702643, 'latency_mean': 5.088875559568405, 'latency_p50': 5.13127064704895, 'latency_p90': 5.684780597686768}, {'batch_size': 10, 'throughput': 1.6466234368393826, 'latency_mean': 6.008679341077805, 'latency_p50': 5.981862187385559, 'latency_p90': 6.79730875492096}]

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

display_name: chaiml-gy-exp72-dpo-exp_92617_v1

is_internal_developer: True

language_model: ChaiML/gy-exp72-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-03

win_ratio: 0.5486497489482969

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|>', '\n', '<|im_end|>'], '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-exp72-dpo-exp-92617-v1-mkmlizer
Waiting for job on chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer to finish
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: Downloaded to shared memory in 77.703s
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: Checking if ChaiML/gy-exp72-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep2 already exists in ChaiML
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpanqy3j0v, device:0
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: quantized model in 49.034s
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: Processed model ChaiML/gy-exp72-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep2 in 126.738s
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/config.json
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/special_tokens_map.json
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/tokenizer_config.json
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/tokenizer.json
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp72-dpo-exp-92617-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.30it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.55it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.42it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.40it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.33it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.76it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.29it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.88it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.68it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:13, 24.25it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.85it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:13, 23.23it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.24it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.39it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.20it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.39it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.31it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.04it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 22.39it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.11it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.99it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.28it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.09it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.94it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.39it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.85it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.51it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.52it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.29it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 25.89it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.35it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.37it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.68it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 25.09it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.71it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.45it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.37it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.36it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 26.60it/s]
Loading 0:  48%|████▊     | 175/363 [00:06<00:06, 26.98it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:07, 26.00it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 26.93it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.70it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:09, 18.10it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 21.38it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 21.98it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 21.98it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:35,  1.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:33,  1.65it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.12it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.78it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.96it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.05it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.07it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.51it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.91it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.73it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.55it/s]
Loading 0:  67%|██████▋   | 245/363 [00:24<00:05, 20.68it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 19.62it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.50it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.21it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 28.70it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.59it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.29it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.14it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.49it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.70it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.89it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 27.17it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.61it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.83it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.93it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.04it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.14it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 25.68it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 22.95it/s]
Loading 0:  90%|████████▉ | 325/363 [00:27<00:01, 26.55it/s]
Loading 0:  90%|█████████ | 328/363 [00:27<00:01, 26.90it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 25.30it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 26.25it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:01, 24.54it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.28it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.04it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 20.86it/s]
Loading 0:  98%|█████████▊| 354/363 [00:29<00:00, 24.52it/s]
Loading 0:  98%|█████████▊| 357/363 [00:29<00:00, 20.34it/s]
                                                            
Job chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer completed after 156.52s with status: succeeded
Stopping job with name chaiml-gy-exp72-dpo-exp-92617-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.06s
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-exp72-dpo-exp-92617-v1
Waiting for inference service chaiml-gy-exp72-dpo-exp-92617-v1 to be ready
Inference service chaiml-gy-exp72-dpo-exp-92617-v1 ready after 210.83243799209595s
Pipeline stage MKMLDeployer completed in 211.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6160898208618164s
Received healthy response to inference request in 2.372690200805664s
Received healthy response to inference request in 2.1120619773864746s
Received healthy response to inference request in 2.3035364151000977s
Received healthy response to inference request in 2.3871657848358154s
5 requests
0 failed requests
5th percentile: 2.1503568649291993
10th percentile: 2.188651752471924
20th percentile: 2.265241527557373
30th percentile: 2.317367172241211
40th percentile: 2.3450286865234373
50th percentile: 2.372690200805664
60th percentile: 2.3784804344177246
70th percentile: 2.384270668029785
80th percentile: 2.4329505920410157
90th percentile: 2.524520206451416
95th percentile: 2.570305013656616
99th percentile: 2.6069328594207763
mean time: 2.3583088397979735
Pipeline stage StressChecker completed in 13.34s
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 0.69s
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 0.81s
Shutdown handler de-registered
chaiml-gy-exp72-dpo-exp_92617_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 0.13s
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-exp72-dpo-exp-92617-v1-profiler
Waiting for inference service chaiml-gy-exp72-dpo-exp-92617-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 3232.42s
Shutdown handler de-registered
chaiml-gy-exp72-dpo-exp_92617_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp72-dpo-exp_92617_v1 status is now torndown due to DeploymentManager action