chaiml-gy-exp73-dpo-exp_59050

developer_uid: bogoconic1

submission_id: chaiml-gy-exp73-dpo-exp_59050_v1

model_name: chaiml-gy-exp73-dpo-exp_59050_v1

model_group: ChaiML/gy-exp73-dpo-exp3

status: torndown

timestamp: 2025-07-03T16:08:52+00:00

num_battles: 8870

num_wins: 4815

celo_rating: 1314.36

family_friendly_score: 0.45920000000000005

family_friendly_standard_error: 0.007047486927976525

submission_type: basic

model_repo: ChaiML/gy-exp73-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-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': 0.5140815045278347, 'latency_mean': 1.945089955329895, 'latency_p50': 1.9557374715805054, 'latency_p90': 2.1474801301956177}, {'batch_size': 3, 'throughput': 1.0519167218316536, 'latency_mean': 2.835909914970398, 'latency_p50': 2.814099073410034, 'latency_p90': 3.1430089235305787}, {'batch_size': 5, 'throughput': 1.338134779114327, 'latency_mean': 3.730414286851883, 'latency_p50': 3.74215030670166, 'latency_p90': 4.1490964651107785}, {'batch_size': 6, 'throughput': 1.443476455150981, 'latency_mean': 4.133417552709579, 'latency_p50': 4.124613404273987, 'latency_p90': 4.617749571800232}, {'batch_size': 8, 'throughput': 1.567544965275771, 'latency_mean': 5.062347222566604, 'latency_p50': 5.056143164634705, 'latency_p90': 5.681760954856872}, {'batch_size': 10, 'throughput': 1.6518070207311881, 'latency_mean': 5.991171375513077, 'latency_p50': 6.003482699394226, 'latency_p90': 6.635066223144531}]

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

display_name: chaiml-gy-exp73-dpo-exp_59050_v1

is_internal_developer: True

language_model: ChaiML/gy-exp73-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-03

win_ratio: 0.5428410372040586

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-exp73-dpo-exp-59050-v1-mkmlizer
Waiting for job on chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer to finish
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: Downloaded to shared memory in 82.912s
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: Checking if ChaiML/gy-exp73-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep1 already exists in ChaiML
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpng2_ucqj, device:0
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: quantized model in 48.702s
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: Processed model ChaiML/gy-exp73-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-ep1 in 131.614s
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/config.json
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/special_tokens_map.json
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/tokenizer_config.json
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/tokenizer.json
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp73-dpo-exp-59050-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 32.20it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 25.97it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.29it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.12it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.01it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.79it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 32.35it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.13it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.41it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.62it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.71it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.38it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 23.86it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.85it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 25.13it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.93it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.35it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.53it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 25.98it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.06it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.13it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.15it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.82it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 26.24it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.22it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.39it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.44it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.08it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.95it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.36it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.43it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.79it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.31it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 20.95it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.83it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.02it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.47it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 21.97it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:07, 26.69it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 23.33it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.52it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.27it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.21it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.47it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.47it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.69it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:10,  2.14it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.04it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.15it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.15it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.63it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.97it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 15.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 17.02it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.09it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.63it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.61it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.01it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.55it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.49it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 20.82it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 21.43it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.49it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.71it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 24.06it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 29.17it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 27.40it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.97it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.78it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.55it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.40it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.51it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 27.06it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.12it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 26.95it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 27.95it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:01, 24.84it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 14.03it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 19.24it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 19.98it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 24.18it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 21.82it/s]
Loading 0: 100%|█████████▉| 362/363 [00:29<00:00, 25.35it/s]
                                                            
Job chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer completed after 167.38s with status: succeeded
Stopping job with name chaiml-gy-exp73-dpo-exp-59050-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp73-dpo-exp-59050-v1
Waiting for inference service chaiml-gy-exp73-dpo-exp-59050-v1 to be ready
Inference service chaiml-gy-exp73-dpo-exp-59050-v1 ready after 210.94425797462463s
Pipeline stage MKMLDeployer completed in 211.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5748629570007324s
Received healthy response to inference request in 2.2233455181121826s
Received healthy response to inference request in 2.0565807819366455s
Received healthy response to inference request in 1.8498597145080566s
Received healthy response to inference request in 2.3747787475585938s
5 requests
0 failed requests
5th percentile: 1.8912039279937745
10th percentile: 1.9325481414794923
20th percentile: 2.015236568450928
30th percentile: 2.089933729171753
40th percentile: 2.1566396236419676
50th percentile: 2.2233455181121826
60th percentile: 2.2839188098907472
70th percentile: 2.3444921016693114
80th percentile: 2.4147955894470217
90th percentile: 2.494829273223877
95th percentile: 2.5348461151123045
99th percentile: 2.5668595886230468
mean time: 2.215885543823242
Pipeline stage StressChecker completed in 12.76s
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 0.77s
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 0.77s
Shutdown handler de-registered
chaiml-gy-exp73-dpo-exp_59050_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4050.25s
Shutdown handler de-registered
chaiml-gy-exp73-dpo-exp_59050_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp73-dpo-exp_59050_v1 status is now torndown due to DeploymentManager action