developer_uid: bogoconic1
submission_id: chaiml-gy-exp80-dpo-exp_56703_v4
model_name: chaiml-gy-exp80-dpo-exp_56703_v4
model_group: ChaiML/gy-exp80-dpo-exp7
status: torndown
timestamp: 2025-07-04T14:19:15+00:00
num_battles: 9781
num_wins: 5158
celo_rating: 1307.85
family_friendly_score: 0.5242
family_friendly_standard_error: 0.007062780755481512
submission_type: basic
model_repo: ChaiML/gy-exp80-dpo-exp78ep2s2-majib-0630-rm-win-safe-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': 0.5192481595145958, 'latency_mean': 1.9257394182682037, 'latency_p50': 1.9376376867294312, 'latency_p90': 2.136893701553345}, {'batch_size': 3, 'throughput': 1.0497353973177679, 'latency_mean': 2.8501653707027437, 'latency_p50': 2.860832929611206, 'latency_p90': 3.1756332397460936}, {'batch_size': 5, 'throughput': 1.343650759670673, 'latency_mean': 3.696904186010361, 'latency_p50': 3.688671350479126, 'latency_p90': 4.095274615287781}, {'batch_size': 6, 'throughput': 1.4572759568819615, 'latency_mean': 4.088144444227218, 'latency_p50': 4.098011374473572, 'latency_p90': 4.537515783309936}, {'batch_size': 8, 'throughput': 1.5795889687310394, 'latency_mean': 5.024938453435897, 'latency_p50': 5.024475932121277, 'latency_p90': 5.740866661071777}, {'batch_size': 10, 'throughput': 1.6828489816884615, 'latency_mean': 5.892630915641785, 'latency_p50': 5.8886085748672485, 'latency_p90': 6.721925258636475}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp80-dpo-exp_56703_v4
is_internal_developer: True
language_model: ChaiML/gy-exp80-dpo-exp78ep2s2-majib-0630-rm-win-safe-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-07-04
win_ratio: 0.5273489418259891
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-exp80-dpo-exp-56703-v4-mkmlizer
Waiting for job on chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer to finish
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: Downloaded to shared memory in 64.372s
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: Checking if ChaiML/gy-exp80-dpo-exp78ep2s2-majib-0630-rm-win-safe-ep2 already exists in ChaiML
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq7uu1xb9, device:0
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: quantized model in 49.896s
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: Processed model ChaiML/gy-exp80-dpo-exp78ep2s2-majib-0630-rm-win-safe-ep2 in 114.269s
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp80-dpo-exp-56703-v4/nvidia
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp80-dpo-exp-56703-v4/nvidia/special_tokens_map.json
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp80-dpo-exp-56703-v4/nvidia/config.json
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp80-dpo-exp-56703-v4/nvidia/tokenizer_config.json
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp80-dpo-exp-56703-v4/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.79it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.10it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.31it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.27it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 31.36it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.95it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 33.30it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 19.99it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.76it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 23.56it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:13, 23.64it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.80it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.42it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 23.82it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.83it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.24it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.43it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.22it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 22.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.72it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.43it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.25it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.48it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 26.19it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.69it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.88it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.73it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.81it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.28it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.12it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.57it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.83it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.52it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.15it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:08, 23.67it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.04it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.78it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.83it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.63it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.94it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 27.76it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.67it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.10it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.81it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.55it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 22.78it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 22.78it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:12,  1.19s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:39,  1.01it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:35,  1.62it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:13,  2.07it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:54,  2.72it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.90it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.97it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.90it/s]
Loading 0:  63%|██████▎   | 229/363 [00:24<00:15,  8.73it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:12, 10.37it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.07it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 14.73it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:06, 19.47it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:06, 18.13it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 22.73it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:05, 20.80it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 27.12it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 20.92it/s]
Loading 0:  75%|███████▍  | 271/363 [00:26<00:04, 19.73it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 20.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:04, 21.15it/s]
Loading 0:  77%|███████▋  | 280/363 [00:26<00:03, 22.85it/s]
Loading 0:  78%|███████▊  | 283/363 [00:26<00:03, 23.29it/s]
Loading 0:  79%|███████▉  | 286/363 [00:27<00:03, 23.09it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 25.77it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:03, 22.19it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 24.68it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 21.61it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 20.37it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 21.62it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 21.93it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 25.06it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 22.50it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 26.94it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.33it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 27.29it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:00, 25.94it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.29it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 20.31it/s]
Loading 0:  96%|█████████▌| 349/363 [00:29<00:00, 18.88it/s]
Loading 0:  97%|█████████▋| 353/363 [00:30<00:00, 22.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:30<00:00, 23.57it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 22.72it/s]
                                                            

Job chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer completed after 145.39s with status: succeeded
Stopping job with name chaiml-gy-exp80-dpo-exp-56703-v4-mkmlizer
Pipeline stage MKMLizer completed in 145.89s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp80-dpo-exp-56703-v4
Waiting for inference service chaiml-gy-exp80-dpo-exp-56703-v4 to be ready
Inference service chaiml-gy-exp80-dpo-exp-56703-v4 ready after 221.0444996356964s
Pipeline stage MKMLDeployer completed in 221.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.740088939666748s
Received healthy response to inference request in 2.19496750831604s
Received healthy response to inference request in 1.8608949184417725s
Received healthy response to inference request in 2.187094211578369s
Received healthy response to inference request in 2.234841823577881s
5 requests
0 failed requests
5th percentile: 1.9261347770690918
10th percentile: 1.991374635696411
20th percentile: 2.1218543529510496
30th percentile: 2.1886688709259032
40th percentile: 2.191818189620972
50th percentile: 2.19496750831604
60th percentile: 2.2109172344207764
70th percentile: 2.2268669605255127
80th percentile: 2.3358912467956543
90th percentile: 2.537990093231201
95th percentile: 2.6390395164489746
99th percentile: 2.7198790550231933
mean time: 2.243577480316162
Pipeline stage StressChecker completed in 13.01s
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 0.68s
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 0.71s
Shutdown handler de-registered
chaiml-gy-exp80-dpo-exp_56703_v4 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 3268.70s
Shutdown handler de-registered
chaiml-gy-exp80-dpo-exp_56703_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp80-dpo-exp_56703_v4 status is now torndown due to DeploymentManager action