chaiml-gy-exp152-cpo-ex_57787

developer_uid: bogoconic1

submission_id: chaiml-gy-exp152-cpo-ex_57787_v2

model_name: chaiml-gy-exp152-cpo-ex_57787_v2

model_group: ChaiML/gy-exp152-cpo-exp

status: torndown

timestamp: 2025-07-12T17:02:44+00:00

num_battles: 8159

num_wins: 4196

celo_rating: 1279.41

family_friendly_score: 0.708

family_friendly_standard_error: 0.006430178846657377

submission_type: basic

model_repo: ChaiML/gy-exp152-cpo-exp54ep6s2-exp146data-ep2

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': 0.5247878341726577, 'latency_mean': 1.9053361022472382, 'latency_p50': 1.9085981845855713, 'latency_p90': 2.0963015079498293}, {'batch_size': 3, 'throughput': 1.048841427677999, 'latency_mean': 2.8459560441970826, 'latency_p50': 2.8298306465148926, 'latency_p90': 3.1573317527770994}, {'batch_size': 5, 'throughput': 1.3383874976787329, 'latency_mean': 3.716725152730942, 'latency_p50': 3.7334635257720947, 'latency_p90': 4.187719798088073}, {'batch_size': 6, 'throughput': 1.4213847406480684, 'latency_mean': 4.192417455911636, 'latency_p50': 4.168005347251892, 'latency_p90': 4.7175703048706055}, {'batch_size': 8, 'throughput': 1.5627020969414949, 'latency_mean': 5.0838180196285245, 'latency_p50': 5.0808387994766235, 'latency_p90': 5.712590861320495}, {'batch_size': 10, 'throughput': 1.653176205160678, 'latency_mean': 6.009005765914917, 'latency_p50': 5.985799193382263, 'latency_p90': 6.734220838546753}]

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

display_name: chaiml-gy-exp152-cpo-ex_57787_v2

is_internal_developer: False

language_model: ChaiML/gy-exp152-cpo-exp54ep6s2-exp146data-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-12

win_ratio: 0.5142787106263023

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': ['\n', '<|im_end|>', '<|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-exp152-cpo-ex-57787-v2-mkmlizer
Waiting for job on chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer to finish
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: Downloaded to shared memory in 79.187s
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: Checking if ChaiML/gy-exp152-cpo-exp54ep6s2-exp146data-ep2 already exists in ChaiML
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt2l9g9m2, device:0
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: quantized model in 60.760s
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: Processed model ChaiML/gy-exp152-cpo-exp54ep6s2-exp146data-ep2 in 140.041s
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/config.json
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/special_tokens_map.json
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/tokenizer_config.json
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/tokenizer.json
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp152-cpo-ex-57787-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 26.39it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.37it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:15, 22.55it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:14, 23.39it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:15, 22.37it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:13, 25.79it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:16, 20.74it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 24.75it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:11, 28.27it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:21, 15.24it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:18, 17.91it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:14, 21.76it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:15, 19.80it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:13, 23.02it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 23.52it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 22.70it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.22it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:11, 25.56it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.53it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.71it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:15, 18.25it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:16, 16.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:13, 20.49it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:13, 20.97it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:15, 17.37it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.11it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.53it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.78it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:10, 24.09it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:15, 16.89it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:13, 18.31it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:13, 18.31it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:12, 20.12it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:11, 20.58it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 20.65it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:09, 25.01it/s]
Loading 0:  36%|███▌      | 131/363 [00:06<00:12, 18.99it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 25.20it/s]
Loading 0:  39%|███▊      | 140/363 [00:06<00:11, 19.39it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 22.97it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 25.48it/s]
Loading 0:  42%|████▏     | 153/363 [00:07<00:13, 15.61it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:11, 18.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:11, 18.22it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:10, 19.72it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:09, 20.83it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:09, 20.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 22.59it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 21.80it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:09, 19.94it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:08, 20.65it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:07, 24.84it/s]
Loading 0:  52%|█████▏    | 188/363 [00:09<00:11, 15.03it/s]
Loading 0:  53%|█████▎    | 191/363 [00:09<00:10, 16.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:09<00:12, 13.98it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:08, 18.92it/s]
Loading 0:  55%|█████▌    | 200/363 [00:19<00:08, 18.92it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:37,  1.71s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:39,  1.37s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:02,  1.26it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<01:30,  1.67it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<01:06,  2.25it/s]
Loading 0:  60%|██████    | 218/363 [00:28<00:44,  3.29it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:33,  4.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:28<00:26,  5.17it/s]
Loading 0:  63%|██████▎   | 228/363 [00:28<00:18,  7.38it/s]
Loading 0:  64%|██████▎   | 231/363 [00:29<00:15,  8.70it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:09, 13.00it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:08, 13.84it/s]
Loading 0:  68%|██████▊   | 246/363 [00:29<00:06, 18.66it/s]
Loading 0:  69%|██████▊   | 249/363 [00:29<00:06, 18.07it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:04, 22.57it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:05, 20.88it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:03, 25.83it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:04, 21.38it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:05, 18.34it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:04, 21.09it/s]
Loading 0:  76%|███████▋  | 277/363 [00:30<00:04, 21.27it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:03, 22.42it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:03, 22.87it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:03, 22.44it/s]
Loading 0:  80%|████████  | 291/363 [00:31<00:02, 25.57it/s]
Loading 0:  81%|████████  | 294/363 [00:31<00:03, 22.52it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:02, 25.99it/s]
Loading 0:  83%|████████▎ | 303/363 [00:31<00:02, 27.73it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 16.94it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:02, 20.12it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 20.11it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 21.90it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 22.81it/s]
Loading 0:  89%|████████▊ | 322/363 [00:32<00:01, 22.89it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:01, 24.87it/s]
Loading 0:  91%|█████████ | 330/363 [00:33<00:01, 22.16it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 25.62it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 20.58it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 13.70it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 18.39it/s]
Loading 0:  96%|█████████▌| 349/363 [00:34<00:00, 17.87it/s]
Loading 0:  97%|█████████▋| 353/363 [00:34<00:00, 21.26it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 21.78it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 21.97it/s]
                                                            
Job chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer completed after 177.22s with status: succeeded
Stopping job with name chaiml-gy-exp152-cpo-ex-57787-v2-mkmlizer
Pipeline stage MKMLizer completed in 177.68s
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-exp152-cpo-ex-57787-v2
Waiting for inference service chaiml-gy-exp152-cpo-ex-57787-v2 to be ready
Inference service chaiml-gy-exp152-cpo-ex-57787-v2 ready after 211.44436812400818s
Pipeline stage MKMLDeployer completed in 211.98s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission zmeeks-capitanito-22_v1: HTTPConnectionPool(host='zmeeks-capitanito-22-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.635277509689331s
Received healthy response to inference request in 2.2288384437561035s
Received healthy response to inference request in 2.122276782989502s
Received healthy response to inference request in 1.9908678531646729s
Received healthy response to inference request in 2.3709566593170166s
5 requests
0 failed requests
5th percentile: 2.017149639129639
10th percentile: 2.0434314250946044
20th percentile: 2.095994997024536
30th percentile: 2.1435891151428224
40th percentile: 2.1862137794494627
50th percentile: 2.2288384437561035
60th percentile: 2.285685729980469
70th percentile: 2.342533016204834
80th percentile: 2.4238208293914796
90th percentile: 2.529549169540405
95th percentile: 2.582413339614868
99th percentile: 2.6247046756744385
mean time: 2.269643449783325
Pipeline stage StressChecker completed in 12.92s
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 0.69s
Shutdown handler de-registered
chaiml-gy-exp152-cpo-ex_57787_v2 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 4066.79s
Shutdown handler de-registered
chaiml-gy-exp152-cpo-ex_57787_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp152-cpo-ex_57787_v2 status is now torndown due to DeploymentManager action