chaiml-gy-exp159-lipo-g_95172

developer_uid: bogoconic1

submission_id: chaiml-gy-exp159-lipo-g_95172_v1

model_name: chaiml-gy-exp159-lipo-g_95172_v1

model_group: ChaiML/gy-exp159-lipo-gy

status: torndown

timestamp: 2025-07-13T07:07:16+00:00

num_battles: 7539

num_wins: 3988

celo_rating: 1323.67

family_friendly_score: 0.526

family_friendly_standard_error: 0.007061501256815012

submission_type: basic

model_repo: ChaiML/gy-exp159-lipo-gy-datamix-v3-bo8-dpo-gt0.6-3ans

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': 0.5148321247005169, 'latency_mean': 1.9421899139881134, 'latency_p50': 1.941414475440979, 'latency_p90': 2.1621294260025024}, {'batch_size': 3, 'throughput': 1.0379291472595893, 'latency_mean': 2.8788452744483948, 'latency_p50': 2.8580679893493652, 'latency_p90': 3.218305492401123}, {'batch_size': 5, 'throughput': 1.3249967153898838, 'latency_mean': 3.7470950043201445, 'latency_p50': 3.734925150871277, 'latency_p90': 4.142569255828858}, {'batch_size': 6, 'throughput': 1.4131161874152864, 'latency_mean': 4.210432815551758, 'latency_p50': 4.186577558517456, 'latency_p90': 4.701707935333252}, {'batch_size': 8, 'throughput': 1.544757443406808, 'latency_mean': 5.142346740961075, 'latency_p50': 5.12006676197052, 'latency_p90': 5.7387107610702515}, {'batch_size': 10, 'throughput': 1.6313676519920042, 'latency_mean': 6.089943619966507, 'latency_p50': 6.081368446350098, 'latency_p90': 6.87992787361145}]

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

display_name: chaiml-gy-exp159-lipo-g_95172_v1

is_internal_developer: False

language_model: ChaiML/gy-exp159-lipo-gy-datamix-v3-bo8-dpo-gt0.6-3ans

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-13

win_ratio: 0.5289826236901446

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-exp159-lipo-g-95172-v1-mkmlizer
Waiting for job on chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer to finish
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: Downloaded to shared memory in 79.887s
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: Checking if ChaiML/gy-exp159-lipo-gy-datamix-v3-bo8-dpo-gt0.6-3ans already exists in ChaiML
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0t9_2d39, device:0
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: quantized model in 57.838s
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: Processed model ChaiML/gy-exp159-lipo-gy-datamix-v3-bo8-dpo-gt0.6-3ans in 137.725s
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/config.json
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/special_tokens_map.json
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/tokenizer_config.json
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/tokenizer.json
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp159-lipo-g-95172-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 30.89it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:14, 24.03it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 25.30it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:17, 20.20it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:13, 26.02it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 21.82it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 25.43it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.06it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:19, 17.14it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 19.97it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:15, 20.04it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 21.81it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 22.68it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.40it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:13, 22.83it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 23.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 22.17it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.52it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:11, 25.67it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:17, 17.02it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.71it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:14, 19.53it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:15, 17.79it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:13, 20.06it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:15, 18.22it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:12, 21.78it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:12, 21.50it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 22.83it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.04it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.65it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.23it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:14, 17.39it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:12, 19.36it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 19.66it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 21.49it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 22.55it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.04it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:10, 22.42it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:10, 22.98it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 22.42it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 24.02it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 23.78it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 22.71it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 24.03it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 26.87it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 17.05it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 18.37it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:13, 15.43it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 21.13it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:09, 21.62it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:09, 21.32it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 22.54it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 22.85it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 22.43it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:07, 23.81it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 25.29it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:11, 15.08it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:09, 18.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 18.63it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 20.67it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 20.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:49,  1.79s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:44,  1.40s/it]
Loading 0:  57%|█████▋    | 208/363 [00:26<02:01,  1.27it/s]
Loading 0:  58%|█████▊    | 211/363 [00:26<01:29,  1.70it/s]
Loading 0:  59%|█████▉    | 214/363 [00:27<01:04,  2.31it/s]
Loading 0:  60%|██████    | 218/363 [00:27<00:42,  3.38it/s]
Loading 0:  61%|██████    | 221/363 [00:27<00:32,  4.39it/s]
Loading 0:  62%|██████▏   | 224/363 [00:27<00:26,  5.30it/s]
Loading 0:  63%|██████▎   | 228/363 [00:27<00:17,  7.59it/s]
Loading 0:  64%|██████▎   | 231/363 [00:27<00:14,  8.93it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:09, 13.46it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:08, 14.34it/s]
Loading 0:  68%|██████▊   | 246/363 [00:28<00:06, 19.13it/s]
Loading 0:  69%|██████▊   | 249/363 [00:28<00:06, 18.93it/s]
Loading 0:  70%|███████   | 255/363 [00:28<00:04, 23.40it/s]
Loading 0:  71%|███████   | 258/363 [00:28<00:04, 21.62it/s]
Loading 0:  72%|███████▏  | 263/363 [00:29<00:03, 26.80it/s]
Loading 0:  74%|███████▎  | 267/363 [00:29<00:04, 21.09it/s]
Loading 0:  74%|███████▍  | 270/363 [00:29<00:05, 18.20it/s]
Loading 0:  75%|███████▌  | 274/363 [00:29<00:04, 21.18it/s]
Loading 0:  76%|███████▋  | 277/363 [00:29<00:03, 21.64it/s]
Loading 0:  78%|███████▊  | 282/363 [00:29<00:03, 24.57it/s]
Loading 0:  79%|███████▊  | 285/363 [00:30<00:03, 21.96it/s]
Loading 0:  80%|███████▉  | 289/363 [00:30<00:03, 24.54it/s]
Loading 0:  80%|████████  | 292/363 [00:30<00:02, 24.69it/s]
Loading 0:  81%|████████▏ | 295/363 [00:30<00:02, 23.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:30<00:02, 24.28it/s]
Loading 0:  84%|████████▎ | 304/363 [00:30<00:02, 20.97it/s]
Loading 0:  85%|████████▍ | 307/363 [00:31<00:02, 19.75it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:02, 20.81it/s]
Loading 0:  86%|████████▌ | 313/363 [00:31<00:02, 21.31it/s]
Loading 0:  87%|████████▋ | 316/363 [00:31<00:02, 23.15it/s]
Loading 0:  88%|████████▊ | 319/363 [00:31<00:01, 23.75it/s]
Loading 0:  89%|████████▊ | 322/363 [00:31<00:01, 23.12it/s]
Loading 0:  90%|█████████ | 327/363 [00:31<00:01, 25.76it/s]
Loading 0:  91%|█████████ | 330/363 [00:32<00:01, 22.92it/s]
Loading 0:  92%|█████████▏| 334/363 [00:32<00:01, 26.68it/s]
Loading 0:  93%|█████████▎| 337/363 [00:32<00:01, 22.98it/s]
Loading 0:  94%|█████████▍| 341/363 [00:32<00:01, 14.53it/s]
Loading 0:  95%|█████████▌| 346/363 [00:32<00:00, 19.52it/s]
Loading 0:  96%|█████████▌| 349/363 [00:33<00:00, 18.81it/s]
Loading 0:  97%|█████████▋| 353/363 [00:33<00:00, 22.09it/s]
Loading 0:  98%|█████████▊| 356/363 [00:33<00:00, 23.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00, 23.50it/s]
                                                            
Job chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer completed after 168.76s with status: succeeded
Stopping job with name chaiml-gy-exp159-lipo-g-95172-v1-mkmlizer
Pipeline stage MKMLizer completed in 169.36s
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-exp159-lipo-g-95172-v1
Waiting for inference service chaiml-gy-exp159-lipo-g-95172-v1 to be ready
Inference service chaiml-gy-exp159-lipo-g-95172-v1 ready after 220.81595396995544s
Pipeline stage MKMLDeployer completed in 221.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.632996082305908s
Failed to get response for submission chaiml-gy-exp126-dpo-e_77990_v17: HTTPConnectionPool(host='chaiml-gy-exp126-dpo-e-77990-v17-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.0124545097351074s
Received healthy response to inference request in 1.857945203781128s
Received healthy response to inference request in 2.0533621311187744s
Received healthy response to inference request in 1.9308085441589355s
5 requests
0 failed requests
5th percentile: 1.8725178718566895
10th percentile: 1.887090539932251
20th percentile: 1.916235876083374
30th percentile: 1.9471377372741698
40th percentile: 1.9797961235046386
50th percentile: 2.0124545097351074
60th percentile: 2.028817558288574
70th percentile: 2.045180606842041
80th percentile: 2.1692889213562014
90th percentile: 2.4011425018310546
95th percentile: 2.517069292068481
99th percentile: 2.609810724258423
mean time: 2.097513294219971
Pipeline stage StressChecker completed in 12.10s
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 0.73s
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 0.74s
Shutdown handler de-registered
chaiml-gy-exp159-lipo-g_95172_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 5854.41s
Shutdown handler de-registered
chaiml-gy-exp159-lipo-g_95172_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp159-lipo-g_95172_v1 status is now torndown due to DeploymentManager action