chaiml-gy-exp163-lipo-gy_3635

developer_uid: bogoconic1

submission_id: chaiml-gy-exp163-lipo-gy_3635_v1

model_name: chaiml-gy-exp163-lipo-gy_3635_v1

model_group: ChaiML/gy-exp163-lipo-gy

status: torndown

timestamp: 2025-07-13T18:09:57+00:00

num_battles: 10698

num_wins: 5683

celo_rating: 1311.87

family_friendly_score: 0.5274

family_friendly_standard_error: 0.007060442479051862

submission_type: basic

model_repo: ChaiML/gy-exp163-lipo-gy-datamix-v3-v5-bo8-dpo-gt0.6-3ans-ep1

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': 0.5191910007038452, 'latency_mean': 1.9259742414951324, 'latency_p50': 1.9434536695480347, 'latency_p90': 2.1176721811294557}, {'batch_size': 3, 'throughput': 1.0540402871439931, 'latency_mean': 2.8339281249046326, 'latency_p50': 2.8540934324264526, 'latency_p90': 3.128260087966919}, {'batch_size': 5, 'throughput': 1.3420874267099467, 'latency_mean': 3.70121701836586, 'latency_p50': 3.706358551979065, 'latency_p90': 4.143829369544983}, {'batch_size': 6, 'throughput': 1.4357835933904999, 'latency_mean': 4.147821266651153, 'latency_p50': 4.158166408538818, 'latency_p90': 4.651309490203857}, {'batch_size': 8, 'throughput': 1.5855255831791755, 'latency_mean': 5.013472090959549, 'latency_p50': 4.974258065223694, 'latency_p90': 5.736149644851684}, {'batch_size': 10, 'throughput': 1.6539954781369142, 'latency_mean': 5.995128903388977, 'latency_p50': 6.032629013061523, 'latency_p90': 6.7539678573608395}]

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

display_name: chaiml-gy-exp163-lipo-gy_3635_v1

is_internal_developer: False

language_model: ChaiML/gy-exp163-lipo-gy-datamix-v3-v5-bo8-dpo-gt0.6-3ans-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-13

win_ratio: 0.5312207889325108

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_start|>', '<|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-exp163-lipo-gy-3635-v1-mkmlizer
Waiting for job on chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer to finish
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: Downloaded to shared memory in 82.609s
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: Checking if ChaiML/gy-exp163-lipo-gy-datamix-v3-v5-bo8-dpo-gt0.6-3ans-ep1 already exists in ChaiML
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3cuu73_g, device:0
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: quantized model in 60.825s
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: Processed model ChaiML/gy-exp163-lipo-gy-datamix-v3-v5-bo8-dpo-gt0.6-3ans-ep1 in 143.435s
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/config.json
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/special_tokens_map.json
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/tokenizer_config.json
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/tokenizer.json
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp163-lipo-gy-3635-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 27.00it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.56it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:15, 22.43it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:15, 23.24it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:16, 21.54it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:15, 22.48it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:15, 22.51it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:16, 20.62it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:15, 21.58it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.45it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:21, 15.16it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:22, 14.66it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:19, 16.31it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:21, 15.25it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.63it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:15, 20.03it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:16, 19.24it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:15, 20.48it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:14, 20.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:15, 19.64it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:14, 20.65it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:12, 22.70it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:18, 15.54it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:19, 15.07it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:15, 18.91it/s]
Loading 0:  22%|██▏       | 81/363 [00:04<00:15, 17.65it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.95it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:12, 22.34it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.13it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.85it/s]
Loading 0:  28%|██▊       | 100/363 [00:05<00:10, 24.47it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:11, 23.59it/s]
Loading 0:  29%|██▉       | 107/363 [00:05<00:13, 19.24it/s]
Loading 0:  31%|███       | 111/363 [00:05<00:11, 22.26it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 19.31it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 22.17it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:10, 22.78it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 21.70it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:10, 22.78it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:09, 23.88it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 21.74it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 22.81it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 23.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:10, 21.70it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:09, 22.83it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 25.43it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 16.29it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 17.39it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:14, 14.43it/s]
Loading 0:  45%|████▍     | 163/363 [00:08<00:10, 19.27it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:09, 20.29it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:09, 19.93it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 21.29it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 21.56it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:09, 20.15it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:08, 21.23it/s]
Loading 0:  51%|█████     | 186/363 [00:09<00:07, 23.58it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:12, 14.26it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:09, 17.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:09, 17.21it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:08, 18.67it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:08, 18.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<05:05,  1.89s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:57,  1.49s/it]
Loading 0:  57%|█████▋    | 208/363 [00:28<02:09,  1.20it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<01:34,  1.60it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:16,  1.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:47,  3.05it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:36,  3.95it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:26,  5.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:22,  6.14it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:17,  7.84it/s]
Loading 0:  64%|██████▍   | 232/363 [00:29<00:13,  9.42it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:10, 11.80it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:08, 14.18it/s]
Loading 0:  66%|██████▋   | 241/363 [00:30<00:07, 15.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:30<00:05, 20.52it/s]
Loading 0:  69%|██████▊   | 249/363 [00:30<00:06, 18.49it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:04, 22.03it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:04, 23.31it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 22.85it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:03, 26.51it/s]
Loading 0:  74%|███████▎  | 267/363 [00:31<00:04, 19.93it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:05, 17.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:04, 20.52it/s]
Loading 0:  76%|███████▋  | 277/363 [00:31<00:04, 20.98it/s]
Loading 0:  78%|███████▊  | 282/363 [00:31<00:03, 24.49it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:03, 22.36it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:02, 26.73it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:02, 23.52it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:02, 26.56it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:02, 28.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:32<00:02, 19.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:02, 20.40it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 20.43it/s]
Loading 0:  88%|████████▊ | 318/363 [00:33<00:01, 24.23it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:01, 22.11it/s]
Loading 0:  90%|████████▉ | 325/363 [00:33<00:01, 25.47it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 26.44it/s]
Loading 0:  91%|█████████ | 331/363 [00:33<00:01, 24.94it/s]
Loading 0:  92%|█████████▏| 335/363 [00:34<00:01, 25.75it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 23.70it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 12.71it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 17.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:35<00:00, 17.19it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:00, 23.08it/s]
Loading 0:  99%|█████████▊| 358/363 [00:35<00:00, 21.13it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 24.67it/s]
                                                            
Job chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer completed after 177.42s with status: succeeded
Stopping job with name chaiml-gy-exp163-lipo-gy-3635-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.91s
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-exp163-lipo-gy-3635-v1
Waiting for inference service chaiml-gy-exp163-lipo-gy-3635-v1 to be ready
Inference service chaiml-gy-exp163-lipo-gy-3635-v1 ready after 221.36514019966125s
Pipeline stage MKMLDeployer completed in 221.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3347954750061035s
Received healthy response to inference request in 2.070274591445923s
Received healthy response to inference request in 2.090049982070923s
Received healthy response to inference request in 2.2998573780059814s
Received healthy response to inference request in 2.1204781532287598s
5 requests
0 failed requests
5th percentile: 2.074229669570923
10th percentile: 2.0781847476959228
20th percentile: 2.0860949039459227
30th percentile: 2.0961356163024902
40th percentile: 2.108306884765625
50th percentile: 2.1204781532287598
60th percentile: 2.1922298431396485
70th percentile: 2.2639815330505373
80th percentile: 2.506844997406006
90th percentile: 2.9208202362060547
95th percentile: 3.127807855606079
99th percentile: 3.2933979511260985
mean time: 2.383091115951538
Pipeline stage StressChecker completed in 13.44s
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 0.67s
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 0.75s
Shutdown handler de-registered
chaiml-gy-exp163-lipo-gy_3635_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3474.57s
Shutdown handler de-registered
chaiml-gy-exp163-lipo-gy_3635_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp163-lipo-gy_3635_v1 status is now torndown due to DeploymentManager action