chaiml-ca18-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-ca18-c13f-linear-w01_v24

model_name: chaiml-ca18-c13f-linear-w01_v24

model_group: ChaiML/ca18-c13f-linear-

status: torndown

timestamp: 2025-12-12T18:27:00+00:00

num_battles: 5560

num_wins: 2766

celo_rating: 1302.86

family_friendly_score: 0.519

family_friendly_standard_error: 0.007065960656556191

submission_type: basic

model_repo: ChaiML/ca18-c13f-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 7

max_input_tokens: 1280

max_output_tokens: 60

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.809468643851305, 'latency_mean': 1.235281184911728, 'latency_p50': 1.2409790754318237, 'latency_p90': 1.3666618108749389}, {'batch_size': 4, 'throughput': 1.9312231956301862, 'latency_mean': 2.0661981296539307, 'latency_p50': 2.064785361289978, 'latency_p90': 2.344426417350769}, {'batch_size': 5, 'throughput': 2.144706403508481, 'latency_mean': 2.319394223690033, 'latency_p50': 2.3010406494140625, 'latency_p90': 2.6349704027175904}, {'batch_size': 8, 'throughput': 2.5050533803025665, 'latency_mean': 3.157584203481674, 'latency_p50': 3.1786400079727173, 'latency_p90': 3.5761717081069944}, {'batch_size': 10, 'throughput': 2.668010990607084, 'latency_mean': 3.7225069081783295, 'latency_p50': 3.727197766304016, 'latency_p90': 4.270394825935364}, {'batch_size': 12, 'throughput': 2.7643227915685764, 'latency_mean': 4.302239303588867, 'latency_p50': 4.30918824672699, 'latency_p90': 4.84947395324707}, {'batch_size': 15, 'throughput': 2.8795724415355717, 'latency_mean': 5.14323317527771, 'latency_p50': 5.1525958776474, 'latency_p90': 6.007714939117432}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ca18-c13f-linear-w01_v24

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/ca18-c13f-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 2.68

us_pacific_date: 2025-11-26

win_ratio: 0.4974820143884892

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['</s>', '###', '\n', 'You:'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 60}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-ca18-c13f-linear-w01-v24-mkmlizer
Waiting for job on chaiml-ca18-c13f-linear-w01-v24-mkmlizer to finish
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: Downloaded to shared memory in 20.525s
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: Checking if ChaiML/ca18-c13f-linear-w01 already exists in ChaiML
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1nmaebo_, device:0
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: quantized model in 27.337s
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: Processed model ChaiML/ca18-c13f-linear-w01 in 47.862s
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia/config.json
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia/special_tokens_map.json
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia/tokenizer_config.json
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia/tokenizer.json
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v24/nvidia/flywheel_model.0.safetensors
chaiml-ca18-c13f-linear-w01-v24-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:16,  2.70s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:20,  1.37it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:25,  4.09it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:51,  6.65it/s]
Loading 0:   7%|▋         | 25/363 [00:05<00:36,  9.34it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.30it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:17, 18.60it/s]
Loading 0:  12%|█▏        | 44/363 [00:06<00:15, 20.03it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 24.72it/s]
Loading 0:  16%|█▋        | 59/363 [00:06<00:09, 32.73it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:08, 35.49it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:07, 39.22it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:07, 40.13it/s]
Loading 0:  24%|██▎       | 86/363 [00:07<00:05, 47.15it/s]
Loading 0:  25%|██▌       | 92/363 [00:07<00:05, 46.43it/s]
Loading 0:  27%|██▋       | 98/363 [00:07<00:05, 47.43it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 45.73it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:05, 48.71it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 42.22it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:05, 43.25it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:05, 42.04it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 46.15it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:04, 50.89it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:05, 35.75it/s]
Loading 0:  44%|████▍     | 160/363 [00:08<00:05, 35.58it/s]
Loading 0:  45%|████▌     | 165/363 [00:09<00:05, 37.70it/s]
Loading 0:  47%|████▋     | 170/363 [00:09<00:05, 37.85it/s]
Loading 0:  49%|████▉     | 177/363 [00:09<00:04, 38.87it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:03, 47.12it/s]
Loading 0:  53%|█████▎    | 191/363 [00:09<00:03, 46.97it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:03, 46.85it/s]
Loading 0:  56%|█████▌    | 202/363 [00:09<00:04, 37.93it/s]
Loading 0:  57%|█████▋    | 207/363 [00:10<00:03, 39.79it/s]
Loading 0:  59%|█████▊    | 213/363 [00:10<00:03, 39.01it/s]
Loading 0:  61%|██████    | 220/363 [00:10<00:03, 45.69it/s]
Loading 0:  62%|██████▏   | 225/363 [00:10<00:02, 46.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:10<00:02, 45.23it/s]
Loading 0:  65%|██████▌   | 236/363 [00:10<00:02, 44.04it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:02, 44.69it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:02, 49.93it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 47.44it/s]
Loading 0:  71%|███████▏  | 259/363 [00:11<00:02, 46.89it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:01, 52.47it/s]
Loading 0:  75%|███████▍  | 272/363 [00:11<00:01, 50.38it/s]
Loading 0:  77%|███████▋  | 278/363 [00:11<00:01, 49.57it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:02, 37.99it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:01, 40.49it/s]
Loading 0:  81%|████████  | 294/363 [00:12<00:01, 34.75it/s]
Loading 0:  83%|████████▎ | 301/363 [00:12<00:01, 41.80it/s]
Loading 0:  84%|████████▍ | 306/363 [00:12<00:01, 40.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:01, 40.84it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 42.70it/s]
Loading 0:  88%|████████▊ | 321/363 [00:12<00:01, 36.28it/s]
Loading 0:  90%|█████████ | 328/363 [00:12<00:00, 42.68it/s]
Loading 0:  92%|█████████▏| 333/363 [00:12<00:00, 42.22it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 41.67it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 43.25it/s]
Loading 0:  96%|█████████▌| 348/363 [00:13<00:00, 34.32it/s]
Loading 0:  98%|█████████▊| 355/363 [00:13<00:00, 41.08it/s]
Loading 0:  99%|█████████▉| 360/363 [00:13<00:00, 40.36it/s]
                                                            
Job chaiml-ca18-c13f-linear-w01-v24-mkmlizer completed after 155.83s with status: succeeded
Stopping job with name chaiml-ca18-c13f-linear-w01-v24-mkmlizer
Pipeline stage MKMLizer completed in 157.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-c13f-linear-w01-v24
Waiting for inference service chaiml-ca18-c13f-linear-w01-v24 to be ready
Inference service chaiml-ca18-c13f-linear-w01-v24 ready after 160.86779689788818s
Pipeline stage MKMLDeployer completed in 161.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6847162246704102s
Received healthy response to inference request in 1.2353026866912842s
Received healthy response to inference request in 1.23457932472229s
Received healthy response to inference request in 1.2293388843536377s
Received healthy response to inference request in 1.1371593475341797s
5 requests
0 failed requests
5th percentile: 1.1555952548980712
10th percentile: 1.1740311622619628
20th percentile: 1.2109029769897461
30th percentile: 1.2303869724273682
40th percentile: 1.232483148574829
50th percentile: 1.23457932472229
60th percentile: 1.2348686695098876
70th percentile: 1.2351580142974854
80th percentile: 1.3251853942871095
90th percentile: 1.5049508094787598
95th percentile: 1.5948335170745849
99th percentile: 1.666739683151245
mean time: 1.3042192935943604
Pipeline stage StressChecker completed in 7.63s
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 0.70s
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 0.66s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v24 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 2401.70s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v24 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-c13f-linear-w01_v24 status is now torndown due to DeploymentManager action