chaiml-02f4-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-02f4-69d4-linear-w01_v30

model_name: chaiml-02f4-69d4-linear-w01_v30

model_group: ChaiML/02f4-69d4-linear-

status: inactive

timestamp: 2025-12-09T22:24:52+00:00

num_battles: 7126

num_wins: 3671

celo_rating: 1320.58

family_friendly_score: 0.49160000000000004

family_friendly_standard_error: 0.007070069872356284

submission_type: basic

model_repo: ChaiML/02f4-69d4-linear-w01

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': 0.439149741075809, 'latency_mean': 2.2770248222351075, 'latency_p50': 2.3005937337875366, 'latency_p90': 2.5487322092056273}, {'batch_size': 3, 'throughput': 0.9196617669105058, 'latency_mean': 3.2436000311374666, 'latency_p50': 3.2627118825912476, 'latency_p90': 3.5590089082717897}, {'batch_size': 5, 'throughput': 1.2147177123174764, 'latency_mean': 4.095089159011841, 'latency_p50': 4.05393648147583, 'latency_p90': 4.661051559448242}, {'batch_size': 6, 'throughput': 1.3175420888297946, 'latency_mean': 4.5413374423980715, 'latency_p50': 4.586179256439209, 'latency_p90': 5.08266658782959}, {'batch_size': 8, 'throughput': 1.4672135907694244, 'latency_mean': 5.421467835903168, 'latency_p50': 5.392604827880859, 'latency_p90': 6.155111646652221}, {'batch_size': 10, 'throughput': 1.5522967347815548, 'latency_mean': 6.380860463380814, 'latency_p50': 6.379050254821777, 'latency_p90': 7.214351844787598}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-02f4-69d4-linear-w01_v30

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/02f4-69d4-linear-w01

model_size: 24B

ranking_group: single

throughput_3p7s: 1.1

us_pacific_date: 2025-11-26

win_ratio: 0.5151557676115633

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-02f4-69d4-linear-w01-v30-mkmlizer
Waiting for job on chaiml-02f4-69d4-linear-w01-v30-mkmlizer to finish
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  belonging to:                                                      ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: Downloaded to shared memory in 50.290s
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: Checking if ChaiML/02f4-69d4-linear-w01 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt7n54osd, device:0
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: quantized model in 42.159s
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: Processed model ChaiML/02f4-69d4-linear-w01 in 92.450s
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: creating bucket guanaco-mkml-models
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/config.json
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/tokenizer.json
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/flywheel_model.1.safetensors
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v30/nvidia/flywheel_model.0.safetensors
chaiml-02f4-69d4-linear-w01-v30-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:46,  2.95s/it]
Loading 0:   1%|▏         | 5/363 [00:06<05:50,  1.02it/s]
Loading 0:   2%|▏         | 7/363 [00:06<03:42,  1.60it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:18,  4.46it/s]
Loading 0:   5%|▍         | 18/363 [00:06<00:53,  6.46it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:41,  8.17it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:35,  9.64it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:22, 14.72it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:19, 17.17it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:14, 21.63it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:13, 23.08it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 27.76it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 27.91it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:09, 31.81it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:12, 24.16it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:10, 29.06it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:10, 28.56it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 32.90it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 31.63it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 35.01it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 35.26it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:07, 35.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:09<00:09, 26.61it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:08, 29.19it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:08, 28.85it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 32.98it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 31.39it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 35.69it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.86it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:06, 35.82it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:06, 32.72it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:08, 27.55it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:08, 27.26it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 31.84it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 31.06it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:06, 34.25it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:06, 31.99it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:05, 35.48it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 32.77it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 36.37it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:07, 25.76it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 30.55it/s]
Loading 0:  52%|█████▏    | 188/363 [00:24<02:39,  1.10it/s]
Loading 0:  53%|█████▎    | 191/363 [00:24<02:02,  1.40it/s]
Loading 0:  54%|█████▎    | 195/363 [00:25<01:27,  1.92it/s]
Loading 0:  56%|█████▌    | 202/363 [00:25<00:48,  3.29it/s]
Loading 0:  57%|█████▋    | 206/363 [00:25<00:36,  4.27it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<00:25,  5.98it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:20,  7.06it/s]
Loading 0:  61%|██████    | 220/363 [00:26<00:14,  9.72it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:11, 11.76it/s]
Loading 0:  63%|██████▎   | 229/363 [00:26<00:08, 15.61it/s]
Loading 0:  64%|██████▍   | 233/363 [00:26<00:07, 17.80it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:05, 22.10it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:05, 23.32it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:04, 27.65it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:04, 27.40it/s]
Loading 0:  71%|███████   | 256/363 [00:27<00:04, 25.06it/s]
Loading 0:  72%|███████▏  | 260/363 [00:27<00:04, 25.45it/s]
Loading 0:  73%|███████▎  | 265/363 [00:27<00:03, 29.52it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:03, 29.12it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:02, 33.09it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 31.28it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 35.27it/s]
Loading 0:  79%|███████▉  | 287/363 [00:28<00:02, 32.65it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:01, 35.65it/s]
Loading 0:  82%|████████▏ | 296/363 [00:28<00:02, 24.99it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 29.34it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:02, 28.62it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:01, 32.98it/s]
Loading 0:  87%|████████▋ | 314/363 [00:28<00:01, 31.56it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 34.91it/s]
Loading 0:  89%|████████▉ | 323/363 [00:29<00:01, 31.89it/s]
Loading 0:  90%|█████████ | 328/363 [00:29<00:00, 35.42it/s]
Loading 0:  91%|█████████▏| 332/363 [00:29<00:01, 25.35it/s]
Loading 0:  93%|█████████▎| 337/363 [00:29<00:00, 29.90it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:00, 29.22it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 33.68it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 32.32it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 34.12it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 31.88it/s]
                                                            
Job chaiml-02f4-69d4-linear-w01-v30-mkmlizer completed after 277.39s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v30-mkmlizer
Pipeline stage MKMLizer completed in 278.61s
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-02f4-69d4-linear-w01-v30
Waiting for inference service chaiml-02f4-69d4-linear-w01-v30 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v30 ready after 161.31914448738098s
Pipeline stage MKMLDeployer completed in 161.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3700428009033203s
Received healthy response to inference request in 2.170145034790039s
Received healthy response to inference request in 2.1116790771484375s
Received healthy response to inference request in 2.2624051570892334s
Received healthy response to inference request in 2.1777937412261963s
5 requests
0 failed requests
5th percentile: 2.123372268676758
10th percentile: 2.135065460205078
20th percentile: 2.1584518432617186
30th percentile: 2.1716747760772703
40th percentile: 2.1747342586517333
50th percentile: 2.1777937412261963
60th percentile: 2.211638307571411
70th percentile: 2.245482873916626
80th percentile: 2.283932685852051
90th percentile: 2.3269877433776855
95th percentile: 2.348515272140503
99th percentile: 2.365737295150757
mean time: 2.218413162231445
Pipeline stage StressChecker completed in 12.26s
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 1.18s
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 0.94s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v30 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 3026.74s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v30 status is now inactive due to auto deactivation removed underperforming models
chaiml-02f4-69d4-linear-w01_v30 status is now protected due to ABTestQueueItem
chaiml-02f4-69d4-linear-w01_v30 status is now protected due to ABTestQueueItem