chaiml-02f4-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-02f4-69d4-linear-w01_v31

model_name: chaiml-02f4-69d4-linear-w01_v31

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

status: torndown

timestamp: 2025-12-12T18:26:47+00:00

num_battles: 7159

num_wins: 3642

celo_rating: 1308.65

family_friendly_score: 0.49139999999999995

family_friendly_standard_error: 0.007070021782144663

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': 0.4320141267073606, 'latency_mean': 2.314611884355545, 'latency_p50': 2.2986918687820435, 'latency_p90': 2.5721062660217284}, {'batch_size': 3, 'throughput': 0.9081641120554358, 'latency_mean': 3.297549842596054, 'latency_p50': 3.289559483528137, 'latency_p90': 3.6206323623657224}, {'batch_size': 5, 'throughput': 1.1829127467660159, 'latency_mean': 4.206586045026779, 'latency_p50': 4.194154381752014, 'latency_p90': 4.71240496635437}, {'batch_size': 6, 'throughput': 1.2772225146102378, 'latency_mean': 4.661157609224319, 'latency_p50': 4.658324599266052, 'latency_p90': 5.3041452169418335}, {'batch_size': 8, 'throughput': 1.4268336150099257, 'latency_mean': 5.551977220773697, 'latency_p50': 5.536723017692566, 'latency_p90': 6.325595188140869}, {'batch_size': 10, 'throughput': 1.5103508311389537, 'latency_mean': 6.578341314792633, 'latency_p50': 6.588293194770813, 'latency_p90': 7.514190077781677}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-02f4-69d4-linear-w01_v31

ineligible_reason: num_battles<10000

is_internal_developer: True

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

model_size: 24B

ranking_group: single

throughput_3p7s: 1.05

us_pacific_date: 2025-11-26

win_ratio: 0.508730269590725

generation_params: {'temperature': 1.1, '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-v31-mkmlizer
Waiting for job on chaiml-02f4-69d4-linear-w01-v31-mkmlizer to finish
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  belonging to:                                                      ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: Downloaded to shared memory in 44.057s
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: Checking if ChaiML/02f4-69d4-linear-w01 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbxctip7v, device:0
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: quantized model in 42.041s
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: Processed model ChaiML/02f4-69d4-linear-w01 in 86.099s
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: creating bucket guanaco-mkml-models
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/config.json
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/tokenizer.json
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/flywheel_model.1.safetensors
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v31/nvidia/flywheel_model.0.safetensors
chaiml-02f4-69d4-linear-w01-v31-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:56,  2.82s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:35,  1.30it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:30,  3.85it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:03,  5.43it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:48,  6.98it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:40,  8.40it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:25, 12.95it/s]
Loading 0:  10%|▉         | 35/363 [00:06<00:21, 15.22it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 19.53it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 21.22it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:12, 25.54it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 25.95it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:09, 30.73it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:12, 23.46it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:10, 28.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:07<00:10, 27.91it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 32.35it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:09, 31.33it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 34.65it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 34.96it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:07, 35.58it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:10, 24.74it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:09, 27.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:09, 27.09it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:08, 31.32it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:08, 29.77it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 34.09it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 31.77it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 34.68it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 32.35it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:08, 27.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:10<00:08, 25.62it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 32.34it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 30.91it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:06, 34.28it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 31.70it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 35.25it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 32.32it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 35.40it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:07, 24.99it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 29.85it/s]
Loading 0:  52%|█████▏    | 188/363 [00:24<02:38,  1.10it/s]
Loading 0:  53%|█████▎    | 193/363 [00:24<01:46,  1.60it/s]
Loading 0:  54%|█████▍    | 197/363 [00:24<01:17,  2.15it/s]
Loading 0:  56%|█████▌    | 202/363 [00:24<00:51,  3.12it/s]
Loading 0:  57%|█████▋    | 206/363 [00:25<00:38,  4.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<00:26,  5.84it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:21,  6.86it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:15,  9.50it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:11, 11.62it/s]
Loading 0:  63%|██████▎   | 229/363 [00:25<00:08, 15.43it/s]
Loading 0:  64%|██████▍   | 233/363 [00:26<00:07, 17.55it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:05, 21.85it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:05, 23.08it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:04, 27.60it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:04, 27.67it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 24.59it/s]
Loading 0:  72%|███████▏  | 260/363 [00:26<00:04, 24.57it/s]
Loading 0:  73%|███████▎  | 265/363 [00:27<00:03, 28.50it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:03, 28.13it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:02, 32.31it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 30.59it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 34.93it/s]
Loading 0:  79%|███████▉  | 287/363 [00:27<00:02, 33.02it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:01, 36.15it/s]
Loading 0:  82%|████████▏ | 296/363 [00:28<00:02, 25.29it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 29.15it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:02, 28.95it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:01, 33.45it/s]
Loading 0:  87%|████████▋ | 314/363 [00:28<00:01, 31.97it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 35.03it/s]
Loading 0:  89%|████████▉ | 323/363 [00:28<00:01, 30.16it/s]
Loading 0:  90%|█████████ | 327/363 [00:29<00:01, 31.34it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:02, 14.90it/s]
Loading 0:  93%|█████████▎| 337/363 [00:29<00:01, 20.56it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 21.91it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 26.58it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 26.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 29.91it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 29.12it/s]
                                                            
Job chaiml-02f4-69d4-linear-w01-v31-mkmlizer completed after 266.61s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v31-mkmlizer
Pipeline stage MKMLizer completed in 267.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-02f4-69d4-linear-w01-v31
Waiting for inference service chaiml-02f4-69d4-linear-w01-v31 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v31 ready after 160.8318099975586s
Pipeline stage MKMLDeployer completed in 161.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7072842121124268s
Received healthy response to inference request in 2.423802137374878s
Received healthy response to inference request in 2.4400296211242676s
Received healthy response to inference request in 2.1284241676330566s
Received healthy response to inference request in 2.1060073375701904s
5 requests
0 failed requests
5th percentile: 2.1104907035827636
10th percentile: 2.1149740695953367
20th percentile: 2.1239408016204835
30th percentile: 2.187499761581421
40th percentile: 2.3056509494781494
50th percentile: 2.423802137374878
60th percentile: 2.4302931308746336
70th percentile: 2.4367841243743897
80th percentile: 2.4934805393218995
90th percentile: 2.600382375717163
95th percentile: 2.653833293914795
99th percentile: 2.6965940284729
mean time: 2.361109495162964
Pipeline stage StressChecker completed in 13.00s
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 1.01s
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 0.64s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v31 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-02f4-69d4-linear-w01-v31-profiler
Waiting for inference service chaiml-02f4-69d4-linear-w01-v31-profiler to be ready
Inference service chaiml-02f4-69d4-linear-w01-v31-profiler ready after 161.97552394866943s
Pipeline stage MKMLProfilerDeployer completed in 162.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-02f4-69d4-lincf566054e07876df70265a2c87e341c1-deplo87l46:/code/chaiverse_profiler_1764198989 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-02f4-69d4-lincf566054e07876df70265a2c87e341c1-deplo87l46 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1764198989 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1764198989/summary.json'
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 2873.58s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v31 status is now inactive due to auto deactivation removed underperforming models
chaiml-02f4-69d4-linear-w01_v31 status is now torndown due to DeploymentManager action