chaiml-2a6f-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-2a6f-69d4-linear-w01_v15

model_name: chaiml-2a6f-69d4-linear-w01_v15

model_group: ChaiML/2a6f-69d4-linear-

status: torndown

timestamp: 2025-12-12T18:26:53+00:00

num_battles: 6081

num_wins: 3151

celo_rating: 1311.84

family_friendly_score: 0.5234

family_friendly_standard_error: 0.007063319899310805

submission_type: basic

model_repo: ChaiML/2a6f-69d4-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 7

max_input_tokens: 1280

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.42473596036687755, 'latency_mean': 2.3543033587932585, 'latency_p50': 2.3687052726745605, 'latency_p90': 2.6108856201171875}, {'batch_size': 3, 'throughput': 0.8765074414737911, 'latency_mean': 3.4114057922363283, 'latency_p50': 3.401206374168396, 'latency_p90': 3.761105990409851}, {'batch_size': 5, 'throughput': 1.1473073630293897, 'latency_mean': 4.345737622976303, 'latency_p50': 4.375990271568298, 'latency_p90': 4.9129204750061035}, {'batch_size': 6, 'throughput': 1.2383616649345868, 'latency_mean': 4.824474350214005, 'latency_p50': 4.836676359176636, 'latency_p90': 5.497662281990051}, {'batch_size': 8, 'throughput': 1.3677868856556723, 'latency_mean': 5.806008341312409, 'latency_p50': 5.834312677383423, 'latency_p90': 6.642105150222778}, {'batch_size': 10, 'throughput': 1.4546210386599896, 'latency_mean': 6.8165052235126495, 'latency_p50': 6.850328683853149, 'latency_p90': 7.8161317110061646}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-2a6f-69d4-linear-w01_v15

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/2a6f-69d4-linear-w01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.98

us_pacific_date: 2025-11-26

win_ratio: 0.5181713533958231

generation_params: {'temperature': 1.1, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

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-2a6f-69d4-linear-w01-v15-mkmlizer
Waiting for job on chaiml-2a6f-69d4-linear-w01-v15-mkmlizer to finish
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  belonging to:                                                      ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: Downloaded to shared memory in 42.955s
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: Checking if ChaiML/2a6f-69d4-linear-w01 already exists in ChaiML
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpupxzca0g, device:0
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: quantized model in 41.666s
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: Processed model ChaiML/2a6f-69d4-linear-w01 in 84.622s
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia/config.json
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia/special_tokens_map.json
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia/tokenizer_config.json
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia/flywheel_model.1.safetensors
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v15/nvidia/flywheel_model.0.safetensors
chaiml-2a6f-69d4-linear-w01-v15-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:26,  2.73s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:27,  1.33it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:28,  3.96it/s]
Loading 0:   5%|▍         | 18/363 [00:05<01:01,  5.58it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:47,  7.14it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:39,  8.58it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:25, 13.21it/s]
Loading 0:  10%|▉         | 35/363 [00:06<00:21, 15.61it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 19.90it/s]
Loading 0:  12%|█▏        | 44/363 [00:06<00:14, 21.93it/s]
Loading 0:  13%|█▎        | 49/363 [00:06<00:11, 26.75it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 27.72it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:09, 32.37it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:12, 24.95it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:10, 29.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 31.37it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:08, 33.05it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:07, 35.80it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 31.59it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 38.96it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:09, 28.80it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:08, 30.85it/s]
Loading 0:  29%|██▉       | 107/363 [00:08<00:08, 30.36it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:07, 34.24it/s]
Loading 0:  32%|███▏      | 116/363 [00:08<00:07, 32.52it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 36.56it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:06, 34.08it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.78it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 34.47it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:07, 28.50it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:07, 28.38it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:06, 32.95it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 31.97it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 35.25it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 33.36it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 36.96it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 34.11it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 37.84it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:06, 26.45it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 31.24it/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 [00:24<01:27,  1.93it/s]
Loading 0:  56%|█████▌    | 202/363 [00:24<00:48,  3.30it/s]
Loading 0:  57%|█████▋    | 206/363 [00:24<00:37,  4.24it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<00:25,  5.95it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:21,  7.04it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:14,  9.68it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:11, 11.82it/s]
Loading 0:  63%|██████▎   | 229/363 [00:25<00:08, 15.71it/s]
Loading 0:  64%|██████▍   | 233/363 [00:25<00:07, 18.04it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:05, 22.33it/s]
Loading 0:  67%|██████▋   | 242/363 [00:25<00:05, 23.90it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:04, 28.55it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:04, 27.69it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 25.37it/s]
Loading 0:  72%|███████▏  | 260/363 [00:26<00:03, 25.89it/s]
Loading 0:  73%|███████▎  | 265/363 [00:26<00:03, 30.05it/s]
Loading 0:  74%|███████▍  | 269/363 [00:26<00:03, 29.48it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:02, 33.22it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 32.09it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 35.68it/s]
Loading 0:  79%|███████▉  | 287/363 [00:27<00:02, 33.67it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:01, 36.78it/s]
Loading 0:  82%|████████▏ | 296/363 [00:27<00:02, 25.82it/s]
Loading 0:  83%|████████▎ | 301/363 [00:27<00:02, 30.43it/s]
Loading 0:  84%|████████▍ | 305/363 [00:27<00:01, 30.22it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:01, 33.94it/s]
Loading 0:  87%|████████▋ | 314/363 [00:28<00:01, 32.51it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 36.00it/s]
Loading 0:  89%|████████▉ | 323/363 [00:28<00:01, 33.63it/s]
Loading 0:  90%|█████████ | 328/363 [00:28<00:00, 36.70it/s]
Loading 0:  91%|█████████▏| 332/363 [00:28<00:01, 25.70it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:00, 30.15it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:00, 29.79it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 33.37it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 28.26it/s]
Loading 0:  98%|█████████▊| 354/363 [00:29<00:00, 27.97it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 19.64it/s]
Loading 0: 100%|█████████▉| 362/363 [00:30<00:00, 20.79it/s]
                                                            
Job chaiml-2a6f-69d4-linear-w01-v15-mkmlizer completed after 246.56s with status: succeeded
Stopping job with name chaiml-2a6f-69d4-linear-w01-v15-mkmlizer
Pipeline stage MKMLizer completed in 247.41s
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-2a6f-69d4-linear-w01-v15
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v15 to be ready
Inference service chaiml-2a6f-69d4-linear-w01-v15 ready after 170.95270085334778s
Pipeline stage MKMLDeployer completed in 171.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8689277172088623s
Received healthy response to inference request in 2.492626905441284s
Received healthy response to inference request in 2.5084877014160156s
Received healthy response to inference request in 2.1751105785369873s
Received healthy response to inference request in 2.476530075073242s
5 requests
0 failed requests
5th percentile: 2.2353944778442383
10th percentile: 2.2956783771514893
20th percentile: 2.416246175765991
30th percentile: 2.4797494411468506
40th percentile: 2.4861881732940674
50th percentile: 2.492626905441284
60th percentile: 2.4989712238311768
70th percentile: 2.5053155422210693
80th percentile: 2.580575704574585
90th percentile: 2.7247517108917236
95th percentile: 2.796839714050293
99th percentile: 2.8545101165771483
mean time: 2.5043365955352783
Pipeline stage StressChecker completed in 14.33s
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 0.76s
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 0.89s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v15 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-2a6f-69d4-linear-w01-v15-profiler
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v15-profiler to be ready
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 3112.95s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v15 status is now torndown due to DeploymentManager action