chaiml-02f4-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-02f4-69d4-linear-w01_v37

model_name: chaiml-02f4-69d4-linear-w01_v37

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

status: torndown

timestamp: 2025-12-12T18:26:48+00:00

num_battles: 6517

num_wins: 3364

celo_rating: 1317.06

family_friendly_score: 0.49239999999999995

family_friendly_standard_error: 0.007070250914925156

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': 0.4385516405220673, 'latency_mean': 2.280113776922226, 'latency_p50': 2.2917909622192383, 'latency_p90': 2.5329389333724976}, {'batch_size': 3, 'throughput': 0.9234110519868644, 'latency_mean': 3.2415705120563505, 'latency_p50': 3.248194456100464, 'latency_p90': 3.5568957805633543}, {'batch_size': 5, 'throughput': 1.2252898884839885, 'latency_mean': 4.0619344234466555, 'latency_p50': 4.0576746463775635, 'latency_p90': 4.559763479232788}, {'batch_size': 6, 'throughput': 1.3080978402109877, 'latency_mean': 4.547686793804169, 'latency_p50': 4.530213832855225, 'latency_p90': 5.1524818420410154}, {'batch_size': 8, 'throughput': 1.4670423298321056, 'latency_mean': 5.4163551211357115, 'latency_p50': 5.430481314659119, 'latency_p90': 6.200296878814697}, {'batch_size': 10, 'throughput': 1.559256309763512, 'latency_mean': 6.34956295132637, 'latency_p50': 6.315960049629211, 'latency_p90': 7.2622403383255}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-02f4-69d4-linear-w01_v37

ineligible_reason: num_battles<10000

is_internal_developer: True

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

model_size: 24B

ranking_group: single

throughput_3p7s: 1.11

us_pacific_date: 2025-11-26

win_ratio: 0.5161884302593218

generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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-v37-mkmlizer
Waiting for job on chaiml-02f4-69d4-linear-w01-v37-mkmlizer to finish
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  belonging to:                                                      ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: Downloaded to shared memory in 48.616s
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: Checking if ChaiML/02f4-69d4-linear-w01 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp80pwrqon, device:0
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: quantized model in 41.001s
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: Processed model ChaiML/02f4-69d4-linear-w01 in 89.618s
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: creating bucket guanaco-mkml-models
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/config.json
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/tokenizer.json
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/flywheel_model.1.safetensors
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v37/nvidia/flywheel_model.0.safetensors
chaiml-02f4-69d4-linear-w01-v37-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:30,  2.74s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:28,  1.33it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:28,  3.96it/s]
Loading 0:   5%|▍         | 18/363 [00:05<01:01,  5.59it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:46,  7.26it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:38,  8.73it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:24, 13.44it/s]
Loading 0:  10%|▉         | 35/363 [00:06<00:20, 15.84it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:15, 20.31it/s]
Loading 0:  12%|█▏        | 44/363 [00:06<00:14, 22.06it/s]
Loading 0:  13%|█▎        | 49/363 [00:06<00:11, 26.89it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 27.14it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:11, 25.55it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:10, 27.89it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 30.18it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 31.96it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:08, 33.73it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:07, 37.22it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 35.62it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 36.12it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:07, 36.68it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:09, 27.64it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:08, 29.80it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:08, 31.80it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:07, 33.33it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:07, 34.33it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:06, 35.53it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:06, 36.02it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.80it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 35.62it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:07, 28.45it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:07, 28.28it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:06, 32.49it/s]
Loading 0:  42%|████▏     | 153/363 [00:10<00:06, 34.09it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:05, 34.44it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 34.96it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 35.34it/s]
Loading 0:  47%|████▋     | 171/363 [00:10<00:05, 36.30it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:05, 32.79it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:07, 24.08it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:06, 28.88it/s]
Loading 0:  52%|█████▏    | 189/363 [00:23<02:31,  1.15it/s]
Loading 0:  53%|█████▎    | 193/363 [00:24<01:49,  1.55it/s]
Loading 0:  54%|█████▍    | 196/363 [00:24<01:25,  1.96it/s]
Loading 0:  56%|█████▌    | 202/363 [00:24<00:50,  3.16it/s]
Loading 0:  57%|█████▋    | 206/363 [00:24<00:37,  4.18it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<00:25,  5.95it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:20,  7.09it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:13, 10.23it/s]
Loading 0:  62%|██████▏   | 225/363 [00:25<00:11, 11.68it/s]
Loading 0:  63%|██████▎   | 229/363 [00:25<00:09, 14.23it/s]
Loading 0:  64%|██████▍   | 233/363 [00:25<00:07, 16.53it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:05, 21.13it/s]
Loading 0:  67%|██████▋   | 242/363 [00:25<00:05, 22.72it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:04, 27.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:25<00:04, 26.75it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 24.56it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 23.71it/s]
Loading 0:  73%|███████▎  | 265/363 [00:26<00:03, 30.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:26<00:03, 29.78it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:02, 33.93it/s]
Loading 0:  77%|███████▋  | 278/363 [00:26<00:02, 32.77it/s]
Loading 0:  78%|███████▊  | 283/363 [00:26<00:02, 36.12it/s]
Loading 0:  79%|███████▉  | 287/363 [00:27<00:02, 33.85it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:01, 37.33it/s]
Loading 0:  82%|████████▏ | 296/363 [00:27<00:02, 26.59it/s]
Loading 0:  83%|████████▎ | 301/363 [00:27<00:01, 31.21it/s]
Loading 0:  84%|████████▍ | 305/363 [00:27<00:01, 30.79it/s]
Loading 0:  86%|████████▌ | 311/363 [00:27<00:01, 34.30it/s]
Loading 0:  87%|████████▋ | 315/363 [00:27<00:01, 35.28it/s]
Loading 0:  88%|████████▊ | 320/363 [00:28<00:01, 35.55it/s]
Loading 0:  89%|████████▉ | 324/363 [00:28<00:01, 36.53it/s]
Loading 0:  91%|█████████ | 329/363 [00:28<00:00, 36.87it/s]
Loading 0:  92%|█████████▏| 333/363 [00:28<00:01, 28.19it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 30.81it/s]
Loading 0:  94%|█████████▍| 342/363 [00:28<00:00, 32.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 33.29it/s]
Loading 0:  97%|█████████▋| 351/363 [00:29<00:00, 34.34it/s]
Loading 0:  98%|█████████▊| 356/363 [00:29<00:00, 34.87it/s]
Loading 0:  99%|█████████▉| 360/363 [00:29<00:00, 35.42it/s]
                                                            
Job chaiml-02f4-69d4-linear-w01-v37-mkmlizer completed after 236.47s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v37-mkmlizer
Pipeline stage MKMLizer completed in 237.07s
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-v37
Waiting for inference service chaiml-02f4-69d4-linear-w01-v37 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v37 ready after 161.61666011810303s
Pipeline stage MKMLDeployer completed in 162.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.579244375228882s
Received healthy response to inference request in 2.4569356441497803s
Received healthy response to inference request in 2.6777899265289307s
Received healthy response to inference request in 2.2529349327087402s
Received healthy response to inference request in 2.2756879329681396s
5 requests
0 failed requests
5th percentile: 2.25748553276062
10th percentile: 2.2620361328125
20th percentile: 2.27113733291626
30th percentile: 2.3119374752044677
40th percentile: 2.384436559677124
50th percentile: 2.4569356441497803
60th percentile: 2.505859136581421
70th percentile: 2.5547826290130615
80th percentile: 2.5989534854888916
90th percentile: 2.638371706008911
95th percentile: 2.658080816268921
99th percentile: 2.673848104476929
mean time: 2.4485185623168944
Pipeline stage StressChecker completed in 14.45s
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 0.60s
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 0.61s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v37 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 3152.58s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v37 status is now inactive due to auto deactivation removed underperforming models
chaiml-02f4-69d4-linear-w01_v37 status is now torndown due to DeploymentManager action