chaiml-02f4-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-02f4-69d4-linear-w01_v38

model_name: chaiml-02f4-69d4-linear-w01_v38

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

status: torndown

timestamp: 2025-12-12T18:26:49+00:00

num_battles: 6319

num_wins: 3219

celo_rating: 1308.44

family_friendly_score: 0.4982

family_friendly_standard_error: 0.007071021991197595

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': 0.44161186815723363, 'latency_mean': 2.264334338903427, 'latency_p50': 2.2571510076522827, 'latency_p90': 2.5302262783050535}, {'batch_size': 3, 'throughput': 0.8990663848738694, 'latency_mean': 3.3150336599349974, 'latency_p50': 3.325640320777893, 'latency_p90': 3.6298949480056764}, {'batch_size': 5, 'throughput': 1.1952714873654613, 'latency_mean': 4.16292206287384, 'latency_p50': 4.151974201202393, 'latency_p90': 4.715449881553649}, {'batch_size': 6, 'throughput': 1.2865163734702645, 'latency_mean': 4.635396915674209, 'latency_p50': 4.603776574134827, 'latency_p90': 5.237528657913208}, {'batch_size': 8, 'throughput': 1.4374676720664392, 'latency_mean': 5.544483560323715, 'latency_p50': 5.4875757694244385, 'latency_p90': 6.295473432540893}, {'batch_size': 10, 'throughput': 1.5156393081957105, 'latency_mean': 6.539014675617218, 'latency_p50': 6.522998571395874, 'latency_p90': 7.652554273605347}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-02f4-69d4-linear-w01_v38

ineligible_reason: num_battles<10000

is_internal_developer: True

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

model_size: 24B

ranking_group: single

throughput_3p7s: 1.06

us_pacific_date: 2025-11-26

win_ratio: 0.5094160468428549

generation_params: {'temperature': 0.8, '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-v38-mkmlizer
Waiting for job on chaiml-02f4-69d4-linear-w01-v38-mkmlizer to finish
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  belonging to:                                                      ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: Downloaded to shared memory in 43.882s
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: Checking if ChaiML/02f4-69d4-linear-w01 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnl0jglae, device:0
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: quantized model in 41.766s
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: Processed model ChaiML/02f4-69d4-linear-w01 in 85.649s
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: creating bucket guanaco-mkml-models
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/config.json
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/tokenizer.json
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/flywheel_model.1.safetensors
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v38/nvidia/flywheel_model.0.safetensors
chaiml-02f4-69d4-linear-w01-v38-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:13,  2.86s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:39,  1.28it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:31,  3.81it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:03,  5.41it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:48,  7.04it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:39,  8.50it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:27, 12.20it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:24, 13.66it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 19.35it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 21.24it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:12, 26.04it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 27.06it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:12, 25.29it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:10, 27.54it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 29.76it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:10, 27.82it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:09, 30.26it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:08, 33.70it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:09, 29.41it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 37.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:09, 27.78it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:08, 29.76it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:08, 28.76it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 32.90it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 31.43it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 35.64it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 33.38it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.40it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 33.46it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:07, 28.55it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:07, 27.96it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 32.64it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 31.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 34.82it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 33.06it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 36.65it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 33.69it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:04, 37.60it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:07, 25.93it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 30.69it/s]
Loading 0:  52%|█████▏    | 188/363 [00:24<02:37,  1.11it/s]
Loading 0:  53%|█████▎    | 191/363 [00:24<02:01,  1.42it/s]
Loading 0:  54%|█████▎    | 195/363 [00:24<01:26,  1.95it/s]
Loading 0:  56%|█████▌    | 202/363 [00:24<00:48,  3.34it/s]
Loading 0:  57%|█████▋    | 206/363 [00:25<00:36,  4.33it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<00:25,  6.07it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:20,  7.12it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:14,  9.83it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:11, 11.93it/s]
Loading 0:  63%|██████▎   | 229/363 [00:25<00:08, 15.67it/s]
Loading 0:  64%|██████▍   | 233/363 [00:25<00:07, 17.80it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:05, 21.82it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:05, 22.90it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:04, 26.93it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:04, 27.11it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 24.78it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 23.79it/s]
Loading 0:  73%|███████▎  | 265/363 [00:26<00:03, 29.97it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:03, 29.16it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:02, 33.27it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 31.98it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 35.29it/s]
Loading 0:  79%|███████▉  | 287/363 [00:27<00:02, 32.99it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:01, 36.56it/s]
Loading 0:  82%|████████▏ | 296/363 [00:27<00:02, 25.70it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 30.12it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:01, 29.88it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:01, 34.34it/s]
Loading 0:  87%|████████▋ | 314/363 [00:28<00:01, 32.14it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 35.40it/s]
Loading 0:  89%|████████▉ | 323/363 [00:28<00:01, 32.87it/s]
Loading 0:  90%|█████████ | 328/363 [00:28<00:00, 36.42it/s]
Loading 0:  91%|█████████▏| 332/363 [00:29<00:01, 21.36it/s]
Loading 0:  93%|█████████▎| 337/363 [00:29<00:01, 25.39it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:00, 26.18it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 30.33it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 29.85it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 33.65it/s]
Loading 0:  99%|█████████▉| 359/363 [00:29<00:00, 31.70it/s]
                                                            
Job chaiml-02f4-69d4-linear-w01-v38-mkmlizer completed after 236.57s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v38-mkmlizer
Pipeline stage MKMLizer completed in 237.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-02f4-69d4-linear-w01-v38
Waiting for inference service chaiml-02f4-69d4-linear-w01-v38 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v38 ready after 160.9923861026764s
Pipeline stage MKMLDeployer completed in 162.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0068933963775635s
Received healthy response to inference request in 1.842858076095581s
Received healthy response to inference request in 1.7282636165618896s
Received healthy response to inference request in 1.7213249206542969s
Received healthy response to inference request in 1.7975010871887207s
5 requests
0 failed requests
5th percentile: 1.7227126598358153
10th percentile: 1.724100399017334
20th percentile: 1.7268758773803712
30th percentile: 1.7421111106872558
40th percentile: 1.7698060989379882
50th percentile: 1.7975010871887207
60th percentile: 1.815643882751465
70th percentile: 1.833786678314209
80th percentile: 1.8756651401519775
90th percentile: 1.9412792682647706
95th percentile: 1.974086332321167
99th percentile: 2.000331983566284
mean time: 1.8193682193756104
Pipeline stage StressChecker completed in 10.32s
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 0.64s
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 0.62s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v38 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 0.11s
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-v38-profiler
Waiting for inference service chaiml-02f4-69d4-linear-w01-v38-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 3074.86s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v38 status is now inactive due to auto deactivation removed underperforming models
chaiml-02f4-69d4-linear-w01_v38 status is now torndown due to DeploymentManager action