chaiml-ca18-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-ca18-c13f-linear-w01_v22

model_name: chaiml-ca18-c13f-linear-w01_v22

model_group: ChaiML/ca18-c13f-linear-

status: torndown

timestamp: 2025-12-12T18:26:59+00:00

num_battles: 5383

num_wins: 2668

celo_rating: 1294.83

family_friendly_score: 0.5182

family_friendly_standard_error: 0.0070663818181584265

submission_type: basic

model_repo: ChaiML/ca18-c13f-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 7

max_input_tokens: 1280

max_output_tokens: 60

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.803655420598238, 'latency_mean': 1.2442177629470825, 'latency_p50': 1.2491034269332886, 'latency_p90': 1.3855520725250243}, {'batch_size': 4, 'throughput': 1.9293813296753246, 'latency_mean': 2.060785188674927, 'latency_p50': 2.065794348716736, 'latency_p90': 2.3259406328201293}, {'batch_size': 5, 'throughput': 2.1572473952720665, 'latency_mean': 2.3060431659221647, 'latency_p50': 2.3121907711029053, 'latency_p90': 2.5901931047439573}, {'batch_size': 8, 'throughput': 2.5203005818062345, 'latency_mean': 3.1443916273117067, 'latency_p50': 3.1343319416046143, 'latency_p90': 3.534774136543274}, {'batch_size': 10, 'throughput': 2.6924219176402637, 'latency_mean': 3.6733843171596527, 'latency_p50': 3.6797107458114624, 'latency_p90': 4.137454056739807}, {'batch_size': 12, 'throughput': 2.7853526411264578, 'latency_mean': 4.2593031287193295, 'latency_p50': 4.267003893852234, 'latency_p90': 4.941052436828613}, {'batch_size': 15, 'throughput': 2.8695883620367555, 'latency_mean': 5.157659765481949, 'latency_p50': 5.150001287460327, 'latency_p90': 5.995152521133423}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ca18-c13f-linear-w01_v22

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/ca18-c13f-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 2.73

us_pacific_date: 2025-11-26

win_ratio: 0.4956344046070964

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['###', '\n', 'You:', '</s>'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 60}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-ca18-c13f-linear-w01-v22-mkmlizer
Waiting for job on chaiml-ca18-c13f-linear-w01-v22-mkmlizer to finish
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: Downloaded to shared memory in 29.638s
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: Checking if ChaiML/ca18-c13f-linear-w01 already exists in ChaiML
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjdjqx_vh, device:0
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: quantized model in 25.433s
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: Processed model ChaiML/ca18-c13f-linear-w01 in 55.071s
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia/special_tokens_map.json
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia/config.json
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia/tokenizer_config.json
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia/tokenizer.json
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v22/nvidia/flywheel_model.0.safetensors
chaiml-ca18-c13f-linear-w01-v22-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:19,  2.71s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:21,  1.37it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:25,  4.09it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:51,  6.68it/s]
Loading 0:   7%|▋         | 25/363 [00:05<00:35,  9.39it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:22, 14.54it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:17, 18.02it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:14, 21.58it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 25.38it/s]
Loading 0:  17%|█▋        | 60/363 [00:06<00:09, 32.49it/s]
Loading 0:  19%|█▉        | 69/363 [00:06<00:07, 38.33it/s]
Loading 0:  21%|██        | 77/363 [00:06<00:06, 45.77it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:05, 46.85it/s]
Loading 0:  25%|██▍       | 89/363 [00:07<00:05, 48.07it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 47.49it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 50.30it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 52.53it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 45.95it/s]
Loading 0:  35%|███▍      | 127/363 [00:07<00:04, 48.43it/s]
Loading 0:  37%|███▋      | 133/363 [00:08<00:04, 46.86it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 48.38it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:03, 55.47it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:03, 53.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:03, 54.69it/s]
Loading 0:  46%|████▋     | 168/363 [00:08<00:03, 51.32it/s]
Loading 0:  49%|████▉     | 177/363 [00:08<00:03, 53.14it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:03, 59.21it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:02, 58.58it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:02, 58.92it/s]
Loading 0:  57%|█████▋    | 206/363 [00:09<00:03, 41.59it/s]
Loading 0:  59%|█████▊    | 213/363 [00:09<00:03, 42.60it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:03, 46.68it/s]
Loading 0:  64%|██████▎   | 231/363 [00:10<00:02, 48.96it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:02, 50.42it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:02, 56.30it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:01, 56.72it/s]
Loading 0:  72%|███████▏  | 261/363 [00:10<00:01, 56.03it/s]
Loading 0:  74%|███████▎  | 267/363 [00:10<00:01, 51.05it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:01, 57.94it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:01, 57.86it/s]
Loading 0:  79%|███████▉  | 288/363 [00:11<00:01, 42.41it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 41.86it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 46.31it/s]
Loading 0:  86%|████████▌ | 312/363 [00:11<00:01, 49.05it/s]
Loading 0:  88%|████████▊ | 321/363 [00:11<00:00, 51.21it/s]
Loading 0:  91%|█████████ | 330/363 [00:11<00:00, 53.20it/s]
Loading 0:  93%|█████████▎| 339/363 [00:12<00:00, 54.35it/s]
Loading 0:  96%|█████████▌| 348/363 [00:12<00:00, 54.95it/s]
Loading 0:  98%|█████████▊| 356/363 [00:12<00:00, 60.24it/s]
Loading 0: 100%|██████████| 363/363 [00:12<00:00, 59.90it/s]
                                                            
Job chaiml-ca18-c13f-linear-w01-v22-mkmlizer completed after 164.98s with status: succeeded
Stopping job with name chaiml-ca18-c13f-linear-w01-v22-mkmlizer
Pipeline stage MKMLizer completed in 165.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-c13f-linear-w01-v22
Waiting for inference service chaiml-ca18-c13f-linear-w01-v22 to be ready
Inference service chaiml-ca18-c13f-linear-w01-v22 ready after 160.91181707382202s
Pipeline stage MKMLDeployer completed in 161.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.380491018295288s
Received healthy response to inference request in 1.1687023639678955s
Received healthy response to inference request in 1.4190387725830078s
Received healthy response to inference request in 1.1573050022125244s
Received healthy response to inference request in 1.527660608291626s
5 requests
0 failed requests
5th percentile: 1.1595844745635986
10th percentile: 1.1618639469146728
20th percentile: 1.1664228916168213
30th percentile: 1.211060094833374
40th percentile: 1.295775556564331
50th percentile: 1.380491018295288
60th percentile: 1.395910120010376
70th percentile: 1.4113292217254638
80th percentile: 1.4407631397247314
90th percentile: 1.4842118740081787
95th percentile: 1.5059362411499024
99th percentile: 1.5233157348632813
mean time: 1.3306395530700683
Pipeline stage StressChecker completed in 7.97s
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 0.71s
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 0.91s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v22 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-c13f-linear-w01-v22-profiler
Waiting for inference service chaiml-ca18-c13f-linear-w01-v22-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 2397.49s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v22 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-c13f-linear-w01_v22 status is now torndown due to DeploymentManager action