developer_uid: rirv938
submission_id: chaiml-ca18-c13f-linear-w01_v23
model_name: chaiml-ca18-c13f-linear-w01_v23
model_group: ChaiML/ca18-c13f-linear-
status: torndown
timestamp: 2025-12-12T18:27:00+00:00
num_battles: 5400
num_wins: 2659
celo_rating: 1292.0
family_friendly_score: 0.5216000000000001
family_friendly_standard_error: 0.007064466575757862
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': 0.8153549722721158, 'latency_mean': 1.2263635897636413, 'latency_p50': 1.2209765911102295, 'latency_p90': 1.3660769224166869}, {'batch_size': 4, 'throughput': 1.9177340168277832, 'latency_mean': 2.0807935667037962, 'latency_p50': 2.085418939590454, 'latency_p90': 2.302365636825561}, {'batch_size': 5, 'throughput': 2.1289436755781845, 'latency_mean': 2.336573543548584, 'latency_p50': 2.3326348066329956, 'latency_p90': 2.6556750297546388}, {'batch_size': 8, 'throughput': 2.4951009827849737, 'latency_mean': 3.174957325458527, 'latency_p50': 3.2206770181655884, 'latency_p90': 3.581560158729553}, {'batch_size': 10, 'throughput': 2.653471791038388, 'latency_mean': 3.7226821982860567, 'latency_p50': 3.7239362001419067, 'latency_p90': 4.27008330821991}, {'batch_size': 12, 'throughput': 2.7451548828285723, 'latency_mean': 4.312041476964951, 'latency_p50': 4.270642280578613, 'latency_p90': 4.994908785820007}, {'batch_size': 15, 'throughput': 2.8522024191635262, 'latency_mean': 5.197482353448867, 'latency_p50': 5.188435316085815, 'latency_p90': 6.031196641921997}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-ca18-c13f-linear-w01_v23
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: 2.68
us_pacific_date: 2025-11-26
win_ratio: 0.4924074074074074
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['You:', '</s>', '###', '\n'], '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-v23-mkmlizer
Waiting for job on chaiml-ca18-c13f-linear-w01-v23-mkmlizer to finish
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Downloaded to shared memory in 22.837s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Checking if ChaiML/ca18-c13f-linear-w01 already exists in ChaiML
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe0z1_39k, device:0
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: quantized model in 27.035s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Processed model ChaiML/ca18-c13f-linear-w01 in 49.872s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/config.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/special_tokens_map.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/tokenizer_config.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/tokenizer.json
Failed to get response for submission chaiml-7b07-69d4-linear-w01_v24: HTTPConnectionPool(host='chaiml-7b07-69d4-linear-w01-v24-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Stopping job with name chaiml-ca18-c13f-linear-w01-v23-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-ca18-c13f-linear-w01-v23-mkmlizer
Waiting for job on chaiml-ca18-c13f-linear-w01-v23-mkmlizer to finish
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ║                                                                     ║
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Downloaded to shared memory in 28.088s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Checking if ChaiML/ca18-c13f-linear-w01 already exists in ChaiML
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkwraj204, device:0
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: quantized model in 25.518s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Processed model ChaiML/ca18-c13f-linear-w01 in 53.606s
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/config.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/special_tokens_map.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/tokenizer_config.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/tokenizer.json
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-c13f-linear-w01-v23/nvidia/flywheel_model.0.safetensors
chaiml-ca18-c13f-linear-w01-v23-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:07,  2.68s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:18,  1.38it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:24,  4.14it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:50,  6.76it/s]
Loading 0:   7%|▋         | 26/363 [00:05<00:33, 10.13it/s]
Loading 0:   9%|▉         | 33/363 [00:05<00:22, 14.52it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:17, 18.33it/s]
Loading 0:  13%|█▎        | 47/363 [00:06<00:13, 23.24it/s]
Loading 0:  15%|█▍        | 53/363 [00:06<00:11, 28.10it/s]
Loading 0:  17%|█▋        | 60/363 [00:06<00:09, 32.09it/s]
Loading 0:  19%|█▉        | 69/363 [00:06<00:08, 34.20it/s]
Loading 0:  21%|██        | 77/363 [00:06<00:06, 41.86it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:06, 43.59it/s]
Loading 0:  25%|██▍       | 89/363 [00:07<00:05, 46.55it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 46.11it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 49.73it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 52.17it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 46.29it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:05, 47.03it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:05, 45.13it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 48.70it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:03, 55.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:03, 54.10it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:03, 54.63it/s]
Loading 0:  46%|████▋     | 168/363 [00:08<00:03, 51.01it/s]
Loading 0:  49%|████▉     | 177/363 [00:08<00:03, 52.77it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:03, 58.36it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:02, 57.98it/s]
Loading 0:  55%|█████▍    | 198/363 [00:09<00:02, 56.71it/s]
Loading 0:  56%|█████▌    | 204/363 [00:09<00:04, 37.94it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:03, 45.88it/s]
Loading 0:  60%|██████    | 218/363 [00:09<00:03, 46.79it/s]
Loading 0:  62%|██████▏   | 224/363 [00:09<00:02, 49.17it/s]
Loading 0:  64%|██████▎   | 231/363 [00:09<00:02, 47.72it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:02, 50.46it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:02, 57.15it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:01, 57.42it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:01, 57.95it/s]
Loading 0:  74%|███████▍  | 268/363 [00:10<00:01, 52.45it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:01, 56.69it/s]
Loading 0:  77%|███████▋  | 281/363 [00:10<00:01, 54.39it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 39.83it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 40.63it/s]
Loading 0:  83%|████████▎ | 302/363 [00:11<00:01, 48.59it/s]
Loading 0:  85%|████████▍ | 308/363 [00:11<00:01, 48.78it/s]
Loading 0:  87%|████████▋ | 314/363 [00:11<00:00, 50.38it/s]
Loading 0:  88%|████████▊ | 321/363 [00:11<00:00, 48.36it/s]
Loading 0:  91%|█████████ | 330/363 [00:11<00:00, 51.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 57.51it/s]
Loading 0:  95%|█████████▌| 345/363 [00:12<00:00, 57.59it/s]
Loading 0:  97%|█████████▋| 351/363 [00:12<00:00, 56.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:12<00:00, 50.69it/s]
                                                            

Job chaiml-ca18-c13f-linear-w01-v23-mkmlizer completed after 93.59s with status: succeeded
Stopping job with name chaiml-ca18-c13f-linear-w01-v23-mkmlizer
Pipeline stage MKMLizer completed in 229.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-c13f-linear-w01-v23
Waiting for inference service chaiml-ca18-c13f-linear-w01-v23 to be ready
Inference service chaiml-ca18-c13f-linear-w01-v23 ready after 160.69322156906128s
Pipeline stage MKMLDeployer completed in 161.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4417643547058105s
Received healthy response to inference request in 1.5491149425506592s
Received healthy response to inference request in 1.3112447261810303s
Received healthy response to inference request in 1.2614331245422363s
Received healthy response to inference request in 1.1715903282165527s
5 requests
0 failed requests
5th percentile: 1.1895588874816894
10th percentile: 1.2075274467468262
20th percentile: 1.2434645652770997
30th percentile: 1.2713954448699951
40th percentile: 1.2913200855255127
50th percentile: 1.3112447261810303
60th percentile: 1.3634525775909423
70th percentile: 1.4156604290008545
80th percentile: 1.4632344722747803
90th percentile: 1.5061747074127196
95th percentile: 1.5276448249816894
99th percentile: 1.5448209190368651
mean time: 1.3470294952392579
Pipeline stage StressChecker completed in 8.51s
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 0.70s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v23 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 2432.09s
Shutdown handler de-registered
chaiml-ca18-c13f-linear-w01_v23 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-c13f-linear-w01_v23 status is now torndown due to DeploymentManager action