chaiml-4d70-fd43-linear-w01

developer_uid: rirv938

submission_id: chaiml-4d70-fd43-linear-w01_v15

model_name: chaiml-4d70-fd43-linear-w01_v15

model_group: ChaiML/4d70-fd43-linear-

status: torndown

timestamp: 2025-12-12T18:26:55+00:00

num_battles: 6477

num_wins: 3421

celo_rating: 1314.58

family_friendly_score: 0.5024

family_friendly_standard_error: 0.007070986352695075

submission_type: basic

model_repo: ChaiML/4d70-fd43-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1800

max_output_tokens: 74

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6262453520955423, 'latency_mean': 1.5967095375061036, 'latency_p50': 1.6009290218353271, 'latency_p90': 1.738705015182495}, {'batch_size': 3, 'throughput': 1.2631290340941776, 'latency_mean': 2.3694973504543304, 'latency_p50': 2.37428617477417, 'latency_p90': 2.563967180252075}, {'batch_size': 5, 'throughput': 1.5842630488926517, 'latency_mean': 3.135756204128265, 'latency_p50': 3.132018208503723, 'latency_p90': 3.5280323266983027}, {'batch_size': 6, 'throughput': 1.6880339411412832, 'latency_mean': 3.5233639693260193, 'latency_p50': 3.515150308609009, 'latency_p90': 3.945989918708801}, {'batch_size': 8, 'throughput': 1.8623469269773147, 'latency_mean': 4.276542373895645, 'latency_p50': 4.2459129095077515, 'latency_p90': 4.888707089424133}, {'batch_size': 10, 'throughput': 1.9245965424435607, 'latency_mean': 5.164069684743882, 'latency_p50': 5.1948559284210205, 'latency_p90': 5.812539505958557}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-4d70-fd43-linear-w01_v15

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/4d70-fd43-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2025-11-26

win_ratio: 0.528176624980701

generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['\n', '<|im_end|>', '</s>', '###', '<|im_start|>'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}

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-4d70-fd43-linear-w01-v15-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v15-mkmlizer to finish
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  belonging to:                                                      ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: Downloaded to shared memory in 31.862s
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w01 already exists in ChaiML
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp742b3b06, device:0
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: quantized model in 29.966s
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w01 in 61.828s
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia/config.json
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia/tokenizer_config.json
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v15/nvidia/flywheel_model.0.safetensors
chaiml-4d70-fd43-linear-w01-v15-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:40,  2.94s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:43,  1.26it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:04,  2.82it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:18,  4.42it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:38,  8.77it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:27, 12.20it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.50it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.43it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.90it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.30it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 31.01it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.75it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 38.61it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 40.34it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:06, 40.06it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:06, 40.33it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:05, 46.33it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:05, 44.78it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 44.55it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 49.63it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 45.99it/s]
Loading 0:  34%|███▍      | 124/363 [00:08<00:07, 31.87it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 38.71it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 39.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 40.14it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 45.47it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 43.60it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 42.72it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:04, 47.11it/s]
Loading 0:  48%|████▊     | 173/363 [00:09<00:04, 45.07it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 44.42it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 48.81it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 46.47it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:03, 45.31it/s]
Loading 0:  56%|█████▌    | 202/363 [00:10<00:04, 34.51it/s]
Loading 0:  57%|█████▋    | 206/363 [00:10<00:04, 34.55it/s]
Loading 0:  58%|█████▊    | 212/363 [00:10<00:03, 38.87it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 39.42it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 40.45it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 45.78it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 44.06it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 43.96it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 48.52it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 46.04it/s]
Loading 0:  71%|███████▏  | 259/363 [00:11<00:02, 45.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:01, 49.98it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:01, 47.07it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 45.66it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 35.30it/s]
Loading 0:  79%|███████▉  | 287/363 [00:12<00:02, 35.19it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:01, 39.28it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 39.92it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 40.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 45.80it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 44.28it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 43.38it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 48.56it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:00, 46.35it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 45.03it/s]
Loading 0:  96%|█████████▌| 347/363 [00:13<00:00, 49.35it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 47.67it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 46.07it/s]
                                                            
Job chaiml-4d70-fd43-linear-w01-v15-mkmlizer completed after 174.77s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v15-mkmlizer
Pipeline stage MKMLizer completed in 175.37s
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-4d70-fd43-linear-w01-v15
Waiting for inference service chaiml-4d70-fd43-linear-w01-v15 to be ready
Inference service chaiml-4d70-fd43-linear-w01-v15 ready after 161.05570006370544s
Pipeline stage MKMLDeployer completed in 161.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6291372776031494s
Received healthy response to inference request in 1.4597022533416748s
Received healthy response to inference request in 1.5073802471160889s
Received healthy response to inference request in 1.6411831378936768s
Received healthy response to inference request in 1.4747858047485352s
5 requests
0 failed requests
5th percentile: 1.4627189636230469
10th percentile: 1.465735673904419
20th percentile: 1.471769094467163
30th percentile: 1.481304693222046
40th percentile: 1.4943424701690673
50th percentile: 1.5073802471160889
60th percentile: 1.5560830593109132
70th percentile: 1.6047858715057373
80th percentile: 1.6315464496612548
90th percentile: 1.636364793777466
95th percentile: 1.6387739658355713
99th percentile: 1.6407013034820557
mean time: 1.542437744140625
Pipeline stage StressChecker completed in 9.18s
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 0.58s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v15 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 2505.60s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v15 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w01_v15 status is now torndown due to DeploymentManager action