chaiml-2fe5-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-2fe5-c13f-linear-w01_v28

model_name: chaiml-2fe5-c13f-linear-w01_v28

model_group: ChaiML/2fe5-c13f-linear-

status: torndown

timestamp: 2025-12-12T18:26:54+00:00

num_battles: 6722

num_wins: 3426

celo_rating: 1300.69

family_friendly_score: 0.5332

family_friendly_standard_error: 0.00705546256456655

submission_type: basic

model_repo: ChaiML/2fe5-c13f-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 10

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.7812174087075302, 'latency_mean': 1.2799344229698182, 'latency_p50': 1.281432867050171, 'latency_p90': 1.4255113363265992}, {'batch_size': 4, 'throughput': 1.8845221989094278, 'latency_mean': 2.111548367738724, 'latency_p50': 2.1268078088760376, 'latency_p90': 2.3502912282943726}, {'batch_size': 5, 'throughput': 2.089917775743237, 'latency_mean': 2.3701530826091766, 'latency_p50': 2.396249532699585, 'latency_p90': 2.6674003124237062}, {'batch_size': 8, 'throughput': 2.470565513338028, 'latency_mean': 3.2038864028453826, 'latency_p50': 3.1969233751296997, 'latency_p90': 3.5838806152343747}, {'batch_size': 10, 'throughput': 2.6398240730723352, 'latency_mean': 3.7583742225170136, 'latency_p50': 3.7409310340881348, 'latency_p90': 4.288687133789062}, {'batch_size': 12, 'throughput': 2.713367403766821, 'latency_mean': 4.382317699193955, 'latency_p50': 4.3709046840667725, 'latency_p90': 4.934919953346252}, {'batch_size': 15, 'throughput': 2.7445982365945336, 'latency_mean': 5.399559413194656, 'latency_p50': 5.350645542144775, 'latency_p90': 6.347281455993652}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-2fe5-c13f-linear-w01_v28

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/2fe5-c13f-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 2.65

us_pacific_date: 2025-11-26

win_ratio: 0.5096697411484677

generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####', '<|eot_id|>', 'Bot:', '<|im_end|>', '\n', 'You:', '</s>', 'User:'], 'max_input_tokens': 1024, 'best_of': 10, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", '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-2fe5-c13f-linear-w01-v28-mkmlizer
Waiting for job on chaiml-2fe5-c13f-linear-w01-v28-mkmlizer to finish
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  belonging to:                                                      ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: Downloaded to shared memory in 29.671s
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: Checking if ChaiML/2fe5-c13f-linear-w01 already exists in ChaiML
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoosatmtb, device:0
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: quantized model in 25.938s
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: Processed model ChaiML/2fe5-c13f-linear-w01 in 55.609s
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia/special_tokens_map.json
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia/config.json
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia/tokenizer_config.json
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia/tokenizer.json
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v28/nvidia/flywheel_model.0.safetensors
chaiml-2fe5-c13f-linear-w01-v28-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:21,  2.72s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:21,  1.36it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:25,  4.08it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:51,  6.63it/s]
Loading 0:   7%|▋         | 25/363 [00:05<00:36,  9.30it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 14.32it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.76it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:14, 21.29it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 24.95it/s]
Loading 0:  17%|█▋        | 60/363 [00:06<00:09, 31.95it/s]
Loading 0:  19%|█▉        | 69/363 [00:06<00:07, 37.74it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:06, 45.14it/s]
Loading 0:  23%|██▎       | 83/363 [00:07<00:06, 45.76it/s]
Loading 0:  25%|██▍       | 89/363 [00:07<00:05, 48.09it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 46.64it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 49.68it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 51.67it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 46.39it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:05, 47.05it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:05, 44.68it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:04, 52.58it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:04, 51.23it/s]
Loading 0:  42%|████▏     | 152/363 [00:08<00:04, 51.90it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:04, 48.55it/s]
Loading 0:  46%|████▌     | 167/363 [00:08<00:03, 55.57it/s]
Loading 0:  48%|████▊     | 173/363 [00:08<00:03, 53.34it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:03, 53.26it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:03, 54.21it/s]
Loading 0:  53%|█████▎    | 191/363 [00:09<00:03, 51.12it/s]
Loading 0:  54%|█████▍    | 197/363 [00:09<00:03, 50.92it/s]
Loading 0:  56%|█████▌    | 203/363 [00:09<00:04, 39.26it/s]
Loading 0:  58%|█████▊    | 209/363 [00:09<00:03, 40.28it/s]
Loading 0:  59%|█████▉    | 214/363 [00:09<00:03, 41.31it/s]
Loading 0:  61%|██████    | 222/363 [00:10<00:03, 43.59it/s]
Loading 0:  63%|██████▎   | 230/363 [00:10<00:02, 51.05it/s]
Loading 0:  65%|██████▌   | 236/363 [00:10<00:02, 49.68it/s]
Loading 0:  67%|██████▋   | 242/363 [00:10<00:02, 51.50it/s]
Loading 0:  69%|██████▊   | 249/363 [00:10<00:02, 49.10it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:01, 56.51it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:01, 54.39it/s]
Loading 0:  74%|███████▍  | 269/363 [00:10<00:01, 55.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:01, 56.31it/s]
Loading 0:  77%|███████▋  | 281/363 [00:11<00:01, 53.42it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 38.95it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 39.88it/s]
Loading 0:  83%|████████▎ | 301/363 [00:11<00:01, 40.52it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:01, 44.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:11<00:01, 40.58it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:00, 49.24it/s]
Loading 0:  90%|████████▉ | 326/363 [00:12<00:00, 48.58it/s]
Loading 0:  91%|█████████▏| 332/363 [00:12<00:00, 50.09it/s]
Loading 0:  93%|█████████▎| 339/363 [00:12<00:00, 47.06it/s]
Loading 0:  96%|█████████▌| 348/363 [00:12<00:00, 49.87it/s]
Loading 0:  98%|█████████▊| 356/363 [00:12<00:00, 56.39it/s]
Loading 0: 100%|█████████▉| 362/363 [00:12<00:00, 54.06it/s]
                                                            
Job chaiml-2fe5-c13f-linear-w01-v28-mkmlizer completed after 154.72s with status: succeeded
Stopping job with name chaiml-2fe5-c13f-linear-w01-v28-mkmlizer
Pipeline stage MKMLizer completed in 155.26s
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-2fe5-c13f-linear-w01-v28
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v28 to be ready
Inference service chaiml-2fe5-c13f-linear-w01-v28 ready after 160.720556974411s
Pipeline stage MKMLDeployer completed in 161.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.156541347503662s
Received healthy response to inference request in 2.2684648036956787s
Received healthy response to inference request in 1.2547531127929688s
Received healthy response to inference request in 1.3928697109222412s
Received healthy response to inference request in 1.2342698574066162s
5 requests
0 failed requests
5th percentile: 1.172087049484253
10th percentile: 1.1876327514648437
20th percentile: 1.2187241554260253
30th percentile: 1.2383665084838866
40th percentile: 1.2465598106384277
50th percentile: 1.2547531127929688
60th percentile: 1.3099997520446778
70th percentile: 1.3652463912963866
80th percentile: 1.5679887294769288
90th percentile: 1.9182267665863038
95th percentile: 2.093345785140991
99th percentile: 2.233440999984741
mean time: 1.4613797664642334
Pipeline stage StressChecker completed in 8.99s
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 0.63s
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 0.59s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v28 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 2385.25s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v28 status is now inactive due to auto deactivation removed underperforming models
chaiml-2fe5-c13f-linear-w01_v28 status is now torndown due to DeploymentManager action