chaiml-2fe5-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-2fe5-c13f-linear-w01_v25

model_name: chaiml-2fe5-c13f-linear-w01_v25

model_group: ChaiML/2fe5-c13f-linear-

status: torndown

timestamp: 2025-12-12T18:26:53+00:00

num_battles: 6634

num_wins: 3394

celo_rating: 1304.44

family_friendly_score: 0.5382

family_friendly_standard_error: 0.007050400839668621

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': 0.7798708430210675, 'latency_mean': 1.2821649610996246, 'latency_p50': 1.295634388923645, 'latency_p90': 1.4159358501434327}, {'batch_size': 4, 'throughput': 1.893113739329933, 'latency_mean': 2.0950855875015257, 'latency_p50': 2.1016149520874023, 'latency_p90': 2.347331142425537}, {'batch_size': 5, 'throughput': 2.126321527238727, 'latency_mean': 2.3477958381175994, 'latency_p50': 2.3363988399505615, 'latency_p90': 2.6601362943649294}, {'batch_size': 8, 'throughput': 2.506650509245858, 'latency_mean': 3.1667241728305817, 'latency_p50': 3.1767133474349976, 'latency_p90': 3.5984543323516847}, {'batch_size': 10, 'throughput': 2.6479091201689084, 'latency_mean': 3.731575177907944, 'latency_p50': 3.7275644540786743, 'latency_p90': 4.25307068824768}, {'batch_size': 12, 'throughput': 2.7400182991734954, 'latency_mean': 4.3257956266403195, 'latency_p50': 4.300211668014526, 'latency_p90': 4.97581045627594}, {'batch_size': 15, 'throughput': 2.7562974424895517, 'latency_mean': 5.3615812861919405, 'latency_p50': 5.387494683265686, 'latency_p90': 6.260068106651306}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-2fe5-c13f-linear-w01_v25

ineligible_reason: num_battles<10000

is_internal_developer: True

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

model_size: 13B

ranking_group: single

throughput_3p7s: 2.67

us_pacific_date: 2025-11-26

win_ratio: 0.5116068736810371

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'User:', '<|im_end|>', '####', '</s>', '<|eot_id|>', 'Bot:', 'You:'], '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-v25-mkmlizer
Waiting for job on chaiml-2fe5-c13f-linear-w01-v25-mkmlizer to finish
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  belonging to:                                                      ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: Downloaded to shared memory in 23.853s
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: Checking if ChaiML/2fe5-c13f-linear-w01 already exists in ChaiML
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplk1t4g58, device:0
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: quantized model in 25.850s
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: Processed model ChaiML/2fe5-c13f-linear-w01 in 49.703s
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia/config.json
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia/special_tokens_map.json
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia/tokenizer_config.json
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia/tokenizer.json
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v25/nvidia/flywheel_model.0.safetensors
chaiml-2fe5-c13f-linear-w01-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:23,  2.72s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:22,  1.36it/s]
Loading 0:   4%|▎         | 13/363 [00:05<01:33,  3.74it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:50,  6.73it/s]
Loading 0:   7%|▋         | 26/363 [00:05<00:33, 10.01it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 14.28it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:06<00:14, 21.78it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 24.28it/s]
Loading 0:  16%|█▋        | 59/363 [00:06<00:09, 32.79it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:08, 36.12it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:07, 40.41it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:06, 41.92it/s]
Loading 0:  24%|██▍       | 87/363 [00:07<00:05, 46.39it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 49.65it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 51.17it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 52.95it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 45.87it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:05, 46.74it/s]
Loading 0:  37%|███▋      | 134/363 [00:08<00:04, 49.01it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 47.26it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:03, 54.31it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:03, 52.81it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:03, 53.81it/s]
Loading 0:  46%|████▋     | 168/363 [00:08<00:03, 50.15it/s]
Loading 0:  49%|████▉     | 177/363 [00:09<00:03, 52.45it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:03, 58.51it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:02, 58.23it/s]
Loading 0:  55%|█████▍    | 198/363 [00:09<00:02, 55.51it/s]
Loading 0:  56%|█████▌    | 204/363 [00:09<00:04, 37.30it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:03, 45.49it/s]
Loading 0:  60%|██████    | 218/363 [00:09<00:03, 46.46it/s]
Loading 0:  62%|██████▏   | 224/363 [00:09<00:02, 49.04it/s]
Loading 0:  64%|██████▎   | 231/363 [00:10<00:02, 47.63it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:02, 50.59it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:02, 57.13it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:01, 56.92it/s]
Loading 0:  72%|███████▏  | 261/363 [00:10<00:01, 55.25it/s]
Loading 0:  74%|███████▎  | 267/363 [00:10<00:01, 50.27it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:01, 57.01it/s]
Loading 0:  77%|███████▋  | 281/363 [00:11<00:01, 54.09it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 40.06it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 41.32it/s]
Loading 0:  83%|████████▎ | 302/363 [00:11<00:01, 49.38it/s]
Loading 0:  85%|████████▍ | 308/363 [00:11<00:01, 49.48it/s]
Loading 0:  87%|████████▋ | 314/363 [00:11<00:00, 50.99it/s]
Loading 0:  88%|████████▊ | 321/363 [00:11<00:00, 49.02it/s]
Loading 0:  91%|█████████ | 330/363 [00:12<00:00, 51.49it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 57.98it/s]
Loading 0:  95%|█████████▌| 345/363 [00:12<00:00, 57.88it/s]
Loading 0:  97%|█████████▋| 352/363 [00:12<00:00, 58.67it/s]
Loading 0:  99%|█████████▉| 359/363 [00:12<00:00, 53.41it/s]
                                                            
Job chaiml-2fe5-c13f-linear-w01-v25-mkmlizer completed after 164.72s with status: succeeded
Stopping job with name chaiml-2fe5-c13f-linear-w01-v25-mkmlizer
Pipeline stage MKMLizer completed in 165.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.57s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2fe5-c13f-linear-w01-v25
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v25 to be ready
Inference service chaiml-2fe5-c13f-linear-w01-v25 ready after 161.17807054519653s
Pipeline stage MKMLDeployer completed in 162.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4957923889160156s
Received healthy response to inference request in 1.8704349994659424s
Received healthy response to inference request in 1.2667622566223145s
Received healthy response to inference request in 1.2516026496887207s
Received healthy response to inference request in 1.8797407150268555s
5 requests
0 failed requests
5th percentile: 1.2546345710754394
10th percentile: 1.2576664924621581
20th percentile: 1.2637303352355957
30th percentile: 1.3125682830810548
40th percentile: 1.4041803359985352
50th percentile: 1.4957923889160156
60th percentile: 1.6456494331359863
70th percentile: 1.795506477355957
80th percentile: 1.872296142578125
90th percentile: 1.8760184288024901
95th percentile: 1.8778795719146728
99th percentile: 1.879368486404419
mean time: 1.5528666019439696
Pipeline stage StressChecker completed in 9.16s
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 0.62s
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 0.67s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v25 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 2378.38s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v25 status is now inactive due to auto deactivation removed underperforming models
chaiml-2fe5-c13f-linear-w01_v25 status is now torndown due to DeploymentManager action