chaiml-02f4-69d4-linear-w01

developer_uid: rirv938

submission_id: chaiml-02f4-69d4-linear-w01_v28

model_name: chaiml-02f4-69d4-linear-w01_v28

model_group: ChaiML/02f4-69d4-linear-

status: torndown

timestamp: 2025-12-12T18:26:47+00:00

num_battles: 7032

num_wins: 3626

celo_rating: 1319.19

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/02f4-69d4-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4420740322693731, 'latency_mean': 2.261969871520996, 'latency_p50': 2.248682975769043, 'latency_p90': 2.517668533325195}, {'batch_size': 3, 'throughput': 0.9246099863201809, 'latency_mean': 3.2373263239860535, 'latency_p50': 3.2367372512817383, 'latency_p90': 3.6016079902648923}, {'batch_size': 5, 'throughput': 1.210760456662972, 'latency_mean': 4.100990114212036, 'latency_p50': 4.098959684371948, 'latency_p90': 4.538641333580017}, {'batch_size': 6, 'throughput': 1.314559569699176, 'latency_mean': 4.513553785085678, 'latency_p50': 4.486563205718994, 'latency_p90': 5.151487731933594}, {'batch_size': 8, 'throughput': 1.4633927878986621, 'latency_mean': 5.441098299026489, 'latency_p50': 5.486334681510925, 'latency_p90': 6.2086745500564575}, {'batch_size': 10, 'throughput': 1.5590165837735914, 'latency_mean': 6.3530234885215755, 'latency_p50': 6.374038577079773, 'latency_p90': 7.245280313491821}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-02f4-69d4-linear-w01_v28

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/02f4-69d4-linear-w01

model_size: 24B

ranking_group: single

throughput_3p7s: 1.1

us_pacific_date: 2025-11-26

win_ratio: 0.5156427758816837

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-02f4-69d4-linear-w01-v28-mkmlizer
Waiting for job on chaiml-02f4-69d4-linear-w01-v28-mkmlizer to finish
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  belonging to:                                                      ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ║                                                                     ║
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: Downloaded to shared memory in 40.945s
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: Checking if ChaiML/02f4-69d4-linear-w01 already exists in ChaiML
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg97vawyd, device:0
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: quantized model in 42.127s
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: Processed model ChaiML/02f4-69d4-linear-w01 in 83.073s
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: creating bucket guanaco-mkml-models
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/config.json
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/tokenizer_config.json
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/special_tokens_map.json
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/tokenizer.json
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/flywheel_model.1.safetensors
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-02f4-69d4-linear-w01-v28/nvidia/flywheel_model.0.safetensors
chaiml-02f4-69d4-linear-w01-v28-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:08,  2.85s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:38,  1.28it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:31,  3.80it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.37it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:49,  6.84it/s]
Loading 0:   7%|▋         | 25/363 [00:06<00:40,  8.26it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:26, 12.77it/s]
Loading 0:  10%|▉         | 35/363 [00:06<00:21, 15.23it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:16, 19.61it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:14, 21.61it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 26.31it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 26.99it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:12, 24.90it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:10, 27.42it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:09, 29.59it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 31.54it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 33.19it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 37.03it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 31.12it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 38.90it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:09, 28.30it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:08, 30.42it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:08, 29.83it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 33.65it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 32.22it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:06, 36.14it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 33.71it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.51it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 33.12it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:08, 27.60it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:08, 27.30it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 31.76it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 30.80it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:06, 34.32it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 32.61it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 35.93it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 33.52it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 37.32it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:07, 25.88it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:05, 30.63it/s]
Loading 0:  52%|█████▏    | 188/363 [00:24<02:41,  1.08it/s]
Loading 0:  53%|█████▎    | 191/363 [00:24<02:04,  1.38it/s]
Loading 0:  54%|█████▎    | 195/363 [00:25<01:29,  1.87it/s]
Loading 0:  56%|█████▌    | 202/363 [00:25<00:50,  3.21it/s]
Loading 0:  57%|█████▋    | 206/363 [00:25<00:37,  4.16it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<00:25,  5.85it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:22,  6.62it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:15,  9.16it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:13, 10.51it/s]
Loading 0:  63%|██████▎   | 229/363 [00:26<00:09, 13.97it/s]
Loading 0:  64%|██████▍   | 233/363 [00:26<00:08, 16.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:06, 20.57it/s]
Loading 0:  67%|██████▋   | 242/363 [00:26<00:05, 22.19it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:04, 26.45it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:04, 26.74it/s]
Loading 0:  71%|███████   | 256/363 [00:27<00:04, 24.24it/s]
Loading 0:  72%|███████▏  | 260/363 [00:27<00:04, 24.74it/s]
Loading 0:  73%|███████▎  | 265/363 [00:27<00:03, 28.85it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:03, 28.52it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:02, 32.40it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 31.16it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 34.54it/s]
Loading 0:  79%|███████▉  | 287/363 [00:28<00:02, 32.28it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:01, 35.91it/s]
Loading 0:  82%|████████▏ | 296/363 [00:28<00:02, 25.38it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 29.74it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:01, 29.35it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:01, 33.84it/s]
Loading 0:  87%|████████▋ | 314/363 [00:29<00:01, 31.96it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 34.88it/s]
Loading 0:  89%|████████▉ | 323/363 [00:29<00:01, 31.20it/s]
Loading 0:  90%|█████████ | 328/363 [00:29<00:01, 32.36it/s]
Loading 0:  91%|█████████▏| 332/363 [00:29<00:01, 23.04it/s]
Loading 0:  93%|█████████▎| 337/363 [00:29<00:00, 27.82it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:00, 28.03it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 31.82it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 30.48it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 34.31it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 32.40it/s]
                                                            
Job chaiml-02f4-69d4-linear-w01-v28-mkmlizer completed after 286.53s with status: succeeded
Stopping job with name chaiml-02f4-69d4-linear-w01-v28-mkmlizer
Pipeline stage MKMLizer completed in 287.04s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-02f4-69d4-linear-w01-v28
Waiting for inference service chaiml-02f4-69d4-linear-w01-v28 to be ready
Inference service chaiml-02f4-69d4-linear-w01-v28 ready after 160.99671721458435s
Pipeline stage MKMLDeployer completed in 161.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.294776439666748s
Received healthy response to inference request in 2.6848342418670654s
Received healthy response to inference request in 2.094963550567627s
Received healthy response to inference request in 2.153482675552368s
Received healthy response to inference request in 2.202144145965576s
5 requests
0 failed requests
5th percentile: 2.1066673755645753
10th percentile: 2.1183712005615236
20th percentile: 2.14177885055542
30th percentile: 2.1632149696350096
40th percentile: 2.182679557800293
50th percentile: 2.202144145965576
60th percentile: 2.2391970634460447
70th percentile: 2.2762499809265138
80th percentile: 2.372788000106812
90th percentile: 2.5288111209869384
95th percentile: 2.6068226814270017
99th percentile: 2.6692319297790528
mean time: 2.286040210723877
Pipeline stage StressChecker completed in 12.84s
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 0.63s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v28 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 0.08s
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-02f4-69d4-linear-w01-v28-profiler
Waiting for inference service chaiml-02f4-69d4-linear-w01-v28-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5445.12s
Shutdown handler de-registered
chaiml-02f4-69d4-linear-w01_v28 status is now torndown due to DeploymentManager action