developer_uid: rirv938
submission_id: chaiml-2a6f-69d4-linear-w01_v16
model_name: chaiml-2a6f-69d4-linear-w01_v16
model_group: ChaiML/2a6f-69d4-linear-
status: torndown
timestamp: 2025-12-12T18:26:53+00:00
num_battles: 6044
num_wins: 3024
celo_rating: 1293.33
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/2a6f-69d4-linear-w01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 7
max_input_tokens: 1280
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.42603236474174117, 'latency_mean': 2.3471187806129454, 'latency_p50': 2.3450353145599365, 'latency_p90': 2.603417468070984}, {'batch_size': 3, 'throughput': 0.8699198232127487, 'latency_mean': 3.441926542520523, 'latency_p50': 3.4171524047851562, 'latency_p90': 3.9429138898849487}, {'batch_size': 5, 'throughput': 1.1373852219060505, 'latency_mean': 4.378793716430664, 'latency_p50': 4.391767740249634, 'latency_p90': 4.937346029281616}, {'batch_size': 6, 'throughput': 1.2096999581687289, 'latency_mean': 4.917898689508438, 'latency_p50': 4.932597637176514, 'latency_p90': 5.475897026062012}, {'batch_size': 8, 'throughput': 1.3472979023232823, 'latency_mean': 5.875331094264984, 'latency_p50': 5.906048774719238, 'latency_p90': 6.7088361263275145}, {'batch_size': 10, 'throughput': 1.4206521619753614, 'latency_mean': 6.9893590259552, 'latency_p50': 7.008703947067261, 'latency_p90': 8.1051664352417}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-2a6f-69d4-linear-w01_v16
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/2a6f-69d4-linear-w01
model_size: 24B
ranking_group: single
throughput_3p7s: 0.96
us_pacific_date: 2025-11-26
win_ratio: 0.500330906684315
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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-2a6f-69d4-linear-w01-v16-mkmlizer
Waiting for job on chaiml-2a6f-69d4-linear-w01-v16-mkmlizer to finish
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  belonging to:                                                      ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: Downloaded to shared memory in 67.432s
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: Checking if ChaiML/2a6f-69d4-linear-w01 already exists in ChaiML
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpis25ss4e, device:0
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: quantized model in 41.874s
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: Processed model ChaiML/2a6f-69d4-linear-w01 in 109.307s
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia/config.json
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia/special_tokens_map.json
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia/tokenizer_config.json
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia/tokenizer.json
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-2a6f-69d4-linear-w01-v16/nvidia/flywheel_model.1.safetensors
chaiml-2a6f-69d4-linear-w01-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:45,  2.79s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:32,  1.31it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:29,  3.89it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:06,  5.22it/s]
Loading 0:   6%|▌         | 21/363 [00:06<00:53,  6.44it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:58,  5.81it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:37,  8.79it/s]
Loading 0:   9%|▉         | 32/363 [00:07<00:31, 10.55it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:25, 12.62it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.43it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 19.95it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:12, 24.99it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.68it/s]
Loading 0:  16%|█▋        | 59/363 [00:08<00:12, 24.60it/s]
Loading 0:  17%|█▋        | 63/363 [00:08<00:11, 27.08it/s]
Loading 0:  19%|█▊        | 68/363 [00:08<00:10, 29.48it/s]
Loading 0:  20%|█▉        | 72/363 [00:08<00:09, 31.57it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:08, 33.20it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 36.76it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 35.30it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 36.02it/s]
Loading 0:  26%|██▌       | 95/363 [00:09<00:07, 36.58it/s]
Loading 0:  27%|██▋       | 99/363 [00:09<00:09, 27.45it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:08, 30.08it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:08, 29.67it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 33.92it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 32.42it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:06, 35.37it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:06, 35.97it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:06, 36.84it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:06, 33.95it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:07, 28.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:07, 27.83it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 32.54it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 31.45it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 34.47it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:06, 32.62it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:05, 36.29it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 33.63it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:06, 27.89it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:06, 30.08it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:05, 31.84it/s]
Loading 0:  52%|█████▏    | 189/363 [00:24<02:33,  1.13it/s]
Loading 0:  53%|█████▎    | 193/363 [00:25<01:51,  1.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:25<01:26,  1.94it/s]
Loading 0:  55%|█████▌    | 200/363 [00:25<01:00,  2.70it/s]
Loading 0:  56%|█████▌    | 204/363 [00:25<00:43,  3.66it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<00:24,  6.16it/s]
Loading 0:  59%|█████▉    | 215/363 [00:25<00:20,  7.23it/s]
Loading 0:  61%|██████    | 221/363 [00:26<00:13, 10.27it/s]
Loading 0:  62%|██████▏   | 225/363 [00:26<00:11, 12.54it/s]
Loading 0:  63%|██████▎   | 230/363 [00:26<00:08, 15.68it/s]
Loading 0:  64%|██████▍   | 234/363 [00:26<00:06, 18.53it/s]
Loading 0:  66%|██████▌   | 239/363 [00:26<00:05, 21.93it/s]
Loading 0:  67%|██████▋   | 243/363 [00:26<00:04, 24.70it/s]
Loading 0:  68%|██████▊   | 248/363 [00:26<00:04, 27.24it/s]
Loading 0:  69%|██████▉   | 252/363 [00:26<00:03, 29.49it/s]
Loading 0:  71%|███████   | 256/363 [00:27<00:04, 25.01it/s]
Loading 0:  72%|███████▏  | 260/363 [00:27<00:04, 25.72it/s]
Loading 0:  73%|███████▎  | 265/363 [00:27<00:03, 30.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:03, 29.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:02, 33.91it/s]
Loading 0:  77%|███████▋  | 278/363 [00:27<00:02, 32.54it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:02, 34.25it/s]
Loading 0:  79%|███████▉  | 287/363 [00:28<00:02, 32.53it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:01, 35.96it/s]
Loading 0:  82%|████████▏ | 296/363 [00:28<00:02, 25.76it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 30.35it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:01, 29.77it/s]
Loading 0:  86%|████████▌ | 311/363 [00:28<00:01, 33.38it/s]
Loading 0:  87%|████████▋ | 315/363 [00:28<00:01, 34.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:29<00:01, 34.26it/s]
Loading 0:  89%|████████▉ | 324/363 [00:29<00:01, 34.66it/s]
Loading 0:  91%|█████████ | 329/363 [00:29<00:00, 34.96it/s]
Loading 0:  92%|█████████▏| 333/363 [00:29<00:01, 26.57it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:00, 29.47it/s]
Loading 0:  94%|█████████▍| 342/363 [00:29<00:00, 31.14it/s]
Loading 0:  95%|█████████▌| 346/363 [00:29<00:00, 32.55it/s]
Loading 0:  96%|█████████▋| 350/363 [00:30<00:00, 30.23it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 34.38it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 32.72it/s]
                                                            

Job chaiml-2a6f-69d4-linear-w01-v16-mkmlizer completed after 248.22s with status: succeeded
Stopping job with name chaiml-2a6f-69d4-linear-w01-v16-mkmlizer
Pipeline stage MKMLizer completed in 249.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2a6f-69d4-linear-w01-v16
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v16 to be ready
Inference service chaiml-2a6f-69d4-linear-w01-v16 ready after 160.6286928653717s
Pipeline stage MKMLDeployer completed in 161.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0086238384246826s
Received healthy response to inference request in 2.396040201187134s
Received healthy response to inference request in 2.2917089462280273s
Received healthy response to inference request in 2.2800681591033936s
Received healthy response to inference request in 2.3996965885162354s
5 requests
0 failed requests
5th percentile: 2.2823963165283203
10th percentile: 2.284724473953247
20th percentile: 2.2893807888031006
30th percentile: 2.3125751972198487
40th percentile: 2.354307699203491
50th percentile: 2.396040201187134
60th percentile: 2.3975027561187745
70th percentile: 2.398965311050415
80th percentile: 2.521482038497925
90th percentile: 2.7650529384613036
95th percentile: 2.886838388442993
99th percentile: 2.9842667484283445
mean time: 2.4752275466918947
Pipeline stage StressChecker completed in 14.09s
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 1.02s
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 1.25s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v16 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 0.10s
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-2a6f-69d4-linear-w01-v16-profiler
Waiting for inference service chaiml-2a6f-69d4-linear-w01-v16-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 4821.31s
Shutdown handler de-registered
chaiml-2a6f-69d4-linear-w01_v16 status is now torndown due to DeploymentManager action