chaiml-2fe5-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-2fe5-c13f-linear-w01_v29

model_name: chaiml-2fe5-c13f-linear-w01_v29

model_group: ChaiML/2fe5-c13f-linear-

status: inactive

timestamp: 2025-12-09T22:24:33+00:00

num_battles: 5636

num_wins: 2870

celo_rating: 1307.79

family_friendly_score: 0.5336000000000001

family_friendly_standard_error: 0.007055083840749166

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': 0.7876581190875199, 'latency_mean': 1.2694593155384064, 'latency_p50': 1.2630279064178467, 'latency_p90': 1.4131339550018311}, {'batch_size': 4, 'throughput': 1.8893381983163708, 'latency_mean': 2.114491877555847, 'latency_p50': 2.109948754310608, 'latency_p90': 2.371921706199646}, {'batch_size': 5, 'throughput': 2.104325661964078, 'latency_mean': 2.3659652602672576, 'latency_p50': 2.3688141107559204, 'latency_p90': 2.6564810514450072}, {'batch_size': 8, 'throughput': 2.4652094322515183, 'latency_mean': 3.218090629577637, 'latency_p50': 3.2286174297332764, 'latency_p90': 3.6281911611557005}, {'batch_size': 10, 'throughput': 2.5916355673630167, 'latency_mean': 3.825552133321762, 'latency_p50': 3.811777114868164, 'latency_p90': 4.321756815910339}, {'batch_size': 12, 'throughput': 2.682028044428162, 'latency_mean': 4.405994892120361, 'latency_p50': 4.417844891548157, 'latency_p90': 5.0777854204177855}, {'batch_size': 15, 'throughput': 2.71553228569316, 'latency_mean': 5.456809653043747, 'latency_p50': 5.452228307723999, 'latency_p90': 6.294954419136047}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-2fe5-c13f-linear-w01_v29

ineligible_reason: num_battles<10000

is_internal_developer: True

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

model_size: 13B

ranking_group: single

throughput_3p7s: 2.59

us_pacific_date: 2025-11-26

win_ratio: 0.5092264017033357

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '</s>', '\n', 'Bot:', '####', '<|im_end|>', '<|eot_id|>', '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-v29-mkmlizer
Waiting for job on chaiml-2fe5-c13f-linear-w01-v29-mkmlizer to finish
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  belonging to:                                                      ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: Downloaded to shared memory in 27.127s
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: Checking if ChaiML/2fe5-c13f-linear-w01 already exists in ChaiML
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9yondd02, device:0
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: quantized model in 26.146s
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: Processed model ChaiML/2fe5-c13f-linear-w01 in 53.274s
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v29/nvidia
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v29/nvidia/special_tokens_map.json
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v29/nvidia/config.json
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v29/nvidia/tokenizer_config.json
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v29/nvidia/flywheel_model.0.safetensors
chaiml-2fe5-c13f-linear-w01-v29-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:35,  2.76s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:25,  1.35it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:26,  4.03it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:52,  6.57it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:34,  9.86it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:23, 14.16it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:17, 18.05it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:14, 21.62it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 25.39it/s]
Loading 0:  16%|█▋        | 59/363 [00:06<00:08, 34.04it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:08, 37.25it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:07, 41.37it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:06, 42.52it/s]
Loading 0:  24%|██▍       | 87/363 [00:07<00:05, 46.78it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 49.94it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:04, 51.69it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 51.94it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 46.08it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:05, 46.66it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:05, 44.81it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 48.48it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:03, 55.13it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:03, 53.06it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:03, 53.58it/s]
Loading 0:  46%|████▋     | 168/363 [00:08<00:03, 50.49it/s]
Loading 0:  49%|████▉     | 177/363 [00:09<00:03, 52.32it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:03, 58.24it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:02, 58.04it/s]
Loading 0:  55%|█████▍    | 198/363 [00:09<00:02, 56.86it/s]
Loading 0:  56%|█████▌    | 204/363 [00:09<00:04, 38.99it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:04, 34.22it/s]
Loading 0:  60%|██████    | 218/363 [00:10<00:03, 36.89it/s]
Loading 0:  62%|██████▏   | 224/363 [00:10<00:03, 40.95it/s]
Loading 0:  64%|██████▎   | 231/363 [00:10<00:03, 41.76it/s]
Loading 0:  66%|██████▌   | 240/363 [00:10<00:02, 45.81it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:02, 52.89it/s]
Loading 0:  70%|██████▉   | 254/363 [00:10<00:02, 51.30it/s]
Loading 0:  72%|███████▏  | 260/363 [00:10<00:01, 52.33it/s]
Loading 0:  74%|███████▎  | 267/363 [00:10<00:02, 47.91it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:01, 54.48it/s]
Loading 0:  77%|███████▋  | 281/363 [00:11<00:01, 52.66it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 39.94it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 40.89it/s]
Loading 0:  83%|████████▎ | 302/363 [00:11<00:01, 48.94it/s]
Loading 0:  85%|████████▍ | 308/363 [00:11<00:01, 48.93it/s]
Loading 0:  87%|████████▋ | 314/363 [00:11<00:00, 50.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:00, 52.58it/s]
Loading 0:  90%|████████▉ | 326/363 [00:12<00:00, 51.09it/s]
Loading 0:  91%|█████████▏| 332/363 [00:12<00:00, 51.92it/s]
Loading 0:  93%|█████████▎| 339/363 [00:12<00:00, 48.85it/s]
Loading 0:  96%|█████████▌| 347/363 [00:12<00:00, 56.29it/s]
Loading 0:  97%|█████████▋| 353/363 [00:12<00:00, 54.00it/s]
Loading 0:  99%|█████████▉| 359/363 [00:12<00:00, 54.16it/s]
                                                            
Job chaiml-2fe5-c13f-linear-w01-v29-mkmlizer completed after 113.38s with status: succeeded
Stopping job with name chaiml-2fe5-c13f-linear-w01-v29-mkmlizer
Pipeline stage MKMLizer completed in 113.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2fe5-c13f-linear-w01-v29
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v29 to be ready
Inference service chaiml-2fe5-c13f-linear-w01-v29 ready after 160.77941060066223s
Pipeline stage MKMLDeployer completed in 162.15s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.624793529510498s
Received healthy response to inference request in 1.6067397594451904s
Received healthy response to inference request in 1.4119396209716797s
Received healthy response to inference request in 1.5634424686431885s
5 requests
1 failed requests
5th percentile: 1.4422401905059814
10th percentile: 1.4725407600402831
20th percentile: 1.5331418991088868
30th percentile: 1.572101926803589
40th percentile: 1.5894208431243897
50th percentile: 1.6067397594451904
60th percentile: 1.6139612674713135
70th percentile: 1.6211827754974366
80th percentile: 5.322283840179447
90th percentile: 12.717264461517335
95th percentile: 16.414754772186278
99th percentile: 19.372747020721434
mean time: 5.263832092285156
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2519230842590332s
Received healthy response to inference request in 1.8077998161315918s
Received healthy response to inference request in 1.7095847129821777s
Received healthy response to inference request in 1.226407527923584s
Received healthy response to inference request in 1.5749390125274658s
5 requests
0 failed requests
5th percentile: 1.2315106391906738
10th percentile: 1.2366137504577637
20th percentile: 1.2468199729919434
30th percentile: 1.3165262699127198
40th percentile: 1.4457326412200928
50th percentile: 1.5749390125274658
60th percentile: 1.6287972927093506
70th percentile: 1.6826555728912354
80th percentile: 1.7292277336120605
90th percentile: 1.7685137748718263
95th percentile: 1.788156795501709
99th percentile: 1.8038712120056153
mean time: 1.5141308307647705
Pipeline stage StressChecker completed in 36.13s
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 0.59s
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-2fe5-c13f-linear-w01_v29 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 2473.99s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v29 status is now inactive due to auto deactivation removed underperforming models
chaiml-2fe5-c13f-linear-w01_v29 status is now protected due to ABTestQueueItem
chaiml-2fe5-c13f-linear-w01_v29 status is now protected due to ABTestQueueItem