chaiml-4d70-fd43-linear-w01

developer_uid: rirv938

submission_id: chaiml-4d70-fd43-linear-w01_v17

model_name: chaiml-4d70-fd43-linear-w01_v17

model_group: ChaiML/4d70-fd43-linear-

status: inactive

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

num_battles: 6421

num_wins: 3380

celo_rating: 1321.74

family_friendly_score: 0.5048

family_friendly_standard_error: 0.007070741969553125

submission_type: basic

model_repo: ChaiML/4d70-fd43-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1800

max_output_tokens: 74

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6288804327227625, 'latency_mean': 1.5900138199329377, 'latency_p50': 1.5856575965881348, 'latency_p90': 1.7395697355270385}, {'batch_size': 3, 'throughput': 1.245841592178274, 'latency_mean': 2.400769153833389, 'latency_p50': 2.4051684141159058, 'latency_p90': 2.5780287742614747}, {'batch_size': 5, 'throughput': 1.5655592054441694, 'latency_mean': 3.1775976884365082, 'latency_p50': 3.1781681776046753, 'latency_p90': 3.5532003164291384}, {'batch_size': 6, 'throughput': 1.666624467646647, 'latency_mean': 3.584282113313675, 'latency_p50': 3.589116930961609, 'latency_p90': 4.038334488868713}, {'batch_size': 8, 'throughput': 1.8107196538949297, 'latency_mean': 4.382707529067993, 'latency_p50': 4.366976857185364, 'latency_p90': 4.946946048736573}, {'batch_size': 10, 'throughput': 1.8787606826976122, 'latency_mean': 5.282872794866562, 'latency_p50': 5.327032446861267, 'latency_p90': 5.952632594108581}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-4d70-fd43-linear-w01_v17

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/4d70-fd43-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2025-11-26

win_ratio: 0.5263977573586669

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['\n', '</s>', '<|im_end|>', '###', '<|im_start|>'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}

formatter: {'memory_template': '', '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-4d70-fd43-linear-w01-v17-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v17-mkmlizer to finish
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  belonging to:                                                      ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: Downloaded to shared memory in 21.948s
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w01 already exists in ChaiML
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzssh0yt3, device:0
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: quantized model in 26.030s
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w01 in 47.978s
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia/config.json
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia/tokenizer_config.json
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v17/nvidia/flywheel_model.0.safetensors
chaiml-4d70-fd43-linear-w01-v17-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:05,  2.67s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:17,  1.39it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:24,  4.15it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:50,  6.76it/s]
Loading 0:   7%|▋         | 26/363 [00:05<00:33, 10.13it/s]
Loading 0:   9%|▉         | 33/363 [00:05<00:22, 14.47it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:17, 18.19it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:14, 21.78it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 25.46it/s]
Loading 0:  16%|█▋        | 59/363 [00:06<00:08, 34.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:08, 37.08it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:07, 40.72it/s]
Loading 0:  21%|██▏       | 78/363 [00:06<00:06, 41.92it/s]
Loading 0:  24%|██▍       | 87/363 [00:07<00:06, 45.73it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 48.75it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 50.97it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 52.50it/s]
Loading 0:  33%|███▎      | 121/363 [00:07<00:05, 46.16it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:05, 46.83it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:05, 45.15it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:04, 48.76it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:03, 55.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:03, 53.43it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:03, 53.14it/s]
Loading 0:  46%|████▋     | 168/363 [00:08<00:03, 50.04it/s]
Loading 0:  49%|████▉     | 177/363 [00:08<00:03, 51.74it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:03, 57.91it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:02, 57.77it/s]
Loading 0:  55%|█████▍    | 198/363 [00:09<00:02, 56.71it/s]
Loading 0:  56%|█████▌    | 204/363 [00:09<00:04, 38.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:03, 46.12it/s]
Loading 0:  60%|██████    | 218/363 [00:09<00:03, 46.88it/s]
Loading 0:  62%|██████▏   | 224/363 [00:09<00:02, 49.22it/s]
Loading 0:  64%|██████▎   | 231/363 [00:09<00:02, 47.27it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:02, 54.73it/s]
Loading 0:  67%|██████▋   | 245/363 [00:10<00:02, 52.57it/s]
Loading 0:  69%|██████▉   | 251/363 [00:10<00:02, 52.96it/s]
Loading 0:  71%|███████   | 258/363 [00:10<00:02, 49.60it/s]
Loading 0:  74%|███████▎  | 267/363 [00:10<00:01, 51.16it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:01, 57.29it/s]
Loading 0:  77%|███████▋  | 281/363 [00:10<00:01, 53.88it/s]
Loading 0:  79%|███████▉  | 287/363 [00:11<00:01, 39.89it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 41.07it/s]
Loading 0:  83%|████████▎ | 303/363 [00:11<00:01, 45.10it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:01, 51.98it/s]
Loading 0:  87%|████████▋ | 317/363 [00:11<00:00, 50.82it/s]
Loading 0:  89%|████████▉ | 323/363 [00:11<00:00, 51.82it/s]
Loading 0:  91%|█████████ | 330/363 [00:11<00:00, 49.49it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 56.09it/s]
Loading 0:  95%|█████████▍| 344/363 [00:12<00:00, 53.65it/s]
Loading 0:  96%|█████████▋| 350/363 [00:12<00:00, 54.17it/s]
Loading 0:  98%|█████████▊| 357/363 [00:12<00:00, 49.91it/s]
                                                            
Job chaiml-4d70-fd43-linear-w01-v17-mkmlizer completed after 164.57s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v17-mkmlizer
Pipeline stage MKMLizer completed in 165.50s
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-4d70-fd43-linear-w01-v17
Waiting for inference service chaiml-4d70-fd43-linear-w01-v17 to be ready
Inference service chaiml-4d70-fd43-linear-w01-v17 ready after 161.8642737865448s
Pipeline stage MKMLDeployer completed in 162.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1344258785247803s
Received healthy response to inference request in 1.4528942108154297s
Received healthy response to inference request in 1.8043794631958008s
Received healthy response to inference request in 1.4274392127990723s
Received healthy response to inference request in 1.495771884918213s
5 requests
0 failed requests
5th percentile: 1.4325302124023438
10th percentile: 1.4376212120056153
20th percentile: 1.4478032112121582
30th percentile: 1.4614697456359864
40th percentile: 1.4786208152770997
50th percentile: 1.495771884918213
60th percentile: 1.619214916229248
70th percentile: 1.7426579475402832
80th percentile: 1.8703887462615967
90th percentile: 2.0024073123931885
95th percentile: 2.0684165954589844
99th percentile: 2.121224021911621
mean time: 1.662982130050659
Pipeline stage StressChecker completed in 9.95s
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 0.86s
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 0.62s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v17 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 2830.29s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v17 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w01_v17 status is now protected due to ABTestQueueItem
chaiml-4d70-fd43-linear-w01_v17 status is now protected due to ABTestQueueItem