chaiml-collin-servant-pr_8683

developer_uid: chai_backend_admin

submission_id: chaiml-collin-servant-pr_8683_v4

model_name: chaiml-collin-servant-pr_8683_v4

model_group: ChaiML/Collin-Servant-Pr

status: torndown

timestamp: 2025-07-10T19:15:26+00:00

num_battles: 9175

num_wins: 4639

celo_rating: 1292.59

family_friendly_score: 0.5112

family_friendly_standard_error: 0.007069293599787747

submission_type: basic

model_repo: ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft

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': 0.5224914503754, 'latency_mean': 1.9138068652153015, 'latency_p50': 1.8934388160705566, 'latency_p90': 2.1153714656829834}, {'batch_size': 3, 'throughput': 1.0568177956961398, 'latency_mean': 2.824025411605835, 'latency_p50': 2.8558809757232666, 'latency_p90': 3.0905239820480346}, {'batch_size': 5, 'throughput': 1.344554150558057, 'latency_mean': 3.6918363440036774, 'latency_p50': 3.7039769887924194, 'latency_p90': 4.077529835700989}, {'batch_size': 6, 'throughput': 1.4593450263756713, 'latency_mean': 4.08876500248909, 'latency_p50': 4.118304491043091, 'latency_p90': 4.538127994537353}, {'batch_size': 8, 'throughput': 1.599046241481097, 'latency_mean': 4.969274104833603, 'latency_p50': 4.924320936203003, 'latency_p90': 5.697620296478271}, {'batch_size': 10, 'throughput': 1.684602534249807, 'latency_mean': 5.884192218780518, 'latency_p50': 5.895062327384949, 'latency_p90': 6.723691463470459}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-collin-servant-pr_8683_v4

is_internal_developer: True

language_model: ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-10

win_ratio: 0.5056130790190736

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '####', '</s>', '\n', '####\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {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-collin-servant-pr-8683-v4-mkmlizer
Waiting for job on chaiml-collin-servant-pr-8683-v4-mkmlizer to finish
chaiml-collin-servant-pr-8683-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║                                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║                                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║                                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║                                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ║                                                                     ║
chaiml-collin-servant-pr-8683-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-collin-servant-pr-8683-v4-mkmlizer: Downloaded to shared memory in 83.377s
chaiml-collin-servant-pr-8683-v4-mkmlizer: Checking if ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft already exists in ChaiML
chaiml-collin-servant-pr-8683-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0vtzs3d4, device:0
chaiml-collin-servant-pr-8683-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-collin-servant-pr-8683-v4-mkmlizer: quantized model in 56.037s
chaiml-collin-servant-pr-8683-v4-mkmlizer: Processed model ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft in 139.416s
chaiml-collin-servant-pr-8683-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-collin-servant-pr-8683-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-collin-servant-pr-8683-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia
chaiml-collin-servant-pr-8683-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia/config.json
chaiml-collin-servant-pr-8683-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia/special_tokens_map.json
chaiml-collin-servant-pr-8683-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia/tokenizer_config.json
chaiml-collin-servant-pr-8683-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia/tokenizer.json
chaiml-collin-servant-pr-8683-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v4/nvidia/flywheel_model.0.safetensors
chaiml-collin-servant-pr-8683-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.71it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.95it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.71it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.48it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.32it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.13it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 30.98it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 20.74it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 19.21it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 19.83it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:16, 19.42it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:14, 21.29it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:14, 22.15it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.97it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:12, 25.22it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 21.68it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.53it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.63it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 19.25it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.81it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:13, 21.37it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 20.85it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.77it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.32it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.50it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.35it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.64it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.04it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 25.21it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:13, 19.08it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:12, 20.91it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:11, 21.47it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 25.08it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.10it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 25.94it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 25.53it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 24.39it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 25.26it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 25.47it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 24.73it/s]
Loading 0:  40%|████      | 147/363 [00:06<00:07, 30.36it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:10, 20.72it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 19.01it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:10, 20.23it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 20.47it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 22.38it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 23.00it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.83it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.40it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.68it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 25.46it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 21.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 20.17it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.87it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.20it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 22.94it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 22.94it/s]
Loading 0:  55%|█████▌    | 201/363 [00:24<04:34,  1.70s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<03:33,  1.34s/it]
Loading 0:  57%|█████▋    | 208/363 [00:25<01:56,  1.34it/s]
Loading 0:  58%|█████▊    | 211/363 [00:25<01:25,  1.79it/s]
Loading 0:  59%|█████▉    | 214/363 [00:25<01:01,  2.41it/s]
Loading 0:  60%|█████▉    | 217/363 [00:25<00:44,  3.28it/s]
Loading 0:  61%|██████    | 220/363 [00:25<00:33,  4.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:26<00:24,  5.73it/s]
Loading 0:  63%|██████▎   | 228/363 [00:26<00:16,  8.03it/s]
Loading 0:  64%|██████▎   | 231/363 [00:26<00:14,  9.35it/s]
Loading 0:  65%|██████▍   | 235/363 [00:26<00:10, 12.54it/s]
Loading 0:  66%|██████▌   | 238/363 [00:26<00:08, 14.47it/s]
Loading 0:  66%|██████▋   | 241/363 [00:26<00:07, 16.15it/s]
Loading 0:  68%|██████▊   | 246/363 [00:26<00:05, 20.12it/s]
Loading 0:  69%|██████▊   | 249/363 [00:27<00:05, 19.38it/s]
Loading 0:  70%|███████   | 255/363 [00:27<00:04, 24.49it/s]
Loading 0:  71%|███████   | 258/363 [00:27<00:04, 22.35it/s]
Loading 0:  72%|███████▏  | 263/363 [00:27<00:03, 27.50it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:04, 22.73it/s]
Loading 0:  74%|███████▍  | 270/363 [00:27<00:04, 19.44it/s]
Loading 0:  75%|███████▌  | 274/363 [00:28<00:03, 22.75it/s]
Loading 0:  76%|███████▋  | 277/363 [00:28<00:03, 23.01it/s]
Loading 0:  78%|███████▊  | 282/363 [00:28<00:03, 25.78it/s]
Loading 0:  79%|███████▊  | 285/363 [00:28<00:03, 23.25it/s]
Loading 0:  80%|████████  | 291/363 [00:28<00:02, 27.41it/s]
Loading 0:  81%|████████  | 294/363 [00:28<00:02, 24.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:29<00:02, 26.48it/s]
Loading 0:  83%|████████▎ | 303/363 [00:29<00:02, 28.75it/s]
Loading 0:  84%|████████▍ | 306/363 [00:29<00:03, 18.17it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 21.14it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 21.66it/s]
Loading 0:  88%|████████▊ | 318/363 [00:29<00:01, 24.57it/s]
Loading 0:  88%|████████▊ | 321/363 [00:30<00:01, 21.87it/s]
Loading 0:  90%|████████▉ | 325/363 [00:30<00:01, 25.35it/s]
Loading 0:  90%|█████████ | 328/363 [00:30<00:01, 25.64it/s]
Loading 0:  91%|█████████ | 331/363 [00:30<00:01, 24.73it/s]
Loading 0:  92%|█████████▏| 334/363 [00:30<00:01, 25.74it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 21.41it/s]
Loading 0:  94%|█████████▎| 340/363 [00:30<00:00, 23.25it/s]
Loading 0:  94%|█████████▍| 343/363 [00:31<00:01, 13.64it/s]
Loading 0:  96%|█████████▌| 347/363 [00:31<00:00, 17.76it/s]
Loading 0:  96%|█████████▋| 350/363 [00:31<00:00, 18.84it/s]
Loading 0:  97%|█████████▋| 353/363 [00:31<00:00, 20.68it/s]
Loading 0:  98%|█████████▊| 356/363 [00:31<00:00, 21.82it/s]
Loading 0:  99%|█████████▉| 359/363 [00:31<00:00, 21.70it/s]
                                                            
Job chaiml-collin-servant-pr-8683-v4-mkmlizer completed after 178.04s with status: succeeded
Stopping job with name chaiml-collin-servant-pr-8683-v4-mkmlizer
Pipeline stage MKMLizer completed in 178.63s
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-collin-servant-pr-8683-v4
Waiting for inference service chaiml-collin-servant-pr-8683-v4 to be ready
Inference service chaiml-collin-servant-pr-8683-v4 ready after 191.0846598148346s
Pipeline stage MKMLDeployer completed in 191.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8395755290985107s
Received healthy response to inference request in 1.928527593612671s
Received healthy response to inference request in 2.099627733230591s
Received healthy response to inference request in 2.328442335128784s
Received healthy response to inference request in 2.2198426723480225s
5 requests
0 failed requests
5th percentile: 1.962747621536255
10th percentile: 1.996967649459839
20th percentile: 2.065407705307007
30th percentile: 2.123670721054077
40th percentile: 2.17175669670105
50th percentile: 2.2198426723480225
60th percentile: 2.263282537460327
70th percentile: 2.306722402572632
80th percentile: 2.4306689739227294
90th percentile: 2.6351222515106203
95th percentile: 2.7373488903045655
99th percentile: 2.8191302013397217
mean time: 2.2832031726837156
Pipeline stage StressChecker completed in 12.87s
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 0.73s
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 0.73s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_v4 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 3415.31s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-collin-servant-pr_8683_v4 status is now torndown due to DeploymentManager action
chaiml-collin-servant-pr_8683_v4 status is now torndown due to DeploymentManager action