chaiml-katsuki-bakugou-_98991

developer_uid: chai_backend_admin

submission_id: chaiml-katsuki-bakugou-_98991_v1

model_name: chaiml-katsuki-bakugou-_98991_v1

model_group: ChaiML/Katsuki-Bakugou-b

status: torndown

timestamp: 2025-07-08T10:14:42+00:00

num_battles: 7770

num_wins: 3879

celo_rating: 1291.82

family_friendly_score: 0.44520000000000004

family_friendly_standard_error: 0.007028470103799262

submission_type: basic

model_repo: ChaiML/Katsuki-Bakugou-bkdk250708014515_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': 0.5267626605246389, 'latency_mean': 1.898290902376175, 'latency_p50': 1.8995410203933716, 'latency_p90': 2.096406888961792}, {'batch_size': 3, 'throughput': 1.067793304339008, 'latency_mean': 2.8030731749534605, 'latency_p50': 2.820895195007324, 'latency_p90': 3.0802274465560915}, {'batch_size': 5, 'throughput': 1.3489475354479785, 'latency_mean': 3.6831478917598726, 'latency_p50': 3.7240610122680664, 'latency_p90': 4.105534672737122}, {'batch_size': 6, 'throughput': 1.453123297217493, 'latency_mean': 4.105244021415711, 'latency_p50': 4.109063029289246, 'latency_p90': 4.607717418670655}, {'batch_size': 8, 'throughput': 1.5894456362959521, 'latency_mean': 4.9988015532493595, 'latency_p50': 5.012229084968567, 'latency_p90': 5.63821656703949}, {'batch_size': 10, 'throughput': 1.6669971041561853, 'latency_mean': 5.940837190151215, 'latency_p50': 5.927910685539246, 'latency_p90': 6.645943927764892}]

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

display_name: chaiml-katsuki-bakugou-_98991_v1

is_internal_developer: True

language_model: ChaiML/Katsuki-Bakugou-bkdk250708014515_sft

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-08

win_ratio: 0.49922779922779925

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': ['####\n', 'You:', '</s>', '\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-katsuki-bakugou-98991-v1-mkmlizer
Waiting for job on chaiml-katsuki-bakugou-98991-v1-mkmlizer to finish
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║                                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║                                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║                                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║                                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ║                                                                     ║
chaiml-katsuki-bakugou-98991-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-katsuki-bakugou-98991-v1-mkmlizer: Downloaded to shared memory in 88.221s
chaiml-katsuki-bakugou-98991-v1-mkmlizer: Checking if ChaiML/Katsuki-Bakugou-bkdk250708014515_sft already exists in ChaiML
chaiml-katsuki-bakugou-98991-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqpd3f2u1, device:0
chaiml-katsuki-bakugou-98991-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-katsuki-bakugou-98991-v1-mkmlizer: quantized model in 63.199s
chaiml-katsuki-bakugou-98991-v1-mkmlizer: Processed model ChaiML/Katsuki-Bakugou-bkdk250708014515_sft in 151.421s
chaiml-katsuki-bakugou-98991-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-katsuki-bakugou-98991-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-katsuki-bakugou-98991-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/config.json
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/special_tokens_map.json
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/tokenizer_config.json
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/tokenizer.json
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/flywheel_model.1.safetensors
chaiml-katsuki-bakugou-98991-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-katsuki-bakugou-98991-v1/nvidia/flywheel_model.0.safetensors
chaiml-katsuki-bakugou-98991-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:11, 31.64it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 25.47it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.52it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:16, 20.70it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:12, 26.55it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 21.71it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:12, 27.35it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 19.72it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:20, 15.82it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:17, 18.25it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.77it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:15, 20.78it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:14, 21.52it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.84it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:12, 25.00it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:14, 21.20it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 24.55it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:11, 25.51it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.18it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.62it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:14, 19.56it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:16, 17.53it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:14, 19.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:15, 17.27it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:13, 20.12it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:13, 19.38it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:13, 19.95it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:13, 20.09it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:13, 19.97it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:11, 21.76it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:15, 16.29it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 17.39it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:15, 16.14it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:12, 20.08it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:11, 20.68it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 20.52it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:10, 21.99it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:10, 21.97it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 21.52it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 23.30it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 22.62it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:10, 20.95it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:09, 22.07it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 26.07it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 16.84it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 17.77it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:13, 14.78it/s]
Loading 0:  45%|████▍     | 163/363 [00:08<00:09, 20.40it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:09, 20.97it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:09, 20.57it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:08, 22.21it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:08, 22.10it/s]
Loading 0:  49%|████▉     | 178/363 [00:08<00:08, 21.72it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:07, 23.43it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 25.49it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:11, 15.60it/s]
Loading 0:  53%|█████▎    | 193/363 [00:09<00:09, 18.45it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 19.07it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 20.65it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 20.65it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<05:18,  1.97s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<04:07,  1.54s/it]
Loading 0:  57%|█████▋    | 208/363 [00:28<02:13,  1.16it/s]
Loading 0:  58%|█████▊    | 211/363 [00:29<01:38,  1.54it/s]
Loading 0:  59%|█████▉    | 214/363 [00:29<01:11,  2.09it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:51,  2.86it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:38,  3.72it/s]
Loading 0:  61%|██████▏   | 223/363 [00:29<00:28,  5.00it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:22,  6.07it/s]
Loading 0:  63%|██████▎   | 229/363 [00:30<00:16,  7.90it/s]
Loading 0:  64%|██████▍   | 232/363 [00:30<00:13,  9.60it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:09, 13.46it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:08, 14.03it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:06, 17.83it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:06, 18.88it/s]
Loading 0:  69%|██████▉   | 250/363 [00:30<00:05, 19.09it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:04, 22.34it/s]
Loading 0:  71%|███████   | 258/363 [00:31<00:05, 19.61it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:04, 22.34it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:03, 25.18it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:05, 16.54it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 17.04it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:05, 14.79it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 20.04it/s]
Loading 0:  78%|███████▊  | 283/363 [00:32<00:03, 20.45it/s]
Loading 0:  79%|███████▉  | 286/363 [00:32<00:03, 20.95it/s]
Loading 0:  80%|███████▉  | 289/363 [00:32<00:03, 22.13it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:03, 21.59it/s]
Loading 0:  81%|████████▏ | 295/363 [00:33<00:03, 19.69it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 20.87it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 24.97it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.89it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 17.05it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:03, 14.76it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 19.93it/s]
Loading 0:  88%|████████▊ | 319/363 [00:34<00:02, 20.49it/s]
Loading 0:  89%|████████▊ | 322/363 [00:34<00:02, 20.42it/s]
Loading 0:  90%|████████▉ | 325/363 [00:34<00:01, 22.22it/s]
Loading 0:  90%|█████████ | 328/363 [00:34<00:01, 21.93it/s]
Loading 0:  91%|█████████ | 331/363 [00:34<00:01, 21.65it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 23.53it/s]
Loading 0:  93%|█████████▎| 337/363 [00:35<00:01, 19.60it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 12.71it/s]
Loading 0:  95%|█████████▌| 346/363 [00:35<00:00, 17.59it/s]
Loading 0:  96%|█████████▌| 349/363 [00:36<00:00, 16.75it/s]
Loading 0:  97%|█████████▋| 353/363 [00:36<00:00, 19.70it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.79it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00, 20.95it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 22.64it/s]
                                                            
Job chaiml-katsuki-bakugou-98991-v1-mkmlizer completed after 189.08s with status: succeeded
Stopping job with name chaiml-katsuki-bakugou-98991-v1-mkmlizer
Pipeline stage MKMLizer completed in 189.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-katsuki-bakugou-98991-v1
Waiting for inference service chaiml-katsuki-bakugou-98991-v1 to be ready
Inference service chaiml-katsuki-bakugou-98991-v1 ready after 191.45592617988586s
Pipeline stage MKMLDeployer completed in 191.98s
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 2.696760892868042s
Received healthy response to inference request in 2.146115779876709s
Received healthy response to inference request in 1.8469407558441162s
Received healthy response to inference request in 2.3778579235076904s
5 requests
1 failed requests
5th percentile: 1.9067757606506348
10th percentile: 1.9666107654571534
20th percentile: 2.0862807750701906
30th percentile: 2.1924642086029054
40th percentile: 2.2851610660552977
50th percentile: 2.3778579235076904
60th percentile: 2.505419111251831
70th percentile: 2.6329802989959714
80th percentile: 6.188799428939822
90th percentile: 13.172876501083376
95th percentile: 16.664915037155147
99th percentile: 19.45854586601257
mean time: 5.844925785064698
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0981967449188232s
Received healthy response to inference request in 1.9962570667266846s
Received healthy response to inference request in 2.1736350059509277s
Received healthy response to inference request in 1.8918211460113525s
Received healthy response to inference request in 2.4386041164398193s
5 requests
0 failed requests
5th percentile: 1.912708330154419
10th percentile: 1.9335955142974854
20th percentile: 1.9753698825836181
30th percentile: 2.016645002365112
40th percentile: 2.0574208736419677
50th percentile: 2.0981967449188232
60th percentile: 2.128372049331665
70th percentile: 2.158547353744507
80th percentile: 2.226628828048706
90th percentile: 2.3326164722442626
95th percentile: 2.385610294342041
99th percentile: 2.428005352020264
mean time: 2.1197028160095215
Pipeline stage StressChecker completed in 43.28s
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 0.83s
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 0.81s
Shutdown handler de-registered
chaiml-katsuki-bakugou-_98991_v1 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-katsuki-bakugou-98991-v1-profiler
Waiting for inference service chaiml-katsuki-bakugou-98991-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3003.57s
Shutdown handler de-registered
chaiml-katsuki-bakugou-_98991_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-katsuki-bakugou-_98991_v1 status is now torndown due to DeploymentManager action