developer_uid: richhx
submission_id: chaiml-sukuna-mafia-bos_77581_v2
model_name: chaiml-sukuna-mafia-bos_77581_v2
model_group: ChaiML/sukuna-mafia-boss
status: torndown
timestamp: 2025-07-08T05:40:03+00:00
num_battles: 8053
num_wins: 3964
celo_rating: 1281.81
family_friendly_score: 0.532
family_friendly_standard_error: 0.007056571405434795
submission_type: basic
model_repo: ChaiML/sukuna-mafia-boss_Blade-Mafia-Au_dark-250410135759_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': 0.4886335777999598, 'latency_mean': 2.046357647180557, 'latency_p50': 2.049023389816284, 'latency_p90': 2.2895750999450684}, {'batch_size': 3, 'throughput': 0.9422312247530338, 'latency_mean': 3.174185254573822, 'latency_p50': 3.152275562286377, 'latency_p90': 3.5326223850250242}, {'batch_size': 5, 'throughput': 1.1764702829935938, 'latency_mean': 4.228174651861191, 'latency_p50': 4.181949496269226, 'latency_p90': 4.770933938026428}, {'batch_size': 6, 'throughput': 1.2604645345457934, 'latency_mean': 4.718555228710175, 'latency_p50': 4.7504308223724365, 'latency_p90': 5.367487525939941}, {'batch_size': 8, 'throughput': 1.3666811937432546, 'latency_mean': 5.802520288228989, 'latency_p50': 5.809017181396484, 'latency_p90': 6.542089939117432}, {'batch_size': 10, 'throughput': 1.4167029500193937, 'latency_mean': 6.982950531244278, 'latency_p50': 6.984783172607422, 'latency_p90': 7.892001390457153}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-sukuna-mafia-bos_77581_v2
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/sukuna-mafia-boss_Blade-Mafia-Au_dark-250410135759_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.08
us_pacific_date: 2025-07-07
win_ratio: 0.4922389171737241
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:', '####', '\n', '</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-sukuna-mafia-bos-77581-v2-mkmlizer
Waiting for job on chaiml-sukuna-mafia-bos-77581-v2-mkmlizer to finish
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ belonging to: ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ║ ║
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Downloaded to shared memory in 79.150s
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Checking if ChaiML/sukuna-mafia-boss_Blade-Mafia-Au_dark-250410135759_sft already exists in ChaiML
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdfkh96ev, device:0
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: quantized model in 49.036s
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Processed model ChaiML/sukuna-mafia-boss_Blade-Mafia-Au_dark-250410135759_sft in 128.187s
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/config.json
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/special_tokens_map.json
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/tokenizer_config.json
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/tokenizer.json
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/flywheel_model.1.safetensors
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sukuna-mafia-bos-77581-v2/nvidia/flywheel_model.0.safetensors
chaiml-sukuna-mafia-bos-77581-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 37.46it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 28.48it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 30.55it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:12, 27.86it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:10, 31.90it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:11, 28.91it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 34.37it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:15, 21.04it/s] Loading 0: 11%|█ | 40/363 [00:01<00:13, 23.87it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:12, 25.23it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 27.07it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 26.03it/s] Loading 0: 16%|█▌ | 57/363 [00:02<00:10, 28.75it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 27.08it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 27.70it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 24.20it/s] Loading 0: 20%|██ | 73/363 [00:02<00:14, 20.60it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:11, 25.67it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 24.65it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 25.94it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 25.33it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:13, 20.66it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 27.42it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:10, 24.62it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:11, 21.77it/s] Loading 0: 31%|███ | 112/363 [00:04<00:10, 24.77it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:10, 24.55it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 27.44it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 24.70it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:08, 29.22it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 27.77it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:07, 29.63it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 28.06it/s] Loading 0: 40%|████ | 147/363 [00:05<00:06, 32.70it/s] Loading 0: 42%|████▏ | 151/363 [00:05<00:09, 23.51it/s] Loading 0: 42%|████▏ | 154/363 [00:05<00:09, 21.89it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:08, 23.14it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:08, 23.38it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 26.48it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:08, 23.68it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 27.97it/s] Loading 0: 49%|████▉ | 177/363 [00:06<00:07, 24.86it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:06, 26.85it/s] Loading 0: 52%|█████▏ | 187/363 [00:07<00:07, 23.62it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 22.30it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 23.39it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 23.46it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:06, 23.46it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<03:04, 1.14s/it] Loading 0: 56%|█████▌ | 203/363 [00:22<02:32, 1.05it/s] Loading 0: 57%|█████▋ | 208/363 [00:22<01:31, 1.69it/s] Loading 0: 58%|█████▊ | 211/363 [00:22<01:10, 2.15it/s] Loading 0: 59%|█████▉ | 214/363 [00:23<00:52, 2.84it/s] Loading 0: 60%|██████ | 218/363 [00:23<00:35, 4.05it/s] Loading 0: 61%|██████ | 221/363 [00:23<00:27, 5.15it/s] Loading 0: 62%|██████▏ | 224/363 [00:23<00:22, 6.05it/s] Loading 0: 63%|██████▎ | 228/363 [00:23<00:15, 8.50it/s] Loading 0: 64%|██████▎ | 231/363 [00:23<00:13, 9.84it/s] Loading 0: 65%|██████▍ | 235/363 [00:23<00:09, 13.17it/s] Loading 0: 66%|██████▌ | 238/363 [00:24<00:08, 15.31it/s] Loading 0: 66%|██████▋ | 241/363 [00:24<00:07, 16.62it/s] Loading 0: 67%|██████▋ | 244/363 [00:24<00:06, 18.98it/s] Loading 0: 68%|██████▊ | 247/363 [00:24<00:05, 20.86it/s] Loading 0: 69%|██████▉ | 250/363 [00:24<00:05, 21.69it/s] Loading 0: 70%|███████ | 255/363 [00:24<00:04, 25.31it/s] Loading 0: 71%|███████ | 258/363 [00:24<00:04, 22.94it/s] Loading 0: 72%|███████▏ | 262/363 [00:24<00:03, 26.66it/s] Loading 0: 74%|███████▎ | 267/363 [00:25<00:04, 22.91it/s] Loading 0: 74%|███████▍ | 270/363 [00:25<00:04, 19.75it/s] Loading 0: 75%|███████▌ | 274/363 [00:25<00:03, 22.85it/s] Loading 0: 76%|███████▋ | 277/363 [00:25<00:03, 23.37it/s] Loading 0: 78%|███████▊ | 282/363 [00:25<00:03, 25.94it/s] Loading 0: 79%|███████▊ | 285/363 [00:25<00:03, 23.46it/s] Loading 0: 80%|████████ | 291/363 [00:26<00:02, 28.28it/s] Loading 0: 81%|████████ | 294/363 [00:26<00:02, 25.22it/s] Loading 0: 82%|████████▏ | 299/363 [00:26<00:02, 27.53it/s] Loading 0: 84%|████████▎ | 304/363 [00:26<00:02, 24.06it/s] Loading 0: 85%|████████▍ | 307/363 [00:26<00:02, 22.42it/s] Loading 0: 85%|████████▌ | 310/363 [00:26<00:02, 23.44it/s] Loading 0: 86%|████████▌ | 313/363 [00:27<00:02, 23.56it/s] Loading 0: 88%|████████▊ | 318/363 [00:27<00:01, 26.43it/s] Loading 0: 88%|████████▊ | 321/363 [00:27<00:01, 23.88it/s] Loading 0: 90%|█████████ | 327/363 [00:27<00:01, 27.37it/s] Loading 0: 91%|█████████ | 330/363 [00:27<00:01, 24.12it/s] Loading 0: 92%|█████████▏| 335/363 [00:27<00:01, 26.00it/s] Loading 0: 93%|█████████▎| 338/363 [00:28<00:00, 25.08it/s] Loading 0: 94%|█████████▍| 341/363 [00:28<00:01, 15.19it/s] Loading 0: 96%|█████████▌| 347/363 [00:28<00:00, 20.68it/s] Loading 0: 96%|█████████▋| 350/363 [00:28<00:00, 21.36it/s] Loading 0: 97%|█████████▋| 353/363 [00:28<00:00, 22.68it/s] Loading 0: 98%|█████████▊| 357/363 [00:29<00:00, 21.31it/s]
Job chaiml-sukuna-mafia-bos-77581-v2-mkmlizer completed after 157.42s with status: succeeded
Stopping job with name chaiml-sukuna-mafia-bos-77581-v2-mkmlizer
Pipeline stage MKMLizer completed in 158.01s
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-sukuna-mafia-bos-77581-v2
Waiting for inference service chaiml-sukuna-mafia-bos-77581-v2 to be ready
Failed to get response for submission chaiml-llama31-mer-v2-t_76345_v1: HTTPConnectionPool(host='chaiml-llama31-mer-v2-t-76345-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-llama31-mer-v2-t_76345_v1: HTTPConnectionPool(host='chaiml-llama31-mer-v2-t-76345-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-sukuna-mafia-bos-77581-v2 ready after 191.22965359687805s
Pipeline stage MKMLDeployer completed in 191.73s
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 1.9301064014434814s
Received healthy response to inference request in 2.041766405105591s
Received healthy response to inference request in 1.8491220474243164s
Received healthy response to inference request in 1.9392366409301758s
5 requests
1 failed requests
5th percentile: 1.8653189182281493
10th percentile: 1.8815157890319825
20th percentile: 1.9139095306396485
30th percentile: 1.9319324493408203
40th percentile: 1.935584545135498
50th percentile: 1.9392366409301758
60th percentile: 1.9802485466003419
70th percentile: 2.021260452270508
80th percentile: 5.66836066246033
90th percentile: 12.921549177169801
95th percentile: 16.548143434524533
99th percentile: 19.449418840408324
mean time: 5.586993837356568
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9679713249206543s
Received healthy response to inference request in 1.867532730102539s
Received healthy response to inference request in 2.271801710128784s
Received healthy response to inference request in 2.445601224899292s
Received healthy response to inference request in 1.9270923137664795s
5 requests
0 failed requests
5th percentile: 1.8794446468353272
10th percentile: 1.8913565635681153
20th percentile: 1.9151803970336914
30th percentile: 1.9352681159973144
40th percentile: 1.9516197204589845
50th percentile: 1.9679713249206543
60th percentile: 2.0895034790039064
70th percentile: 2.211035633087158
80th percentile: 2.3065616130828857
90th percentile: 2.376081418991089
95th percentile: 2.4108413219451905
99th percentile: 2.4386492443084715
mean time: 2.0959998607635497
Pipeline stage StressChecker completed in 41.33s
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 0.96s
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 0.66s
Shutdown handler de-registered
chaiml-sukuna-mafia-bos_77581_v2 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 3266.87s
Shutdown handler de-registered
chaiml-sukuna-mafia-bos_77581_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-sukuna-mafia-bos_77581_v2 status is now torndown due to DeploymentManager action