developer_uid: chai_backend_admin
submission_id: chaiml-dante-sparda-dev_92928_v1
model_name: chaiml-dante-sparda-dev_92928_v1
model_group: ChaiML/Dante-Sparda-Devi
status: torndown
timestamp: 2025-05-13T17:31:01+00:00
num_battles: 6917
num_wins: 3529
celo_rating: 1296.6
family_friendly_score: 0.5462
family_friendly_standard_error: 0.007040817566163747
submission_type: basic
model_repo: ChaiML/Dante-Sparda-Devil-May-Cry_cursed-prin250513091815_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': 0.5392626250907087, 'latency_mean': 1.8543268132209778, 'latency_p50': 1.851613998413086, 'latency_p90': 2.0631159782409667}, {'batch_size': 3, 'throughput': 1.098344027270686, 'latency_mean': 2.7225686275959013, 'latency_p50': 2.731723189353943, 'latency_p90': 2.990034747123718}, {'batch_size': 5, 'throughput': 1.4249710384756593, 'latency_mean': 3.4985492622852323, 'latency_p50': 3.4901700019836426, 'latency_p90': 3.9488659143447875}, {'batch_size': 6, 'throughput': 1.5412508839112058, 'latency_mean': 3.873530554771423, 'latency_p50': 3.892714500427246, 'latency_p90': 4.3342678308486935}, {'batch_size': 8, 'throughput': 1.671882340269434, 'latency_mean': 4.734880946874618, 'latency_p50': 4.748491644859314, 'latency_p90': 5.279917001724243}, {'batch_size': 10, 'throughput': 1.779229017401955, 'latency_mean': 5.5839253282547, 'latency_p50': 5.583253741264343, 'latency_p90': 6.2162025451660154}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-dante-sparda-dev_92928_v1
is_internal_developer: True
language_model: ChaiML/Dante-Sparda-Devil-May-Cry_cursed-prin250513091815_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.5
us_pacific_date: 2025-05-13
win_ratio: 0.5101922798901257
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-dante-sparda-dev-92928-v1-mkmlizer
Waiting for job on chaiml-dante-sparda-dev-92928-v1-mkmlizer to finish
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║       /___/                                                         ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║                                                                     ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║                                                                     ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║                                                                     ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ║                                                                     ║
chaiml-dante-sparda-dev-92928-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-dante-sparda-dev-92928-v1-mkmlizer: Downloaded to shared memory in 80.160s
chaiml-dante-sparda-dev-92928-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk6oddo8u, device:0
chaiml-dante-sparda-dev-92928-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-dante-sparda-dev-92928-v1-mkmlizer: quantized model in 53.831s
chaiml-dante-sparda-dev-92928-v1-mkmlizer: Processed model ChaiML/Dante-Sparda-Devil-May-Cry_cursed-prin250513091815_sft in 133.992s
chaiml-dante-sparda-dev-92928-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-dante-sparda-dev-92928-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-dante-sparda-dev-92928-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/config.json
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/special_tokens_map.json
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/tokenizer_config.json
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/tokenizer.json
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/flywheel_model.1.safetensors
chaiml-dante-sparda-dev-92928-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-dante-sparda-dev-92928-v1/flywheel_model.0.safetensors
chaiml-dante-sparda-dev-92928-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.13it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.82it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.40it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.14it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.27it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.56it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.66it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.36it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.45it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.69it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.11it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.14it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.91it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.55it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.30it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.20it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.34it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.60it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.57it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.94it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 26.72it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.07it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.86it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.95it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.26it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.62it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.12it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.39it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.35it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.63it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 23.73it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.44it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.66it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 24.09it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.69it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.02it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.82it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.61it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.83it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.41it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.12it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.33it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.68it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.68it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.91it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.15it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.30it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.30it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.30it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.94it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.84it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.13it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.95it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.19it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.83it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.40it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.05it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 22.99it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 19.71it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 25.95it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 27.52it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.07it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.10it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.40it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.92it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.99it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.24it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.15it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.61it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.07it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.72it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.21it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.73it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:13,  1.69it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.81it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.53it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.22it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.78it/s]
                                                            

Job chaiml-dante-sparda-dev-92928-v1-mkmlizer completed after 156.76s with status: succeeded
Stopping job with name chaiml-dante-sparda-dev-92928-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.48s
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-dante-sparda-dev-92928-v1
Waiting for inference service chaiml-dante-sparda-dev-92928-v1 to be ready
Inference service chaiml-dante-sparda-dev-92928-v1 ready after 130.7126247882843s
Pipeline stage MKMLDeployer completed in 131.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4959444999694824s
Received healthy response to inference request in 2.552187919616699s
Received healthy response to inference request in 2.443718433380127s
Received healthy response to inference request in 2.78271484375s
Received healthy response to inference request in 2.5131678581237793s
5 requests
0 failed requests
5th percentile: 2.454163646697998
10th percentile: 2.4646088600158693
20th percentile: 2.4854992866516112
30th percentile: 2.499389171600342
40th percentile: 2.5062785148620605
50th percentile: 2.5131678581237793
60th percentile: 2.5287758827209474
70th percentile: 2.544383907318115
80th percentile: 2.5982933044433594
90th percentile: 2.6905040740966797
95th percentile: 2.73660945892334
99th percentile: 2.773493766784668
mean time: 2.5575467109680177
Pipeline stage StressChecker completed in 14.08s
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 0.88s
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-dante-sparda-dev_92928_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-dante-sparda-dev-92928-v1-profiler
Waiting for inference service chaiml-dante-sparda-dev-92928-v1-profiler to be ready
Inference service chaiml-dante-sparda-dev-92928-v1-profiler ready after 120.77514362335205s
Pipeline stage MKMLProfilerDeployer completed in 121.53s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-dante-sparda-90f0df82f5ccbe521a3814d448a6a753-deplos22hx:/code/chaiverse_profiler_1747158246 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-dante-sparda-90f0df82f5ccbe521a3814d448a6a753-deplos22hx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1747158246 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1747158246/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Received signal 15, running shutdown handler
Shutdown handler de-registered
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 2942.26s
Shutdown handler de-registered
chaiml-dante-sparda-dev_92928_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-dante-sparda-dev_92928_v1 status is now torndown due to DeploymentManager action