auriaetherwiing-mn-12b-_82974

developer_uid: Luna1040

submission_id: auriaetherwiing-mn-12b-_82974_v3

model_name: auriaetherwiing-mn-12b-_82974_v3

model_group: AuriAetherwiing/MN-12B-S

status: torndown

timestamp: 2025-07-01T14:48:53+00:00

num_battles: 6203

num_wins: 2615

celo_rating: 1232.72

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: AuriAetherwiing/MN-12B-Starcannon-v2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5915292789056663, 'latency_mean': 1.6903748762607576, 'latency_p50': 1.6937187910079956, 'latency_p90': 1.848410177230835}, {'batch_size': 3, 'throughput': 1.0700087869314323, 'latency_mean': 2.787802869081497, 'latency_p50': 2.7729897499084473, 'latency_p90': 3.0875608444213865}, {'batch_size': 5, 'throughput': 1.2691657542223478, 'latency_mean': 3.919859262704849, 'latency_p50': 3.9125454425811768, 'latency_p90': 4.353006196022034}, {'batch_size': 6, 'throughput': 1.3493469931484683, 'latency_mean': 4.423746601343155, 'latency_p50': 4.42256772518158, 'latency_p90': 4.9246750831604}, {'batch_size': 8, 'throughput': 1.4130519338472196, 'latency_mean': 5.621564389467239, 'latency_p50': 5.640200138092041, 'latency_p90': 6.312069320678711}, {'batch_size': 10, 'throughput': 1.4221775452885324, 'latency_mean': 6.979641654491425, 'latency_p50': 7.0339765548706055, 'latency_p90': 7.857982540130616}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: auriaetherwiing-mn-12b-_82974_v3

is_internal_developer: False

language_model: AuriAetherwiing/MN-12B-Starcannon-v2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-07-01

win_ratio: 0.42157020796388844

generation_params: {'temperature': 0.65, 'top_p': 0.97, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 1.0, 'frequency_penalty': 0.82, 'stopping_words': ['<|eot_id|>', '[/INST]', '|im_end|', '<|start_header_id|>', '[INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

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 auriaetherwiing-mn-12b-82974-v3-mkmlizer
Waiting for job on auriaetherwiing-mn-12b-82974-v3-mkmlizer to finish
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║                                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║                                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Version: 0.29.3                                                    ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  https://mk1.ai                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║                                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  belonging to:                                                      ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║                                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Chai Research Corp.                                                ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ║                                                                     ║
auriaetherwiing-mn-12b-82974-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Downloaded to shared memory in 53.530s
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Checking if AuriAetherwiing/MN-12B-Starcannon-v2 already exists in ChaiML
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Creating repo ChaiML/MN-12B-Starcannon-v2 and uploading /tmp/tmp2f0le6hs to it
auriaetherwiing-mn-12b-82974-v3-mkmlizer: 
  0%|          | 0/5 [00:00<?, ?it/s]
 20%|██        | 1/5 [00:03<00:15,  3.85s/it]
 40%|████      | 2/5 [00:11<00:18,  6.07s/it]
 60%|██████    | 3/5 [00:19<00:13,  6.96s/it]
 80%|████████  | 4/5 [00:26<00:06,  6.92s/it]
100%|██████████| 5/5 [00:31<00:00,  6.36s/it]
100%|██████████| 5/5 [00:31<00:00,  6.34s/it]
auriaetherwiing-mn-12b-82974-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2f0le6hs, device:0
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
auriaetherwiing-mn-12b-82974-v3-mkmlizer: quantized model in 30.731s
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Processed model AuriAetherwiing/MN-12B-Starcannon-v2 in 143.313s
auriaetherwiing-mn-12b-82974-v3-mkmlizer: creating bucket guanaco-mkml-models
auriaetherwiing-mn-12b-82974-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
auriaetherwiing-mn-12b-82974-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/config.json
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/special_tokens_map.json
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/tokenizer_config.json
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/vocab.json
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/merges.txt
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/tokenizer.json
auriaetherwiing-mn-12b-82974-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/auriaetherwiing-mn-12b-82974-v3/flywheel_model.0.safetensors
auriaetherwiing-mn-12b-82974-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:56,  3.15s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:01,  1.18it/s]
Loading 0:   4%|▍         | 14/363 [00:06<01:38,  3.56it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:59,  5.77it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:44,  7.55it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:26, 12.60it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:20, 16.15it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:20, 15.83it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:14, 21.48it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:12, 24.83it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 27.71it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 34.24it/s]
Loading 0:  20%|██        | 74/363 [00:08<00:08, 35.83it/s]
Loading 0:  22%|██▏       | 79/363 [00:08<00:07, 37.00it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 42.58it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 44.10it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 37.35it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 43.51it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 42.70it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 43.08it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 44.14it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:08, 26.79it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 34.54it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 36.47it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 38.22it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 40.89it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:05, 35.64it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 42.40it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 42.02it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 42.45it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 40.88it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 40.73it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 44.20it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 43.93it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 43.97it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:03, 41.38it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 28.51it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 33.95it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 35.97it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 37.90it/s]
Loading 0:  63%|██████▎   | 227/363 [00:12<00:03, 37.81it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 38.01it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 41.87it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 42.13it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 42.22it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 43.52it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 35.41it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 42.54it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 42.85it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 43.06it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 44.57it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 26.10it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 32.33it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 33.90it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 34.15it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:01, 34.77it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 37.13it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:01, 39.93it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:01, 34.38it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 41.72it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 42.12it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 41.73it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 43.73it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 36.21it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 41.63it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 41.27it/s]
                                                            
Job auriaetherwiing-mn-12b-82974-v3-mkmlizer completed after 167.52s with status: succeeded
Stopping job with name auriaetherwiing-mn-12b-82974-v3-mkmlizer
Pipeline stage MKMLizer completed in 167.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service auriaetherwiing-mn-12b-82974-v3
Waiting for inference service auriaetherwiing-mn-12b-82974-v3 to be ready
Failed to get response for submission chaiml-mistralnemo-12b-_88791_v2: HTTPConnectionPool(host='chaiml-mistralnemo-12b-88791-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service auriaetherwiing-mn-12b-82974-v3 ready after 200.75506711006165s
Pipeline stage MKMLDeployer completed in 201.45s
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 2.804413318634033s
Received healthy response to inference request in 1.5482306480407715s
Received healthy response to inference request in 1.703977108001709s
Received healthy response to inference request in 1.8902251720428467s
5 requests
1 failed requests
5th percentile: 1.579379940032959
10th percentile: 1.6105292320251465
20th percentile: 1.6728278160095216
30th percentile: 1.7412267208099366
40th percentile: 1.8157259464263915
50th percentile: 1.8902251720428467
60th percentile: 2.255900430679321
70th percentile: 2.6215756893157955
80th percentile: 6.274551486968997
90th percentile: 13.214827823638917
95th percentile: 16.684965991973876
99th percentile: 19.461076526641847
mean time: 5.62039008140564
%s, retrying in %s seconds...
Received healthy response to inference request in 2.089444637298584s
Received healthy response to inference request in 1.6295928955078125s
Received healthy response to inference request in 1.7369990348815918s
Received healthy response to inference request in 1.9778037071228027s
Received healthy response to inference request in 1.5655269622802734s
5 requests
0 failed requests
5th percentile: 1.5783401489257813
10th percentile: 1.591153335571289
20th percentile: 1.6167797088623046
30th percentile: 1.6510741233825683
40th percentile: 1.6940365791320802
50th percentile: 1.7369990348815918
60th percentile: 1.8333209037780762
70th percentile: 1.9296427726745604
80th percentile: 2.000131893157959
90th percentile: 2.0447882652282714
95th percentile: 2.067116451263428
99th percentile: 2.0849790000915527
mean time: 1.799873447418213
Pipeline stage StressChecker completed in 39.80s
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 0.77s
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 1.58s
Shutdown handler de-registered
auriaetherwiing-mn-12b-_82974_v3 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service auriaetherwiing-mn-12b-82974-v3-profiler
Waiting for inference service auriaetherwiing-mn-12b-82974-v3-profiler to be ready
Inference service auriaetherwiing-mn-12b-82974-v3-profiler ready after 211.80746865272522s
Pipeline stage MKMLProfilerDeployer completed in 212.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/auriaetherwiing-mn-1e6b0da11676ece202b140f520842c684-deplonr68x:/code/chaiverse_profiler_1751382019 --namespace tenant-chaiml-guanaco
kubectl exec -it auriaetherwiing-mn-1e6b0da11676ece202b140f520842c684-deplonr68x --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751382019 && 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_1751382019/summary.json'
kubectl exec -it auriaetherwiing-mn-1e6b0da11676ece202b140f520842c684-deplonr68x --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1751382019/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1123.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service auriaetherwiing-mn-12b-82974-v3-profiler is running
Tearing down inference service auriaetherwiing-mn-12b-82974-v3-profiler
Service auriaetherwiing-mn-12b-82974-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.25s
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
auriaetherwiing-mn-12b-_82974_v3 status is now inactive due to auto deactivation removed underperforming models
auriaetherwiing-mn-12b-_82974_v3 status is now torndown due to DeploymentManager action