nitral-ai-captain-eris_45741

developer_uid: huohuo12

submission_id: nitral-ai-captain-eris_45741_v16

model_name: nitral-ai-captain-eris_45741_v16

model_group: Nitral-AI/Captain-Eris_V

status: torndown

timestamp: 2025-02-20T09:44:01+00:00

num_battles: 5649

num_wins: 2959

celo_rating: 1274.67

family_friendly_score: 0.5836

family_friendly_standard_error: 0.0069715283833604235

submission_type: basic

model_repo: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6049507800288251, 'latency_mean': 1.6529330337047576, 'latency_p50': 1.6583338975906372, 'latency_p90': 1.8209377765655517}, {'batch_size': 3, 'throughput': 1.0889455132977066, 'latency_mean': 2.7429597294330597, 'latency_p50': 2.735358476638794, 'latency_p90': 3.0305795431137086}, {'batch_size': 5, 'throughput': 1.3027393475135738, 'latency_mean': 3.8168420708179474, 'latency_p50': 3.852033495903015, 'latency_p90': 4.232879257202148}, {'batch_size': 6, 'throughput': 1.3853036740351692, 'latency_mean': 4.3114168989658355, 'latency_p50': 4.317382574081421, 'latency_p90': 4.803459477424622}, {'batch_size': 8, 'throughput': 1.4380514894388183, 'latency_mean': 5.524146363735199, 'latency_p50': 5.582967758178711, 'latency_p90': 6.226264381408692}, {'batch_size': 10, 'throughput': 1.48917420418, 'latency_mean': 6.647685791254044, 'latency_p50': 6.636224865913391, 'latency_p90': 7.60669219493866}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-captain-eris_45741_v16

is_internal_developer: False

language_model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-02-20

win_ratio: 0.5238095238095238

generation_params: {'temperature': 0.75, 'top_p': 0.88, 'min_p': 0.02, 'top_k': 50, 'presence_penalty': 0.65, 'frequency_penalty': 0.25, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 nitral-ai-captain-eris-45741-v16-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v16-mkmlizer to finish
nitral-ai-captain-eris-45741-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v16-mkmlizer: ║     _____            __           __                                ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║       /___/                                                         ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  Version: 0.12.8                                                    ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-eris-45741-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v16-mkmlizer: Downloaded to shared memory in 33.855s
nitral-ai-captain-eris-45741-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpewrhp5rr, device:0
nitral-ai-captain-eris-45741-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v16-mkmlizer: quantized model in 39.393s
nitral-ai-captain-eris-45741-v16-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 73.248s
nitral-ai-captain-eris-45741-v16-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16
nitral-ai-captain-eris-45741-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16/config.json
nitral-ai-captain-eris-45741-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16/special_tokens_map.json
nitral-ai-captain-eris-45741-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16/tokenizer_config.json
nitral-ai-captain-eris-45741-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16/tokenizer.json
nitral-ai-captain-eris-45741-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v16/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:28,  3.07s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:56,  1.20it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:11,  2.68it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.15it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:51,  6.66it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:38,  8.73it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:26, 12.43it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:22, 14.47it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:17, 18.86it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:20, 15.56it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:15, 19.94it/s]
Loading 0:  14%|█▍        | 51/363 [00:07<00:14, 21.09it/s]
Loading 0:  15%|█▌        | 56/363 [00:08<00:12, 25.17it/s]
Loading 0:  17%|█▋        | 60/363 [00:08<00:12, 24.82it/s]
Loading 0:  18%|█▊        | 65/363 [00:08<00:10, 29.36it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:10, 28.62it/s]
Loading 0:  20%|██        | 74/363 [00:08<00:08, 33.01it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 30.79it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:08, 34.84it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 32.34it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:07, 36.21it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:08, 32.85it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 39.37it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 38.49it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 36.78it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 35.13it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:09, 25.73it/s]
Loading 0:  34%|███▍      | 124/363 [00:10<00:09, 25.32it/s]
Loading 0:  35%|███▌      | 128/363 [00:10<00:08, 27.77it/s]
Loading 0:  36%|███▋      | 132/363 [00:10<00:08, 26.92it/s]
Loading 0:  38%|███▊      | 137/363 [00:10<00:07, 31.80it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:07, 29.94it/s]
Loading 0:  40%|████      | 146/363 [00:10<00:06, 34.16it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 30.50it/s]
Loading 0:  43%|████▎     | 155/363 [00:11<00:06, 33.86it/s]
Loading 0:  44%|████▍     | 159/363 [00:11<00:06, 31.00it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:05, 35.31it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:06, 32.25it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 36.01it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:05, 32.51it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:05, 36.00it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:05, 32.15it/s]
Loading 0:  53%|█████▎    | 191/363 [00:12<00:04, 36.01it/s]
Loading 0:  54%|█████▎    | 195/363 [00:12<00:05, 32.60it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:04, 35.88it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:06, 24.08it/s]
Loading 0:  58%|█████▊    | 209/363 [00:12<00:05, 28.71it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:05, 27.63it/s]
Loading 0:  60%|██████    | 218/363 [00:13<00:04, 31.57it/s]
Loading 0:  61%|██████    | 222/363 [00:13<00:04, 28.24it/s]
Loading 0:  63%|██████▎   | 227/363 [00:13<00:04, 32.50it/s]
Loading 0:  64%|██████▎   | 231/363 [00:13<00:04, 30.00it/s]
Loading 0:  65%|██████▌   | 236/363 [00:13<00:03, 34.04it/s]
Loading 0:  66%|██████▌   | 240/363 [00:13<00:03, 31.17it/s]
Loading 0:  67%|██████▋   | 245/363 [00:13<00:03, 35.28it/s]
Loading 0:  69%|██████▊   | 249/363 [00:14<00:03, 32.72it/s]
Loading 0:  70%|██████▉   | 254/363 [00:14<00:02, 36.63it/s]
Loading 0:  71%|███████   | 258/363 [00:14<00:03, 32.46it/s]
Loading 0:  72%|███████▏  | 263/363 [00:14<00:02, 36.13it/s]
Loading 0:  74%|███████▎  | 267/363 [00:14<00:02, 32.85it/s]
Loading 0:  75%|███████▍  | 272/363 [00:14<00:02, 36.44it/s]
Loading 0:  76%|███████▌  | 276/363 [00:14<00:02, 32.09it/s]
Loading 0:  77%|███████▋  | 281/363 [00:14<00:02, 35.69it/s]
Loading 0:  79%|███████▊  | 285/363 [00:15<00:03, 22.95it/s]
Loading 0:  80%|███████▉  | 290/363 [00:15<00:02, 27.76it/s]
Loading 0:  81%|████████  | 294/363 [00:15<00:02, 27.20it/s]
Loading 0:  82%|████████▏ | 299/363 [00:15<00:02, 31.44it/s]
Loading 0:  83%|████████▎ | 303/363 [00:15<00:02, 29.32it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:01, 33.83it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:01, 31.18it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:01, 34.68it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:01, 31.65it/s]
Loading 0:  90%|████████▉ | 326/363 [00:16<00:01, 35.62it/s]
Loading 0:  91%|█████████ | 330/363 [00:16<00:01, 32.18it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:00, 35.12it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:00, 31.84it/s]
Loading 0:  95%|█████████▍| 344/363 [00:16<00:00, 34.94it/s]
Loading 0:  96%|█████████▌| 348/363 [00:17<00:00, 31.53it/s]
Loading 0:  97%|█████████▋| 353/363 [00:17<00:00, 34.96it/s]
Loading 0:  98%|█████████▊| 357/363 [00:17<00:00, 31.34it/s]
Loading 0: 100%|█████████▉| 362/363 [00:17<00:00, 34.76it/s]
                                                            
Job nitral-ai-captain-eris-45741-v16-mkmlizer completed after 95.14s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v16-mkmlizer
Pipeline stage MKMLizer completed in 95.63s
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 nitral-ai-captain-eris-45741-v16
Waiting for inference service nitral-ai-captain-eris-45741-v16 to be ready
Inference service nitral-ai-captain-eris-45741-v16 ready after 200.67253279685974s
Pipeline stage MKMLDeployer completed in 201.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3964810371398926s
Received healthy response to inference request in 1.6859679222106934s
Received healthy response to inference request in 1.6049580574035645s
Received healthy response to inference request in 1.6594619750976562s
Received healthy response to inference request in 1.6247057914733887s
5 requests
0 failed requests
5th percentile: 1.6089076042175292
10th percentile: 1.6128571510314942
20th percentile: 1.620756244659424
30th percentile: 1.631657028198242
40th percentile: 1.6455595016479492
50th percentile: 1.6594619750976562
60th percentile: 1.670064353942871
70th percentile: 1.680666732788086
80th percentile: 1.8280705451965333
90th percentile: 2.112275791168213
95th percentile: 2.2543784141540524
99th percentile: 2.3680605125427245
mean time: 1.7943149566650392
Pipeline stage StressChecker completed in 10.23s
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 0.72s
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 0.80s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v16 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 2603.33s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v16 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v16 status is now torndown due to DeploymentManager action