developer_uid: huohuo12
submission_id: nitral-ai-captain-eris_45741_v24
model_name: nitral-ai-captain-eris_45741_v24
model_group: Nitral-AI/Captain-Eris_V
status: torndown
timestamp: 2025-02-21T03:46:14+00:00
num_battles: 6850
num_wins: 3436
celo_rating: 1267.19
family_friendly_score: 0.5788
family_friendly_standard_error: 0.006982700910106346
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': 0.6054517023237871, 'latency_mean': 1.6515615940093995, 'latency_p50': 1.651496171951294, 'latency_p90': 1.8072609663009644}, {'batch_size': 3, 'throughput': 1.0879983979515777, 'latency_mean': 2.748021775484085, 'latency_p50': 2.7478398084640503, 'latency_p90': 3.006587767601013}, {'batch_size': 5, 'throughput': 1.310105051018326, 'latency_mean': 3.797116700410843, 'latency_p50': 3.7877843379974365, 'latency_p90': 4.247452998161315}, {'batch_size': 6, 'throughput': 1.3600650359697104, 'latency_mean': 4.380479127168655, 'latency_p50': 4.357112884521484, 'latency_p90': 4.916397476196289}, {'batch_size': 8, 'throughput': 1.4477292357700318, 'latency_mean': 5.499806344509125, 'latency_p50': 5.466030240058899, 'latency_p90': 6.231579995155334}, {'batch_size': 10, 'throughput': 1.47518157957153, 'latency_mean': 6.736113352775574, 'latency_p50': 6.734333515167236, 'latency_p90': 7.575246787071228}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nitral-ai-captain-eris_45741_v24
is_internal_developer: False
language_model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-02-20
win_ratio: 0.5016058394160584
generation_params: {'temperature': 0.74, 'top_p': 0.86, '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-v24-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v24-mkmlizer to finish
nitral-ai-captain-eris-45741-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ /___/ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ Version: 0.12.8 ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ belonging to: ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v24-mkmlizer: Downloaded to shared memory in 32.001s
nitral-ai-captain-eris-45741-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp63owl7ay, device:0
nitral-ai-captain-eris-45741-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v24-mkmlizer: quantized model in 37.672s
nitral-ai-captain-eris-45741-v24-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 69.674s
nitral-ai-captain-eris-45741-v24-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24
nitral-ai-captain-eris-45741-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24/special_tokens_map.json
nitral-ai-captain-eris-45741-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24/config.json
nitral-ai-captain-eris-45741-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24/tokenizer_config.json
nitral-ai-captain-eris-45741-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24/tokenizer.json
nitral-ai-captain-eris-45741-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v24/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v24-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:15, 3.03s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:52, 1.22it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:08, 2.73it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:21, 4.26it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:40, 8.44it/s] Loading 0: 8%|▊ | 28/363 [00:06<00:29, 11.50it/s] Loading 0: 9%|▉ | 33/363 [00:06<00:23, 13.84it/s] Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.63it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 18.82it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:13, 22.78it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 24.50it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:10, 28.55it/s] Loading 0: 17%|█▋ | 62/363 [00:07<00:10, 29.72it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 34.07it/s] Loading 0: 20%|█▉ | 72/363 [00:08<00:08, 35.46it/s] Loading 0: 21%|██ | 77/363 [00:08<00:07, 37.29it/s] Loading 0: 23%|██▎ | 82/363 [00:08<00:07, 39.26it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 33.13it/s] Loading 0: 26%|██▌ | 94/363 [00:08<00:06, 41.02it/s] Loading 0: 27%|██▋ | 99/363 [00:08<00:06, 40.41it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:06, 40.37it/s] Loading 0: 30%|███ | 109/363 [00:08<00:06, 40.32it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:07, 32.23it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:08, 29.44it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 30.07it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 33.40it/s] Loading 0: 37%|███▋ | 134/363 [00:09<00:06, 33.29it/s] Loading 0: 38%|███▊ | 139/363 [00:09<00:06, 36.01it/s] Loading 0: 39%|███▉ | 143/363 [00:10<00:06, 35.09it/s] Loading 0: 41%|████ | 148/363 [00:10<00:05, 37.77it/s] Loading 0: 42%|████▏ | 152/363 [00:10<00:05, 36.59it/s] Loading 0: 43%|████▎ | 157/363 [00:10<00:05, 39.34it/s] Loading 0: 45%|████▍ | 162/363 [00:10<00:05, 38.40it/s] Loading 0: 46%|████▌ | 166/363 [00:10<00:05, 37.97it/s] Loading 0: 47%|████▋ | 170/363 [00:10<00:05, 36.34it/s] Loading 0: 48%|████▊ | 175/363 [00:10<00:04, 38.91it/s] Loading 0: 49%|████▉ | 179/363 [00:10<00:04, 37.45it/s] Loading 0: 51%|█████ | 184/363 [00:11<00:04, 39.83it/s] Loading 0: 52%|█████▏ | 189/363 [00:11<00:04, 39.43it/s] Loading 0: 53%|█████▎ | 193/363 [00:11<00:04, 39.07it/s] Loading 0: 54%|█████▍ | 197/363 [00:11<00:04, 36.86it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:05, 27.37it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:05, 27.89it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 31.38it/s] Loading 0: 59%|█████▉ | 215/363 [00:12<00:04, 31.59it/s] Loading 0: 61%|██████ | 220/363 [00:12<00:04, 35.13it/s] Loading 0: 62%|██████▏ | 224/363 [00:12<00:03, 34.75it/s] Loading 0: 63%|██████▎ | 229/363 [00:12<00:03, 36.96it/s] Loading 0: 64%|██████▍ | 233/363 [00:12<00:03, 35.25it/s] Loading 0: 66%|██████▌ | 238/363 [00:12<00:03, 37.06it/s] Loading 0: 67%|██████▋ | 242/363 [00:12<00:03, 35.46it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:03, 37.08it/s] Loading 0: 69%|██████▉ | 251/363 [00:13<00:03, 35.71it/s] Loading 0: 71%|███████ | 257/363 [00:13<00:02, 39.80it/s] Loading 0: 72%|███████▏ | 262/363 [00:13<00:02, 41.62it/s] Loading 0: 74%|███████▎ | 267/363 [00:13<00:02, 32.40it/s] Loading 0: 75%|███████▌ | 274/363 [00:13<00:02, 39.24it/s] Loading 0: 77%|███████▋ | 279/363 [00:13<00:02, 38.77it/s] Loading 0: 78%|███████▊ | 284/363 [00:14<00:02, 28.96it/s] Loading 0: 79%|███████▉ | 288/363 [00:14<00:02, 30.41it/s] Loading 0: 80%|████████ | 292/363 [00:14<00:02, 31.72it/s] Loading 0: 82%|████████▏ | 296/363 [00:14<00:02, 31.95it/s] Loading 0: 83%|████████▎ | 301/363 [00:14<00:01, 35.00it/s] Loading 0: 84%|████████▍ | 305/363 [00:14<00:01, 34.51it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:01, 36.62it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:01, 34.50it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:01, 36.21it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:01, 34.39it/s] Loading 0: 90%|█████████ | 327/363 [00:15<00:01, 35.68it/s] Loading 0: 91%|█████████ | 331/363 [00:15<00:00, 32.80it/s] Loading 0: 93%|█████████▎| 337/363 [00:15<00:00, 38.76it/s] Loading 0: 94%|█████████▍| 342/363 [00:15<00:00, 39.34it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 40.05it/s] Loading 0: 97%|█████████▋| 352/363 [00:15<00:00, 41.78it/s] Loading 0: 98%|█████████▊| 357/363 [00:16<00:00, 35.44it/s]
Job nitral-ai-captain-eris-45741-v24-mkmlizer completed after 95.13s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v24-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-v24
Waiting for inference service nitral-ai-captain-eris-45741-v24 to be ready
Inference service nitral-ai-captain-eris-45741-v24 ready after 211.2502806186676s
Pipeline stage MKMLDeployer completed in 211.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.298612356185913s
Received healthy response to inference request in 1.5928149223327637s
Received healthy response to inference request in 1.5906717777252197s
Received healthy response to inference request in 1.5546307563781738s
Received healthy response to inference request in 1.6288552284240723s
5 requests
0 failed requests
5th percentile: 1.561838960647583
10th percentile: 1.5690471649169921
20th percentile: 1.5834635734558105
30th percentile: 1.5911004066467285
40th percentile: 1.5919576644897462
50th percentile: 1.5928149223327637
60th percentile: 1.607231044769287
70th percentile: 1.6216471672058106
80th percentile: 1.7628066539764404
90th percentile: 2.0307095050811768
95th percentile: 2.164660930633545
99th percentile: 2.2718220710754395
mean time: 1.7331170082092284
Pipeline stage StressChecker completed in 9.92s
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 0.61s
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 0.69s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v24 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 2576.43s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v24 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v24 status is now torndown due to DeploymentManager action