developer_uid: huohuo12
submission_id: nitral-ai-captain-eris_45741_v17
model_name: nitral-ai-captain-eris_45741_v17
model_group: Nitral-AI/Captain-Eris_V
status: torndown
timestamp: 2025-02-20T10:09:13+00:00
num_battles: 6884
num_wins: 3464
celo_rating: 1264.82
family_friendly_score: 0.5774
family_friendly_standard_error: 0.006985831947592212
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': 0.5993262703512516, 'latency_mean': 1.6684592258930206, 'latency_p50': 1.668186068534851, 'latency_p90': 1.8341211080551147}, {'batch_size': 3, 'throughput': 1.091409471110066, 'latency_mean': 2.7337188231945038, 'latency_p50': 2.7409414052963257, 'latency_p90': 3.0010857820510863}, {'batch_size': 5, 'throughput': 1.3208727126775892, 'latency_mean': 3.7677617752552033, 'latency_p50': 3.766993284225464, 'latency_p90': 4.2536756038665775}, {'batch_size': 6, 'throughput': 1.3882292671339878, 'latency_mean': 4.296394672393799, 'latency_p50': 4.2887126207351685, 'latency_p90': 4.839301872253418}, {'batch_size': 8, 'throughput': 1.43507019578112, 'latency_mean': 5.53707483291626, 'latency_p50': 5.580620169639587, 'latency_p90': 6.272639513015747}, {'batch_size': 10, 'throughput': 1.485336576387696, 'latency_mean': 6.6818706107139585, 'latency_p50': 6.610795497894287, 'latency_p90': 7.728790354728699}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nitral-ai-captain-eris_45741_v17
is_internal_developer: False
language_model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-02-20
win_ratio: 0.5031958163858222
generation_params: {'temperature': 1.06, 'top_p': 0.77, 'min_p': 0.02, 'top_k': 58, 'presence_penalty': 0.55, 'frequency_penalty': 0.35, '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-v17-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v17-mkmlizer to finish
nitral-ai-captain-eris-45741-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ /___/ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ Version: 0.12.8 ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ belonging to: ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v17-mkmlizer: Downloaded to shared memory in 33.681s
nitral-ai-captain-eris-45741-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6spidsi3, device:0
nitral-ai-captain-eris-45741-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v17-mkmlizer: quantized model in 38.780s
nitral-ai-captain-eris-45741-v17-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 72.462s
nitral-ai-captain-eris-45741-v17-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17
nitral-ai-captain-eris-45741-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17/config.json
nitral-ai-captain-eris-45741-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17/special_tokens_map.json
nitral-ai-captain-eris-45741-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17/tokenizer_config.json
nitral-ai-captain-eris-45741-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17/tokenizer.json
nitral-ai-captain-eris-45741-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v17/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v17-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:30, 3.07s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:56, 1.20it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:10, 2.69it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:23, 4.17it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:44, 7.74it/s] Loading 0: 7%|▋ | 26/363 [00:06<00:33, 9.91it/s] Loading 0: 9%|▊ | 31/363 [00:06<00:24, 13.41it/s] Loading 0: 10%|▉ | 35/363 [00:07<00:20, 15.99it/s] Loading 0: 11%|█ | 40/363 [00:07<00:20, 15.87it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 17.22it/s] Loading 0: 13%|█▎ | 47/363 [00:07<00:15, 20.66it/s] Loading 0: 14%|█▍ | 51/363 [00:07<00:14, 22.28it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 27.50it/s] Loading 0: 17%|█▋ | 60/363 [00:08<00:10, 27.89it/s] Loading 0: 18%|█▊ | 67/363 [00:08<00:08, 35.46it/s] Loading 0: 20%|█▉ | 72/363 [00:08<00:08, 35.85it/s] Loading 0: 21%|██ | 76/363 [00:08<00:08, 35.74it/s] Loading 0: 22%|██▏ | 80/363 [00:08<00:08, 33.70it/s] Loading 0: 23%|██▎ | 85/363 [00:08<00:07, 36.06it/s] Loading 0: 25%|██▍ | 89/363 [00:08<00:07, 34.51it/s] Loading 0: 26%|██▌ | 94/363 [00:08<00:07, 36.43it/s] Loading 0: 27%|██▋ | 98/363 [00:09<00:07, 34.53it/s] Loading 0: 28%|██▊ | 103/363 [00:09<00:07, 36.28it/s] Loading 0: 29%|██▉ | 107/363 [00:09<00:07, 33.88it/s] Loading 0: 31%|███ | 111/363 [00:09<00:07, 35.32it/s] Loading 0: 32%|███▏ | 115/363 [00:09<00:07, 32.03it/s] Loading 0: 33%|███▎ | 119/363 [00:09<00:07, 33.45it/s] Loading 0: 34%|███▍ | 123/363 [00:09<00:10, 22.13it/s] Loading 0: 35%|███▌ | 128/363 [00:10<00:08, 26.56it/s] Loading 0: 36%|███▋ | 132/363 [00:10<00:08, 26.00it/s] Loading 0: 38%|███▊ | 137/363 [00:10<00:07, 30.62it/s] Loading 0: 39%|███▉ | 141/363 [00:10<00:07, 29.25it/s] Loading 0: 40%|████ | 146/363 [00:10<00:06, 33.41it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:07, 30.38it/s] Loading 0: 43%|████▎ | 155/363 [00:10<00:06, 34.10it/s] Loading 0: 44%|████▍ | 159/363 [00:11<00:06, 31.73it/s] Loading 0: 45%|████▌ | 164/363 [00:11<00:05, 35.68it/s] Loading 0: 46%|████▋ | 168/363 [00:11<00:05, 32.65it/s] Loading 0: 48%|████▊ | 173/363 [00:11<00:05, 36.55it/s] Loading 0: 49%|████▉ | 177/363 [00:11<00:05, 33.35it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:05, 36.17it/s] Loading 0: 51%|█████ | 186/363 [00:11<00:05, 32.86it/s] Loading 0: 53%|█████▎ | 193/363 [00:11<00:04, 39.47it/s] Loading 0: 55%|█████▍ | 198/363 [00:12<00:04, 38.84it/s] Loading 0: 56%|█████▌ | 202/363 [00:12<00:06, 26.46it/s] Loading 0: 57%|█████▋ | 206/363 [00:12<00:05, 27.68it/s] Loading 0: 58%|█████▊ | 211/363 [00:12<00:04, 30.50it/s] Loading 0: 59%|█████▉ | 215/363 [00:12<00:04, 30.25it/s] Loading 0: 61%|██████ | 220/363 [00:12<00:04, 32.81it/s] Loading 0: 62%|██████▏ | 224/363 [00:13<00:04, 32.42it/s] Loading 0: 63%|██████▎ | 228/363 [00:13<00:04, 33.74it/s] Loading 0: 64%|██████▍ | 232/363 [00:13<00:04, 31.03it/s] Loading 0: 65%|██████▌ | 236/363 [00:13<00:03, 32.70it/s] Loading 0: 66%|██████▌ | 240/363 [00:13<00:04, 30.10it/s] Loading 0: 67%|██████▋ | 245/363 [00:13<00:03, 33.02it/s] Loading 0: 69%|██████▊ | 249/363 [00:13<00:03, 30.83it/s] Loading 0: 71%|███████ | 256/363 [00:13<00:02, 37.73it/s] Loading 0: 72%|███████▏ | 260/363 [00:14<00:02, 35.77it/s] Loading 0: 73%|███████▎ | 264/363 [00:14<00:02, 36.38it/s] Loading 0: 74%|███████▍ | 268/363 [00:14<00:02, 33.29it/s] Loading 0: 75%|███████▌ | 274/363 [00:14<00:02, 37.13it/s] Loading 0: 77%|███████▋ | 278/363 [00:14<00:02, 35.49it/s] Loading 0: 78%|███████▊ | 283/363 [00:14<00:02, 26.91it/s] Loading 0: 79%|███████▉ | 287/363 [00:14<00:02, 27.89it/s] Loading 0: 80%|████████ | 292/363 [00:15<00:02, 30.84it/s] Loading 0: 82%|████████▏ | 296/363 [00:15<00:02, 30.96it/s] Loading 0: 83%|████████▎ | 301/363 [00:15<00:01, 33.41it/s] Loading 0: 84%|████████▍ | 305/363 [00:15<00:01, 32.54it/s] Loading 0: 85%|████████▌ | 310/363 [00:15<00:01, 34.83it/s] Loading 0: 87%|████████▋ | 314/363 [00:15<00:01, 34.28it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:01, 36.49it/s] Loading 0: 89%|████████▉ | 323/363 [00:15<00:01, 34.93it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:00, 36.80it/s] Loading 0: 91%|█████████▏| 332/363 [00:16<00:00, 35.28it/s] Loading 0: 93%|█████████▎| 337/363 [00:16<00:00, 36.78it/s] Loading 0: 94%|█████████▍| 341/363 [00:16<00:00, 34.46it/s] Loading 0: 95%|█████████▌| 345/363 [00:16<00:00, 35.57it/s] Loading 0: 96%|█████████▌| 349/363 [00:16<00:00, 32.73it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 36.96it/s] Loading 0: 99%|█████████▉| 359/363 [00:17<00:00, 34.81it/s]
Job nitral-ai-captain-eris-45741-v17-mkmlizer completed after 94.28s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v17-mkmlizer
Pipeline stage MKMLizer completed in 94.73s
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 nitral-ai-captain-eris-45741-v17
Waiting for inference service nitral-ai-captain-eris-45741-v17 to be ready
Inference service nitral-ai-captain-eris-45741-v17 ready after 200.6561300754547s
Pipeline stage MKMLDeployer completed in 201.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3886191844940186s
Received healthy response to inference request in 1.6173090934753418s
Received healthy response to inference request in 2.0888891220092773s
Received healthy response to inference request in 1.5312612056732178s
Received healthy response to inference request in 1.5755808353424072s
5 requests
0 failed requests
5th percentile: 1.5401251316070557
10th percentile: 1.5489890575408936
20th percentile: 1.5667169094085693
30th percentile: 1.5839264869689942
40th percentile: 1.6006177902221679
50th percentile: 1.6173090934753418
60th percentile: 1.805941104888916
70th percentile: 1.9945731163024902
80th percentile: 2.1488351345062258
90th percentile: 2.268727159500122
95th percentile: 2.32867317199707
99th percentile: 2.376629981994629
mean time: 1.8403318881988526
Pipeline stage StressChecker completed in 10.54s
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 0.64s
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 0.78s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v17 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 2730.28s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v17 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v17 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1