developer_uid: huohuo12
submission_id: nitral-ai-captain-eris_45741_v22
model_name: nitral-ai-captain-eris_45741_v22
model_group: Nitral-AI/Captain-Eris_V
status: torndown
timestamp: 2025-02-21T03:42:02+00:00
num_battles: 5858
num_wins: 2923
celo_rating: 1268.28
family_friendly_score: 0.5798
family_friendly_standard_error: 0.006980429213164474
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': 0.6030112554539243, 'latency_mean': 1.6582553231716155, 'latency_p50': 1.6480611562728882, 'latency_p90': 1.8240779638290405}, {'batch_size': 3, 'throughput': 1.0861538254649938, 'latency_mean': 2.749004232883453, 'latency_p50': 2.741552472114563, 'latency_p90': 3.03675434589386}, {'batch_size': 5, 'throughput': 1.3126337913539299, 'latency_mean': 3.782482635974884, 'latency_p50': 3.7781838178634644, 'latency_p90': 4.240350699424743}, {'batch_size': 6, 'throughput': 1.3821179637463255, 'latency_mean': 4.32540733218193, 'latency_p50': 4.33310866355896, 'latency_p90': 4.8552170753479}, {'batch_size': 8, 'throughput': 1.441803458282421, 'latency_mean': 5.508367512226105, 'latency_p50': 5.480905771255493, 'latency_p90': 6.227269148826599}, {'batch_size': 10, 'throughput': 1.471461056170363, 'latency_mean': 6.749498897790909, 'latency_p50': 6.739395022392273, 'latency_p90': 7.567341160774231}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nitral-ai-captain-eris_45741_v22
is_internal_developer: False
language_model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-02-20
win_ratio: 0.49897575964493
generation_params: {'temperature': 0.72, 'top_p': 0.87, 'min_p': 0.018, 'top_k': 52, 'presence_penalty': 0.63, 'frequency_penalty': 0.22, '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-v22-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v22-mkmlizer to finish
nitral-ai-captain-eris-45741-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ /___/ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ Version: 0.12.8 ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ belonging to: ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v22-mkmlizer: Downloaded to shared memory in 32.566s
nitral-ai-captain-eris-45741-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpydud89pu, device:0
nitral-ai-captain-eris-45741-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v22-mkmlizer: quantized model in 36.093s
nitral-ai-captain-eris-45741-v22-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 68.660s
nitral-ai-captain-eris-45741-v22-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22
nitral-ai-captain-eris-45741-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22/config.json
nitral-ai-captain-eris-45741-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22/special_tokens_map.json
nitral-ai-captain-eris-45741-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22/tokenizer_config.json
nitral-ai-captain-eris-45741-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22/tokenizer.json
nitral-ai-captain-eris-45741-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v22/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v22-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:14, 3.03s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:50, 1.23it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:07, 2.76it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:20, 4.33it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:39, 8.65it/s] Loading 0: 8%|▊ | 29/363 [00:06<00:27, 12.12it/s] Loading 0: 9%|▉ | 34/363 [00:06<00:21, 15.34it/s] Loading 0: 11%|█ | 40/363 [00:07<00:18, 17.74it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:15, 20.16it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 25.44it/s] Loading 0: 15%|█▌ | 55/363 [00:07<00:10, 29.61it/s] Loading 0: 17%|█▋ | 60/363 [00:07<00:10, 29.00it/s] Loading 0: 19%|█▊ | 68/363 [00:07<00:07, 37.90it/s] Loading 0: 20%|██ | 73/363 [00:07<00:07, 40.45it/s] Loading 0: 21%|██▏ | 78/363 [00:07<00:07, 36.00it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 44.05it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 40.84it/s] Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 40.78it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 45.86it/s] Loading 0: 30%|███ | 110/363 [00:08<00:05, 43.79it/s] Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 41.60it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:07, 34.08it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:06, 34.32it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 36.40it/s] Loading 0: 37%|███▋ | 134/363 [00:09<00:06, 36.02it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 40.21it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:05, 42.03it/s] Loading 0: 41%|████▏ | 150/363 [00:09<00:06, 34.60it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:04, 42.01it/s] Loading 0: 45%|████▍ | 162/363 [00:10<00:04, 43.11it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 43.33it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:04, 44.13it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:04, 37.63it/s] Loading 0: 51%|█████ | 185/363 [00:10<00:03, 46.07it/s] Loading 0: 53%|█████▎ | 191/363 [00:10<00:03, 44.85it/s] Loading 0: 54%|█████▍ | 196/363 [00:10<00:03, 43.17it/s] Loading 0: 56%|█████▌ | 202/363 [00:11<00:04, 35.19it/s] Loading 0: 57%|█████▋ | 206/363 [00:11<00:04, 35.25it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:03, 38.30it/s] Loading 0: 60%|█████▉ | 216/363 [00:11<00:03, 39.76it/s] Loading 0: 61%|██████ | 221/363 [00:11<00:03, 41.77it/s] Loading 0: 63%|██████▎ | 227/363 [00:11<00:03, 41.12it/s] Loading 0: 64%|██████▍ | 232/363 [00:11<00:03, 40.67it/s] Loading 0: 66%|██████▌ | 238/363 [00:11<00:02, 44.15it/s] Loading 0: 67%|██████▋ | 243/363 [00:11<00:02, 43.08it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 43.14it/s] Loading 0: 70%|██████▉ | 254/363 [00:12<00:02, 42.07it/s] Loading 0: 71%|███████▏ | 259/363 [00:12<00:02, 41.66it/s] Loading 0: 73%|███████▎ | 266/363 [00:12<00:02, 46.78it/s] Loading 0: 75%|███████▍ | 272/363 [00:12<00:02, 45.38it/s] Loading 0: 76%|███████▋ | 277/363 [00:12<00:01, 44.19it/s] Loading 0: 78%|███████▊ | 283/363 [00:13<00:02, 34.94it/s] Loading 0: 79%|███████▉ | 287/363 [00:13<00:02, 35.12it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 39.17it/s] Loading 0: 82%|████████▏ | 298/363 [00:13<00:01, 40.67it/s] Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 35.74it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 44.26it/s] Loading 0: 87%|████████▋ | 317/363 [00:13<00:01, 43.24it/s] Loading 0: 89%|████████▊ | 322/363 [00:13<00:00, 41.13it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 46.20it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:00, 44.60it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 43.64it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 47.44it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 46.40it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 46.09it/s] Loading 0: 99%|█████████▉| 361/363 [00:14<00:00, 46.86it/s]
Job nitral-ai-captain-eris-45741-v22-mkmlizer completed after 93.9s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v22-mkmlizer
Pipeline stage MKMLizer completed in 94.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nitral-ai-captain-eris-45741-v22
Waiting for inference service nitral-ai-captain-eris-45741-v22 to be ready
Inference service nitral-ai-captain-eris-45741-v22 ready after 211.032954454422s
Pipeline stage MKMLDeployer completed in 211.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2988343238830566s
Received healthy response to inference request in 1.5945191383361816s
Received healthy response to inference request in 1.626739501953125s
Received healthy response to inference request in 1.7547883987426758s
Received healthy response to inference request in 1.5785553455352783s
5 requests
0 failed requests
5th percentile: 1.581748104095459
10th percentile: 1.5849408626556396
20th percentile: 1.5913263797760009
30th percentile: 1.6009632110595704
40th percentile: 1.6138513565063477
50th percentile: 1.626739501953125
60th percentile: 1.6779590606689454
70th percentile: 1.7291786193847656
80th percentile: 1.8635975837707521
90th percentile: 2.0812159538269044
95th percentile: 2.1900251388549803
99th percentile: 2.2770724868774415
mean time: 1.7706873416900635
Pipeline stage StressChecker completed in 10.03s
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 0.66s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v22 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nitral-ai-captain-eris-45741-v22-profiler
Waiting for inference service nitral-ai-captain-eris-45741-v22-profiler to be ready
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 2450.59s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v22 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v22 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1