developer_uid: huohuo12
submission_id: nitral-ai-captain-eris_45741_v18
model_name: nitral-ai-captain-eris_45741_v18
model_group: Nitral-AI/Captain-Eris_V
status: torndown
timestamp: 2025-02-20T10:10:43+00:00
num_battles: 6906
num_wins: 3431
celo_rating: 1262.4
family_friendly_score: 0.5820000000000001
family_friendly_standard_error: 0.006975327949279518
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': 0.6013047437454856, 'latency_mean': 1.6629879879951477, 'latency_p50': 1.6488654613494873, 'latency_p90': 1.847490906715393}, {'batch_size': 3, 'throughput': 1.0898834406851778, 'latency_mean': 2.7488033628463744, 'latency_p50': 2.7543450593948364, 'latency_p90': 3.0093079090118406}, {'batch_size': 5, 'throughput': 1.3048367581413147, 'latency_mean': 3.8111459958553313, 'latency_p50': 3.83397901058197, 'latency_p90': 4.2957754850387575}, {'batch_size': 6, 'throughput': 1.3736369035790916, 'latency_mean': 4.339456359148025, 'latency_p50': 4.349768161773682, 'latency_p90': 4.773297739028931}, {'batch_size': 8, 'throughput': 1.4392629413272444, 'latency_mean': 5.521288747787476, 'latency_p50': 5.524123311042786, 'latency_p90': 6.3366172313690186}, {'batch_size': 10, 'throughput': 1.4717108706591873, 'latency_mean': 6.758093824386597, 'latency_p50': 6.719660520553589, 'latency_p90': 7.626288414001465}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nitral-ai-captain-eris_45741_v18
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: 0.4968143643208804
generation_params: {'temperature': 0.7, 'top_p': 0.94, 'min_p': 0.03, 'top_k': 56, 'presence_penalty': 0.7, 'frequency_penalty': 0.0, '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-v18-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v18-mkmlizer to finish
nitral-ai-captain-eris-45741-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ /___/ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ Version: 0.12.8 ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ belonging to: ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v18-mkmlizer: Downloaded to shared memory in 32.954s
nitral-ai-captain-eris-45741-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9jmzpkzi, device:0
nitral-ai-captain-eris-45741-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v18-mkmlizer: quantized model in 39.293s
nitral-ai-captain-eris-45741-v18-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 72.248s
nitral-ai-captain-eris-45741-v18-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18
nitral-ai-captain-eris-45741-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18/config.json
nitral-ai-captain-eris-45741-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18/special_tokens_map.json
nitral-ai-captain-eris-45741-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18/tokenizer_config.json
nitral-ai-captain-eris-45741-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18/tokenizer.json
nitral-ai-captain-eris-45741-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v18/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v18-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:35, 3.09s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:58, 1.20it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:11, 2.67it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:24, 4.14it/s] Loading 0: 6%|▌ | 20/363 [00:06<00:51, 6.66it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:38, 8.78it/s] Loading 0: 9%|▊ | 31/363 [00:07<00:23, 14.14it/s] Loading 0: 10%|▉ | 36/363 [00:07<00:18, 17.40it/s] Loading 0: 11%|█ | 40/363 [00:07<00:20, 16.12it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:17, 18.54it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:13, 22.64it/s] Loading 0: 15%|█▍ | 53/363 [00:07<00:12, 24.34it/s] Loading 0: 16%|█▌ | 58/363 [00:07<00:10, 28.25it/s] Loading 0: 17%|█▋ | 62/363 [00:08<00:10, 28.65it/s] Loading 0: 18%|█▊ | 66/363 [00:08<00:09, 30.93it/s] Loading 0: 19%|█▉ | 70/363 [00:08<00:10, 28.79it/s] Loading 0: 20%|██ | 74/363 [00:08<00:09, 30.93it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:09, 29.37it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:08, 33.65it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 31.20it/s] Loading 0: 25%|██▌ | 92/363 [00:08<00:07, 35.01it/s] Loading 0: 26%|██▋ | 96/363 [00:09<00:08, 30.78it/s] Loading 0: 28%|██▊ | 101/363 [00:09<00:07, 34.67it/s] Loading 0: 29%|██▉ | 105/363 [00:09<00:08, 31.81it/s] Loading 0: 30%|███ | 110/363 [00:09<00:07, 35.77it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:07, 31.91it/s] Loading 0: 33%|███▎ | 119/363 [00:09<00:06, 35.59it/s] Loading 0: 34%|███▍ | 123/363 [00:10<00:10, 22.59it/s] Loading 0: 35%|███▌ | 128/363 [00:10<00:08, 26.91it/s] Loading 0: 36%|███▋ | 132/363 [00:10<00:08, 26.62it/s] Loading 0: 38%|███▊ | 137/363 [00:10<00:07, 31.06it/s] Loading 0: 39%|███▉ | 141/363 [00:10<00:07, 29.01it/s] Loading 0: 40%|████ | 146/363 [00:10<00:06, 33.13it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:06, 30.71it/s] Loading 0: 43%|████▎ | 155/363 [00:11<00:06, 34.36it/s] Loading 0: 44%|████▍ | 159/363 [00:11<00:06, 31.20it/s] Loading 0: 45%|████▌ | 164/363 [00:11<00:05, 34.99it/s] Loading 0: 46%|████▋ | 168/363 [00:11<00:06, 31.35it/s] Loading 0: 48%|████▊ | 173/363 [00:11<00:05, 34.84it/s] Loading 0: 49%|████▉ | 177/363 [00:11<00:05, 31.36it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:05, 34.87it/s] Loading 0: 51%|█████ | 186/363 [00:12<00:05, 31.81it/s] Loading 0: 53%|█████▎ | 191/363 [00:12<00:04, 35.58it/s] Loading 0: 54%|█████▎ | 195/363 [00:12<00:05, 32.30it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:04, 35.95it/s] Loading 0: 56%|█████▌ | 204/363 [00:12<00:06, 22.91it/s] Loading 0: 58%|█████▊ | 209/363 [00:12<00:05, 27.48it/s] Loading 0: 59%|█████▊ | 213/363 [00:12<00:05, 26.63it/s] Loading 0: 60%|██████ | 218/363 [00:13<00:04, 30.92it/s] Loading 0: 61%|██████ | 222/363 [00:13<00:04, 29.52it/s] Loading 0: 63%|██████▎ | 229/363 [00:13<00:03, 36.14it/s] Loading 0: 64%|██████▍ | 233/363 [00:13<00:03, 34.29it/s] Loading 0: 65%|██████▌ | 237/363 [00:13<00:03, 35.42it/s] Loading 0: 66%|██████▋ | 241/363 [00:13<00:03, 32.21it/s] Loading 0: 67%|██████▋ | 245/363 [00:13<00:03, 33.72it/s] Loading 0: 69%|██████▊ | 249/363 [00:14<00:03, 30.90it/s] Loading 0: 70%|███████ | 255/363 [00:14<00:02, 37.85it/s] Loading 0: 72%|███████▏ | 260/363 [00:14<00:02, 36.48it/s] Loading 0: 73%|███████▎ | 265/363 [00:14<00:02, 37.74it/s] Loading 0: 74%|███████▍ | 269/363 [00:14<00:02, 35.69it/s] Loading 0: 75%|███████▌ | 274/363 [00:14<00:02, 37.39it/s] Loading 0: 77%|███████▋ | 278/363 [00:14<00:02, 35.97it/s] Loading 0: 78%|███████▊ | 283/363 [00:15<00:02, 27.45it/s] Loading 0: 79%|███████▉ | 287/363 [00:15<00:02, 28.24it/s] Loading 0: 80%|████████ | 292/363 [00:15<00:02, 31.08it/s] Loading 0: 82%|████████▏ | 296/363 [00:15<00:02, 30.46it/s] Loading 0: 83%|████████▎ | 300/363 [00:15<00:01, 32.41it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:01, 30.26it/s] Loading 0: 85%|████████▍ | 308/363 [00:15<00:01, 31.88it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:01, 29.52it/s] Loading 0: 87%|████████▋ | 317/363 [00:16<00:01, 34.19it/s] Loading 0: 88%|████████▊ | 321/363 [00:16<00:01, 30.73it/s] Loading 0: 90%|████████▉ | 326/363 [00:16<00:01, 34.97it/s] Loading 0: 91%|█████████ | 330/363 [00:16<00:01, 32.10it/s] Loading 0: 92%|█████████▏| 335/363 [00:16<00:00, 36.02it/s] Loading 0: 93%|█████████▎| 339/363 [00:16<00:00, 32.07it/s] Loading 0: 95%|█████████▍| 344/363 [00:16<00:00, 35.93it/s] Loading 0: 96%|█████████▌| 348/363 [00:17<00:00, 32.44it/s] Loading 0: 97%|█████████▋| 353/363 [00:17<00:00, 35.88it/s] Loading 0: 98%|█████████▊| 357/363 [00:17<00:00, 32.21it/s] Loading 0: 100%|█████████▉| 362/363 [00:17<00:00, 36.17it/s]
Job nitral-ai-captain-eris-45741-v18-mkmlizer completed after 93.75s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v18-mkmlizer
Pipeline stage MKMLizer completed in 94.21s
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-v18
Waiting for inference service nitral-ai-captain-eris-45741-v18 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v426: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v426-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service nitral-ai-captain-eris-45741-v18 ready after 190.6347372531891s
Pipeline stage MKMLDeployer completed in 191.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5248262882232666s
Received healthy response to inference request in 1.608264684677124s
Received healthy response to inference request in 1.7646896839141846s
Received healthy response to inference request in 1.7413966655731201s
Received healthy response to inference request in 1.5784578323364258s
5 requests
0 failed requests
5th percentile: 1.5844192028045654
10th percentile: 1.590380573272705
20th percentile: 1.6023033142089844
30th percentile: 1.6348910808563233
40th percentile: 1.6881438732147216
50th percentile: 1.7413966655731201
60th percentile: 1.750713872909546
70th percentile: 1.7600310802459718
80th percentile: 1.9167170047760012
90th percentile: 2.220771646499634
95th percentile: 2.37279896736145
99th percentile: 2.4944208240509034
mean time: 1.8435270309448242
Pipeline stage StressChecker completed in 10.62s
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 0.70s
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 0.71s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v18 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nitral-ai-captain-eris-45741-v18-profiler
Waiting for inference service nitral-ai-captain-eris-45741-v18-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 2831.77s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v18 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v18 status is now torndown due to DeploymentManager action