developer_uid: huohuo12
submission_id: nitral-ai-captain-eris_45741_v15
model_name: nitral-ai-captain-eris_45741_v15
model_group: Nitral-AI/Captain-Eris_V
status: torndown
timestamp: 2025-02-20T09:38:34+00:00
num_battles: 6060
num_wins: 3102
celo_rating: 1259.19
family_friendly_score: 0.5860000000000001
family_friendly_standard_error: 0.006965687331484238
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': 0.5990523170772507, 'latency_mean': 1.6692290568351746, 'latency_p50': 1.662086844444275, 'latency_p90': 1.8271326303482056}, {'batch_size': 3, 'throughput': 1.0959774450811022, 'latency_mean': 2.7282522201538084, 'latency_p50': 2.7227283716201782, 'latency_p90': 3.0211861610412596}, {'batch_size': 5, 'throughput': 1.3196248158861168, 'latency_mean': 3.773833514451981, 'latency_p50': 3.7924588918685913, 'latency_p90': 4.176726722717285}, {'batch_size': 6, 'throughput': 1.390265806831579, 'latency_mean': 4.2937866246700285, 'latency_p50': 4.298019528388977, 'latency_p90': 4.802512764930725}, {'batch_size': 8, 'throughput': 1.460518797350501, 'latency_mean': 5.440803309679032, 'latency_p50': 5.466763019561768, 'latency_p90': 6.127865982055664}, {'batch_size': 10, 'throughput': 1.4776123742990543, 'latency_mean': 6.705661107301712, 'latency_p50': 6.669230222702026, 'latency_p90': 7.545767521858215}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nitral-ai-captain-eris_45741_v15
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: 0.5118811881188119
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.015, 'top_k': 60, 'presence_penalty': 0.5, 'frequency_penalty': 0.2, '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-v15-mkmlizer
Waiting for job on nitral-ai-captain-eris-45741-v15-mkmlizer to finish
nitral-ai-captain-eris-45741-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ /___/ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ Version: 0.12.8 ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ belonging to: ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ║ ║
nitral-ai-captain-eris-45741-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-eris-45741-v15-mkmlizer: Downloaded to shared memory in 32.605s
nitral-ai-captain-eris-45741-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxnd_23ps, device:0
nitral-ai-captain-eris-45741-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-eris-45741-v15-mkmlizer: quantized model in 39.419s
nitral-ai-captain-eris-45741-v15-mkmlizer: Processed model Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 in 72.024s
nitral-ai-captain-eris-45741-v15-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-eris-45741-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-eris-45741-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15
nitral-ai-captain-eris-45741-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15/config.json
nitral-ai-captain-eris-45741-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15/special_tokens_map.json
nitral-ai-captain-eris-45741-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15/tokenizer_config.json
nitral-ai-captain-eris-45741-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15/tokenizer.json
nitral-ai-captain-eris-45741-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-eris-45741-v15/flywheel_model.0.safetensors
nitral-ai-captain-eris-45741-v15-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:40, 3.11s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:59, 1.19it/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%|▌ | 21/363 [00:06<00:47, 7.21it/s] Loading 0: 7%|▋ | 25/363 [00:06<00:36, 9.24it/s] Loading 0: 8%|▊ | 29/363 [00:07<00:27, 12.02it/s] Loading 0: 9%|▉ | 33/363 [00:07<00:23, 14.27it/s] Loading 0: 10%|█ | 38/363 [00:07<00:17, 18.94it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:20, 15.69it/s] Loading 0: 13%|█▎ | 47/363 [00:07<00:15, 20.25it/s] Loading 0: 14%|█▍ | 51/363 [00:07<00:14, 21.49it/s] Loading 0: 15%|█▌ | 56/363 [00:08<00:11, 26.15it/s] Loading 0: 17%|█▋ | 60/363 [00:08<00:11, 25.87it/s] Loading 0: 18%|█▊ | 65/363 [00:08<00:09, 30.28it/s] Loading 0: 19%|█▉ | 69/363 [00:08<00:10, 28.96it/s] Loading 0: 20%|██ | 74/363 [00:08<00:08, 32.98it/s] Loading 0: 21%|██▏ | 78/363 [00:08<00:09, 30.43it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:08, 34.53it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 32.25it/s] Loading 0: 25%|██▌ | 92/363 [00:09<00:07, 36.22it/s] Loading 0: 26%|██▋ | 96/363 [00:09<00:08, 32.70it/s] Loading 0: 28%|██▊ | 101/363 [00:09<00:07, 35.80it/s] Loading 0: 29%|██▉ | 105/363 [00:09<00:07, 32.76it/s] Loading 0: 30%|███ | 110/363 [00:09<00:06, 36.42it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:07, 32.69it/s] Loading 0: 33%|███▎ | 119/363 [00:09<00:06, 36.33it/s] Loading 0: 34%|███▍ | 123/363 [00:10<00:10, 23.85it/s] Loading 0: 35%|███▌ | 128/363 [00:10<00:08, 28.43it/s] Loading 0: 36%|███▋ | 132/363 [00:10<00:08, 27.46it/s] Loading 0: 38%|███▊ | 137/363 [00:10<00:07, 31.78it/s] Loading 0: 39%|███▉ | 141/363 [00:10<00:07, 29.65it/s] Loading 0: 40%|████ | 146/363 [00:10<00:06, 33.44it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:07, 30.19it/s] Loading 0: 43%|████▎ | 155/363 [00:11<00:06, 34.46it/s] Loading 0: 44%|████▍ | 159/363 [00:11<00:06, 31.16it/s] Loading 0: 45%|████▌ | 164/363 [00:11<00:05, 34.94it/s] Loading 0: 46%|████▋ | 168/363 [00:11<00:06, 31.47it/s] Loading 0: 48%|████▊ | 173/363 [00:11<00:05, 35.69it/s] Loading 0: 49%|████▉ | 177/363 [00:11<00:05, 32.79it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:04, 36.36it/s] Loading 0: 51%|█████ | 186/363 [00:12<00:05, 32.92it/s] Loading 0: 53%|█████▎ | 191/363 [00:12<00:04, 37.03it/s] Loading 0: 54%|█████▎ | 195/363 [00:12<00:05, 33.36it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:04, 36.35it/s] Loading 0: 56%|█████▌ | 204/363 [00:12<00:07, 22.69it/s] Loading 0: 58%|█████▊ | 209/363 [00:12<00:05, 26.93it/s] Loading 0: 59%|█████▊ | 213/363 [00:13<00:05, 26.59it/s] Loading 0: 60%|██████ | 218/363 [00:13<00:04, 30.99it/s] Loading 0: 61%|██████ | 222/363 [00:13<00:04, 29.48it/s] Loading 0: 63%|██████▎ | 227/363 [00:13<00:04, 32.97it/s] Loading 0: 64%|██████▎ | 231/363 [00:13<00:04, 31.37it/s] Loading 0: 65%|██████▌ | 236/363 [00:13<00:03, 35.44it/s] Loading 0: 66%|██████▌ | 240/363 [00:13<00:03, 31.70it/s] Loading 0: 67%|██████▋ | 245/363 [00:13<00:03, 34.94it/s] Loading 0: 69%|██████▊ | 249/363 [00:14<00:03, 31.86it/s] Loading 0: 70%|██████▉ | 254/363 [00:14<00:03, 35.91it/s] Loading 0: 71%|███████ | 258/363 [00:14<00:03, 32.15it/s] Loading 0: 72%|███████▏ | 263/363 [00:14<00:02, 35.93it/s] Loading 0: 74%|███████▎ | 267/363 [00:14<00:02, 32.00it/s] Loading 0: 75%|███████▍ | 272/363 [00:14<00:02, 35.74it/s] Loading 0: 76%|███████▌ | 276/363 [00:14<00:02, 32.04it/s] Loading 0: 77%|███████▋ | 281/363 [00:14<00:02, 36.07it/s] Loading 0: 79%|███████▊ | 285/363 [00:15<00:03, 23.25it/s] Loading 0: 80%|███████▉ | 290/363 [00:15<00:02, 27.73it/s] Loading 0: 81%|████████ | 294/363 [00:15<00:02, 27.05it/s] Loading 0: 82%|████████▏ | 299/363 [00:15<00:02, 31.24it/s] Loading 0: 83%|████████▎ | 303/363 [00:15<00:02, 28.94it/s] Loading 0: 85%|████████▍ | 308/363 [00:15<00:01, 33.11it/s] Loading 0: 86%|████████▌ | 312/363 [00:16<00:01, 30.51it/s] Loading 0: 87%|████████▋ | 317/363 [00:16<00:01, 33.90it/s] Loading 0: 88%|████████▊ | 321/363 [00:16<00:01, 30.65it/s] Loading 0: 90%|████████▉ | 326/363 [00:16<00:01, 34.60it/s] Loading 0: 91%|█████████ | 330/363 [00:16<00:01, 31.61it/s] Loading 0: 92%|█████████▏| 335/363 [00:16<00:00, 35.26it/s] Loading 0: 93%|█████████▎| 339/363 [00:16<00:00, 32.08it/s] Loading 0: 95%|█████████▍| 344/363 [00:17<00:00, 35.56it/s] Loading 0: 96%|█████████▌| 348/363 [00:17<00:00, 31.90it/s] Loading 0: 97%|█████████▋| 353/363 [00:17<00:00, 35.29it/s] Loading 0: 98%|█████████▊| 357/363 [00:17<00:00, 31.88it/s] Loading 0: 100%|█████████▉| 362/363 [00:17<00:00, 35.52it/s]
Job nitral-ai-captain-eris-45741-v15-mkmlizer completed after 93.89s with status: succeeded
Stopping job with name nitral-ai-captain-eris-45741-v15-mkmlizer
Pipeline stage MKMLizer completed in 94.38s
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-v15
Waiting for inference service nitral-ai-captain-eris-45741-v15 to be ready
Inference service nitral-ai-captain-eris-45741-v15 ready after 250.83923602104187s
Pipeline stage MKMLDeployer completed in 251.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3589439392089844s
Received healthy response to inference request in 1.8404338359832764s
Received healthy response to inference request in 1.5714266300201416s
Received healthy response to inference request in 1.5720939636230469s
Received healthy response to inference request in 1.5090765953063965s
5 requests
0 failed requests
5th percentile: 1.5215466022491455
10th percentile: 1.5340166091918945
20th percentile: 1.5589566230773926
30th percentile: 1.5715600967407226
40th percentile: 1.5718270301818849
50th percentile: 1.5720939636230469
60th percentile: 1.6794299125671386
70th percentile: 1.7867658615112305
80th percentile: 1.9441358566284181
90th percentile: 2.1515398979187013
95th percentile: 2.2552419185638426
99th percentile: 2.338203535079956
mean time: 1.770394992828369
Pipeline stage StressChecker completed in 10.10s
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 0.76s
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 0.64s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v15 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nitral-ai-captain-eris-45741-v15-profiler
Waiting for inference service nitral-ai-captain-eris-45741-v15-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 2685.86s
Shutdown handler de-registered
nitral-ai-captain-eris_45741_v15 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-captain-eris_45741_v15 status is now torndown due to DeploymentManager action