submission_id: nitral-ai-captain-bmo-12b_v12
developer_uid: Nitral-AI
best_of: 8
celo_rating: 1290.86
display_name: nitral-ai-captain-bmo-12b_v1
family_friendly_score: 0.5728
family_friendly_standard_error: 0.006995715260071696
formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n\n', '\nYou:', '<|im_end|>', '[/INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Nitral-AI/Captain_BMO-12B
latencies: [{'batch_size': 1, 'throughput': 0.6246212042467163, 'latency_mean': 1.6009024167060852, 'latency_p50': 1.5996397733688354, 'latency_p90': 1.772442674636841}, {'batch_size': 3, 'throughput': 1.1503023814426157, 'latency_mean': 2.5985886418819426, 'latency_p50': 2.596657633781433, 'latency_p90': 2.8627175092697144}, {'batch_size': 5, 'throughput': 1.4181320970344746, 'latency_mean': 3.5061698639392853, 'latency_p50': 3.5349313020706177, 'latency_p90': 3.9154308319091795}, {'batch_size': 6, 'throughput': 1.4793364253973411, 'latency_mean': 4.033589630126953, 'latency_p50': 4.049782156944275, 'latency_p90': 4.48527340888977}, {'batch_size': 8, 'throughput': 1.5706902550017672, 'latency_mean': 5.054101654291153, 'latency_p50': 5.044592022895813, 'latency_p90': 5.697059273719788}, {'batch_size': 10, 'throughput': 1.6000002960205626, 'latency_mean': 6.194980412721634, 'latency_p50': 6.2111440896987915, 'latency_p90': 6.928126263618469}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Nitral-AI/Captain_BMO-12
model_name: nitral-ai-captain-bmo-12b_v1
model_num_parameters: 12772070400.0
model_repo: Nitral-AI/Captain_BMO-12B
model_size: 13B
num_battles: 12641
num_wins: 7076
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.45
timestamp: 2024-11-15T02:16:31+00:00
us_pacific_date: 2024-11-14
win_ratio: 0.5597658413100229
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-bmo-12b-v12-mkmlizer
Waiting for job on nitral-ai-captain-bmo-12b-v12-mkmlizer to finish
nitral-ai-captain-bmo-12b-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ _____ __ __ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ /___/ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ Version: 0.11.12 ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ https://mk1.ai ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ belonging to: ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ║ ║
nitral-ai-captain-bmo-12b-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
nitral-ai-captain-bmo-12b-v12-mkmlizer: Downloaded to shared memory in 155.995s
nitral-ai-captain-bmo-12b-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi1oeqlnz, device:0
nitral-ai-captain-bmo-12b-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-bmo-12b-v12-mkmlizer: quantized model in 37.694s
nitral-ai-captain-bmo-12b-v12-mkmlizer: Processed model Nitral-AI/Captain_BMO-12B in 193.690s
nitral-ai-captain-bmo-12b-v12-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-bmo-12b-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-bmo-12b-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v12
nitral-ai-captain-bmo-12b-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v12/config.json
nitral-ai-captain-bmo-12b-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v12/special_tokens_map.json
nitral-ai-captain-bmo-12b-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v12/tokenizer_config.json
nitral-ai-captain-bmo-12b-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v12/flywheel_model.0.safetensors
nitral-ai-captain-bmo-12b-v12-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:33, 3.09s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:56, 1.20it/s] Loading 0: 3%|▎ | 11/363 [00:06<02:10, 2.70it/s] Loading 0: 4%|▍ | 15/363 [00:06<01:22, 4.21it/s] Loading 0: 6%|▌ | 22/363 [00:06<00:43, 7.87it/s] Loading 0: 7%|▋ | 27/363 [00:06<00:31, 10.82it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:23, 14.17it/s] Loading 0: 10%|█ | 37/363 [00:07<00:18, 18.09it/s] Loading 0: 12%|█▏ | 42/363 [00:07<00:20, 15.73it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:14, 22.17it/s] Loading 0: 15%|█▍ | 54/363 [00:07<00:12, 25.50it/s] Loading 0: 16%|█▋ | 59/363 [00:07<00:10, 28.58it/s] Loading 0: 18%|█▊ | 64/363 [00:07<00:09, 32.06it/s] Loading 0: 19%|█▉ | 69/363 [00:08<00:09, 30.17it/s] Loading 0: 21%|██ | 76/363 [00:08<00:07, 38.00it/s] Loading 0: 22%|██▏ | 81/363 [00:08<00:07, 38.79it/s] Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 40.23it/s] Loading 0: 25%|██▌ | 91/363 [00:08<00:06, 41.57it/s] Loading 0: 26%|██▋ | 96/363 [00:08<00:07, 34.72it/s] Loading 0: 28%|██▊ | 103/363 [00:08<00:06, 42.01it/s] Loading 0: 30%|██▉ | 108/363 [00:08<00:06, 41.89it/s] Loading 0: 31%|███ | 113/363 [00:09<00:06, 41.64it/s] Loading 0: 33%|███▎ | 118/363 [00:09<00:05, 43.04it/s] Loading 0: 34%|███▍ | 123/363 [00:09<00:09, 24.95it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:07, 31.91it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:06, 33.83it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:06, 35.50it/s] Loading 0: 40%|███▉ | 145/363 [00:10<00:05, 37.03it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:06, 32.08it/s] Loading 0: 43%|████▎ | 157/363 [00:10<00:05, 38.82it/s] Loading 0: 45%|████▍ | 162/363 [00:10<00:05, 39.30it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:04, 39.55it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:04, 41.38it/s] Loading 0: 49%|████▉ | 177/363 [00:10<00:05, 34.78it/s] Loading 0: 51%|█████ | 184/363 [00:11<00:04, 40.81it/s] Loading 0: 52%|█████▏ | 189/363 [00:11<00:04, 41.16it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:04, 40.97it/s] Loading 0: 55%|█████▍ | 199/363 [00:11<00:03, 42.34it/s] Loading 0: 56%|█████▌ | 204/363 [00:11<00:06, 25.60it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 32.71it/s] Loading 0: 60%|█████▉ | 216/363 [00:12<00:04, 34.64it/s] Loading 0: 61%|██████ | 221/363 [00:12<00:03, 36.61it/s] Loading 0: 62%|██████▏ | 226/363 [00:12<00:03, 39.08it/s] Loading 0: 64%|██████▎ | 231/363 [00:12<00:04, 32.68it/s] Loading 0: 66%|██████▌ | 238/363 [00:12<00:03, 38.38it/s] Loading 0: 67%|██████▋ | 243/363 [00:12<00:03, 38.44it/s] Loading 0: 68%|██████▊ | 248/363 [00:12<00:02, 38.99it/s] Loading 0: 70%|██████▉ | 253/363 [00:12<00:02, 40.08it/s] Loading 0: 71%|███████ | 258/363 [00:13<00:03, 32.26it/s] Loading 0: 73%|███████▎ | 265/363 [00:13<00:02, 38.27it/s] Loading 0: 74%|███████▍ | 270/363 [00:13<00:02, 37.85it/s] Loading 0: 76%|███████▌ | 275/363 [00:13<00:02, 38.08it/s] Loading 0: 77%|███████▋ | 279/363 [00:13<00:02, 38.23it/s] Loading 0: 78%|███████▊ | 283/363 [00:14<00:03, 25.97it/s] Loading 0: 79%|███████▉ | 287/363 [00:14<00:02, 27.98it/s] Loading 0: 80%|████████ | 292/363 [00:14<00:02, 32.33it/s] Loading 0: 82%|████████▏ | 296/363 [00:14<00:02, 33.02it/s] Loading 0: 83%|████████▎ | 300/363 [00:14<00:01, 34.66it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:01, 31.80it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:01, 37.50it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:01, 36.91it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:01, 39.15it/s] Loading 0: 89%|████████▉ | 324/363 [00:15<00:00, 39.41it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:00, 39.37it/s] Loading 0: 92%|█████████▏| 334/363 [00:15<00:00, 41.15it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:00, 32.31it/s] Loading 0: 95%|█████████▌| 346/363 [00:15<00:00, 38.55it/s] Loading 0: 97%|█████████▋| 351/363 [00:15<00:00, 38.92it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 38.66it/s] Loading 0: 99%|█████████▉| 361/363 [00:16<00:00, 39.98it/s]
Job nitral-ai-captain-bmo-12b-v12-mkmlizer completed after 227.38s with status: succeeded
Stopping job with name nitral-ai-captain-bmo-12b-v12-mkmlizer
Pipeline stage MKMLizer completed in 227.99s
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-bmo-12b-v12
Waiting for inference service nitral-ai-captain-bmo-12b-v12 to be ready
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service nitral-ai-captain-bmo-12b-v12 ready after 190.77203798294067s
Pipeline stage MKMLDeployer completed in 191.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3061137199401855s
Received healthy response to inference request in 1.8178157806396484s
Received healthy response to inference request in 1.7208285331726074s
Received healthy response to inference request in 1.6905419826507568s
Received healthy response to inference request in 2.0028862953186035s
5 requests
0 failed requests
5th percentile: 1.696599292755127
10th percentile: 1.7026566028594972
20th percentile: 1.7147712230682373
30th percentile: 1.7402259826660156
40th percentile: 1.7790208816528321
50th percentile: 1.8178157806396484
60th percentile: 1.8918439865112304
70th percentile: 1.9658721923828124
80th percentile: 2.06353178024292
90th percentile: 2.184822750091553
95th percentile: 2.2454682350158692
99th percentile: 2.2939846229553225
mean time: 1.9076372623443603
Pipeline stage StressChecker completed in 11.11s
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 2.69s
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 2.33s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v12 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 2672.73s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v12 status is now inactive due to auto deactivation removed underperforming models