nitral-ai-captain-bmo-12b

developer_uid: azuruce

submission_id: nitral-ai-captain-bmo-12b_v11

model_name: nitral-ai-captain-bmo-12b_v11

model_group: Nitral-AI/Captain_BMO-12

status: inactive

timestamp: 2024-11-13T19:29:06+00:00

num_battles: 7356

num_wins: 4038

celo_rating: 1280.46

family_friendly_score: 0.5696

family_friendly_standard_error: 0.007002225931801972

submission_type: basic

model_repo: Nitral-AI/Captain_BMO-12B

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6319172865340003, 'latency_mean': 1.5824295485019684, 'latency_p50': 1.569555640220642, 'latency_p90': 1.73774254322052}, {'batch_size': 3, 'throughput': 1.2416977528336919, 'latency_mean': 2.4096047925949096, 'latency_p50': 2.4034481048583984, 'latency_p90': 2.623161554336548}, {'batch_size': 5, 'throughput': 1.5594360461054488, 'latency_mean': 3.196442724466324, 'latency_p50': 3.1758267879486084, 'latency_p90': 3.5912633419036863}, {'batch_size': 6, 'throughput': 1.6593369529985353, 'latency_mean': 3.5920602655410767, 'latency_p50': 3.5829551219940186, 'latency_p90': 4.129693555831909}, {'batch_size': 8, 'throughput': 1.813643580144147, 'latency_mean': 4.388346382379532, 'latency_p50': 4.363519072532654, 'latency_p90': 4.978973722457885}, {'batch_size': 10, 'throughput': 1.8951296876226236, 'latency_mean': 5.228137427568436, 'latency_p50': 5.198572754859924, 'latency_p90': 6.009816026687622}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-captain-bmo-12b_v11

is_internal_developer: True

language_model: Nitral-AI/Captain_BMO-12B

model_size: 13B

ranking_group: single

throughput_3p7s: 1.69

us_pacific_date: 2024-11-13

win_ratio: 0.5489396411092985

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-bmo-12b-v11-mkmlizer
Waiting for job on nitral-ai-captain-bmo-12b-v11-mkmlizer to finish
nitral-ai-captain-bmo-12b-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║     _____            __           __                                ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║       /___/                                                         ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  Version: 0.11.12                                                   ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-bmo-12b-v11-mkmlizer: Downloaded to shared memory in 80.938s
nitral-ai-captain-bmo-12b-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmowo7hr6, device:0
nitral-ai-captain-bmo-12b-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-bmo-12b-v11-mkmlizer: quantized model in 36.227s
nitral-ai-captain-bmo-12b-v11-mkmlizer: Processed model Nitral-AI/Captain_BMO-12B in 117.165s
nitral-ai-captain-bmo-12b-v11-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-bmo-12b-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-bmo-12b-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11
nitral-ai-captain-bmo-12b-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11/config.json
nitral-ai-captain-bmo-12b-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11/special_tokens_map.json
nitral-ai-captain-bmo-12b-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11/tokenizer_config.json
nitral-ai-captain-bmo-12b-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11/tokenizer.json
nitral-ai-captain-bmo-12b-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v11/flywheel_model.0.safetensors
nitral-ai-captain-bmo-12b-v11-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:23,  3.06s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:53,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.34it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.87it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.96it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.34it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.45it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.18it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.14it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.89it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.35it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 37.01it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 37.77it/s]
Loading 0:  22%|██▏       | 79/363 [00:08<00:07, 38.38it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 44.02it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 44.55it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 36.70it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 44.05it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 43.21it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 44.00it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 43.11it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:07, 29.95it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 35.36it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 37.36it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 39.34it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 40.96it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:06, 35.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 43.32it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 43.46it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 43.49it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 42.05it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 40.48it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 44.91it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 45.04it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.36it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:03, 43.50it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 30.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 36.02it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 37.45it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 39.32it/s]
Loading 0:  62%|██████▏   | 226/363 [00:11<00:03, 41.40it/s]
Loading 0:  64%|██████▎   | 231/363 [00:11<00:03, 35.56it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 43.13it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 43.14it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 43.95it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 45.42it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 38.62it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 43.79it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 42.62it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 42.70it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 41.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.08it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.86it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 35.83it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 36.26it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 38.94it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 33.10it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 39.55it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 39.64it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 40.40it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 41.92it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 35.40it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 42.73it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 43.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 43.77it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 42.82it/s]
                                                            
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
Job nitral-ai-captain-bmo-12b-v11-mkmlizer completed after 145.77s with status: succeeded
Stopping job with name nitral-ai-captain-bmo-12b-v11-mkmlizer
Pipeline stage MKMLizer completed in 146.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nitral-ai-captain-bmo-12b-v11
Waiting for inference service nitral-ai-captain-bmo-12b-v11 to be ready
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service nitral-ai-captain-bmo-12b-v11 ready after 190.7214479446411s
Pipeline stage MKMLDeployer completed in 191.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9137909412384033s
Received healthy response to inference request in 1.3992772102355957s
Received healthy response to inference request in 2.030949115753174s
Received healthy response to inference request in 2.0156402587890625s
Received healthy response to inference request in 1.3454320430755615s
5 requests
0 failed requests
5th percentile: 1.3562010765075683
10th percentile: 1.3669701099395752
20th percentile: 1.388508176803589
30th percentile: 1.5021799564361573
40th percentile: 1.7079854488372803
50th percentile: 1.9137909412384033
60th percentile: 1.954530668258667
70th percentile: 1.9952703952789306
80th percentile: 2.0187020301818848
90th percentile: 2.0248255729675293
95th percentile: 2.0278873443603516
99th percentile: 2.0303367614746093
mean time: 1.7410179138183595
Pipeline stage StressChecker completed in 10.25s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.88s
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 2.69s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v11 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 2326.53s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v11 status is now inactive due to auto deactivation removed underperforming models