nitral-ai-captain-bmo-12b

developer_uid: jxlu90

submission_id: nitral-ai-captain-bmo-12b_v18

model_name: nitral-ai-captain-bmo-12b_v18

model_group: Nitral-AI/Captain_BMO-12

status: inactive

timestamp: 2024-12-17T23:33:46+00:00

num_battles: 10003

num_wins: 5355

celo_rating: 1288.76

family_friendly_score: 0.5786

family_friendly_standard_error: 0.006983151723971061

submission_type: basic

model_repo: Nitral-AI/Captain_BMO-12B

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.4941286025605236, 'latency_mean': 2.023703225851059, 'latency_p50': 2.0272634029388428, 'latency_p90': 2.210884380340576}, {'batch_size': 2, 'throughput': 0.6885588368856768, 'latency_mean': 2.9029036271572113, 'latency_p50': 2.896833300590515, 'latency_p90': 3.18887403011322}, {'batch_size': 3, 'throughput': 0.7934470488434551, 'latency_mean': 3.775729730129242, 'latency_p50': 3.795858383178711, 'latency_p90': 4.073863363265991}, {'batch_size': 4, 'throughput': 0.8650218094212302, 'latency_mean': 4.611509108543396, 'latency_p50': 4.610133767127991, 'latency_p90': 5.144296145439148}, {'batch_size': 5, 'throughput': 0.9014630027990912, 'latency_mean': 5.529783420562744, 'latency_p50': 5.576095342636108, 'latency_p90': 6.104267311096192}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-captain-bmo-12b_v18

is_internal_developer: True

language_model: Nitral-AI/Captain_BMO-12B

model_size: 13B

ranking_group: single

throughput_3p7s: 0.79

us_pacific_date: 2024-12-17

win_ratio: 0.5353393981805459

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': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '{memory}\n####\n', '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-v18-mkmlizer
Waiting for job on nitral-ai-captain-bmo-12b-v18-mkmlizer to finish
nitral-ai-captain-bmo-12b-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║     _____            __           __                                ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║       /___/                                                         ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  Version: 0.11.12                                                   ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
nitral-ai-captain-bmo-12b-v18-mkmlizer: Downloaded to shared memory in 49.567s
nitral-ai-captain-bmo-12b-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_rkxdbsm, device:0
nitral-ai-captain-bmo-12b-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
nitral-ai-captain-bmo-12b-v18-mkmlizer: quantized model in 37.252s
Connection pool is full, discarding connection: %s. Connection pool size: %s
nitral-ai-captain-bmo-12b-v18-mkmlizer: Processed model Nitral-AI/Captain_BMO-12B in 86.820s
Retrying (%r) after connection broken by '%r': %s
nitral-ai-captain-bmo-12b-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-bmo-12b-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18
nitral-ai-captain-bmo-12b-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18/special_tokens_map.json
nitral-ai-captain-bmo-12b-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18/config.json
nitral-ai-captain-bmo-12b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18/tokenizer_config.json
nitral-ai-captain-bmo-12b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18/tokenizer.json
nitral-ai-captain-bmo-12b-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v18/flywheel_model.0.safetensors
nitral-ai-captain-bmo-12b-v18-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:52,  3.14s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:01,  1.18it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:47,  3.26it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:06,  5.18it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:44,  7.66it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.16it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.34it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:20, 15.66it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:17, 18.10it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 23.42it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.98it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 27.97it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 36.59it/s]
Loading 0:  20%|██        | 74/363 [00:08<00:07, 36.55it/s]
Loading 0:  22%|██▏       | 79/363 [00:08<00:07, 37.17it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 42.76it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 41.97it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 40.02it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 44.75it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:05, 45.78it/s]
Loading 0:  31%|███▏      | 114/363 [00:09<00:06, 38.21it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:07, 32.16it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 32.39it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 35.58it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 34.57it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 38.65it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 41.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.17it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 41.78it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 42.31it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 42.10it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 43.94it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:04, 37.66it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 44.55it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 42.93it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 42.75it/s]
Loading 0:  55%|█████▍    | 199/363 [00:11<00:03, 43.10it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 25.12it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 33.33it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:04, 35.47it/s]
Loading 0:  61%|██████▏   | 223/363 [00:12<00:04, 34.97it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 39.65it/s]
Loading 0:  64%|██████▍   | 234/363 [00:12<00:03, 41.26it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 41.77it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 41.05it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.75it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 43.91it/s]
Loading 0:  72%|███████▏  | 261/363 [00:12<00:02, 43.62it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 44.04it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 45.00it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 33.39it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 29.20it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 30.01it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.78it/s]
Loading 0:  82%|████████▏ | 296/363 [00:13<00:01, 34.59it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 38.86it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:01, 40.98it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 35.00it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 43.24it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 44.68it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 36.70it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 43.93it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 43.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 42.90it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 44.19it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 37.41it/s]
                                                            
Job nitral-ai-captain-bmo-12b-v18-mkmlizer completed after 114.93s with status: succeeded
Stopping job with name nitral-ai-captain-bmo-12b-v18-mkmlizer
Pipeline stage MKMLizer completed in 115.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nitral-ai-captain-bmo-12b-v18
Waiting for inference service nitral-ai-captain-bmo-12b-v18 to be ready
Inference service nitral-ai-captain-bmo-12b-v18 ready after 241.24226140975952s
Pipeline stage MKMLDeployer completed in 241.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.126753807067871s
Received healthy response to inference request in 1.6038587093353271s
Received healthy response to inference request in 1.919250726699829s
Received healthy response to inference request in 1.5324914455413818s
Received healthy response to inference request in 1.4681758880615234s
5 requests
0 failed requests
5th percentile: 1.481038999557495
10th percentile: 1.4939021110534667
20th percentile: 1.5196283340454102
30th percentile: 1.546764898300171
40th percentile: 1.575311803817749
50th percentile: 1.6038587093353271
60th percentile: 1.730015516281128
70th percentile: 1.8561723232269287
80th percentile: 1.9607513427734375
90th percentile: 2.043752574920654
95th percentile: 2.085253190994263
99th percentile: 2.1184536838531494
mean time: 1.7301061153411865
Pipeline stage StressChecker completed in 10.26s
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 2.23s
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 2.13s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v18 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 3720.43s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v18 status is now inactive due to auto deactivation removed underperforming models