nitral-ai-captain-bmo-12b

developer_uid: zonemercy

submission_id: nitral-ai-captain-bmo-12b_v16

model_name: nitral-ai-captain-bmo-12b_v16

model_group: Nitral-AI/Captain_BMO-12

status: inactive

timestamp: 2024-12-03T10:28:13+00:00

num_battles: 11003

num_wins: 5589

celo_rating: 1267.71

family_friendly_score: 0.5778

family_friendly_standard_error: 0.006984943235273999

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': 0.6402749110056428, 'latency_mean': 1.561731231212616, 'latency_p50': 1.549365520477295, 'latency_p90': 1.7338435411453248}, {'batch_size': 3, 'throughput': 1.2549853683695484, 'latency_mean': 2.378825786113739, 'latency_p50': 2.4100215435028076, 'latency_p90': 2.627522683143616}, {'batch_size': 5, 'throughput': 1.5966655937983516, 'latency_mean': 3.118491196632385, 'latency_p50': 3.1095045804977417, 'latency_p90': 3.46698637008667}, {'batch_size': 6, 'throughput': 1.706037561844794, 'latency_mean': 3.495974599123001, 'latency_p50': 3.4795843362808228, 'latency_p90': 3.9614359378814696}, {'batch_size': 8, 'throughput': 1.863193059997831, 'latency_mean': 4.259124662876129, 'latency_p50': 4.266240954399109, 'latency_p90': 4.834160113334655}, {'batch_size': 10, 'throughput': 1.9533936179999933, 'latency_mean': 5.078840554952621, 'latency_p50': 5.091906309127808, 'latency_p90': 5.706301665306091}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-captain-bmo-12b_v16

is_internal_developer: True

language_model: Nitral-AI/Captain_BMO-12B

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-03

win_ratio: 0.507952376624557

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-v16-mkmlizer
Waiting for job on nitral-ai-captain-bmo-12b-v16-mkmlizer to finish
nitral-ai-captain-bmo-12b-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║     _____            __           __                                ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║       /___/                                                         ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  Version: 0.11.12                                                   ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ║                                                                     ║
nitral-ai-captain-bmo-12b-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-captain-bmo-12b-v16-mkmlizer: Downloaded to shared memory in 40.062s
nitral-ai-captain-bmo-12b-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq5u860ca, device:0
nitral-ai-captain-bmo-12b-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-captain-bmo-12b-v16-mkmlizer: quantized model in 37.154s
nitral-ai-captain-bmo-12b-v16-mkmlizer: Processed model Nitral-AI/Captain_BMO-12B in 77.216s
nitral-ai-captain-bmo-12b-v16-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-captain-bmo-12b-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-captain-bmo-12b-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16
nitral-ai-captain-bmo-12b-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16/config.json
nitral-ai-captain-bmo-12b-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16/special_tokens_map.json
nitral-ai-captain-bmo-12b-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16/tokenizer_config.json
nitral-ai-captain-bmo-12b-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16/tokenizer.json
nitral-ai-captain-bmo-12b-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-captain-bmo-12b-v16/flywheel_model.0.safetensors
Job nitral-ai-captain-bmo-12b-v16-mkmlizer completed after 124.96s with status: succeeded
Stopping job with name nitral-ai-captain-bmo-12b-v16-mkmlizer
Pipeline stage MKMLizer completed in 125.49s
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-v16
Waiting for inference service nitral-ai-captain-bmo-12b-v16 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
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-v16 ready after 150.50729823112488s
Pipeline stage MKMLDeployer completed in 151.01s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.9632940292358398s
Received healthy response to inference request in 1.7314069271087646s
Received healthy response to inference request in 1.5262572765350342s
Received healthy response to inference request in 2.2063255310058594s
5 requests
1 failed requests
5th percentile: 1.5672872066497803
10th percentile: 1.6083171367645264
20th percentile: 1.6903769969940186
30th percentile: 1.7777843475341797
40th percentile: 1.8705391883850098
50th percentile: 1.9632940292358398
60th percentile: 2.0605066299438475
70th percentile: 2.1577192306518556
80th percentile: 5.7923074245452915
90th percentile: 12.964271211624148
95th percentile: 16.55025310516357
99th percentile: 19.419038619995117
mean time: 5.5127037525177
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3689618110656738s
Received healthy response to inference request in 1.510805606842041s
Received healthy response to inference request in 1.620734453201294s
Received healthy response to inference request in 1.3500659465789795s
Received healthy response to inference request in 1.3461706638336182s
5 requests
0 failed requests
5th percentile: 1.3469497203826903
10th percentile: 1.3477287769317627
20th percentile: 1.3492868900299073
30th percentile: 1.3538451194763184
40th percentile: 1.361403465270996
50th percentile: 1.3689618110656738
60th percentile: 1.4256993293762208
70th percentile: 1.4824368476867675
80th percentile: 1.5327913761138916
90th percentile: 1.5767629146575928
95th percentile: 1.5987486839294434
99th percentile: 1.6163372993469238
mean time: 1.4393476963043212
Pipeline stage StressChecker completed in 37.37s
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 2.37s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v16 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nitral-ai-captain-bmo-12b-v16-profiler
Waiting for inference service nitral-ai-captain-bmo-12b-v16-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 2796.12s
Shutdown handler de-registered
nitral-ai-captain-bmo-12b_v16 status is now inactive due to auto deactivation removed underperforming models