developer_uid: robert_irvine
submission_id: mistralai-mistral-nemo_9330_v150
model_name: mistralai-mistral-nemo_9330_v150
model_group: mistralai/Mistral-Nemo-I
status: torndown
timestamp: 2024-10-08T17:41:20+00:00
num_battles: 6889
num_wins: 3331
celo_rating: 1244.57
family_friendly_score: 0.619426183560108
family_friendly_standard_error: 0.005972449285861048
submission_type: basic
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: mistralai-mistral-nemo_9330_v150
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-08
win_ratio: 0.48352445928291476
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|>'], 'max_input_tokens': 1024, 'best_of': 8, '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 mistralai-mistral-nemo-9330-v150-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v150-mkmlizer to finish
mistralai-mistral-nemo-9330-v150-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v150-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  Version: 0.11.12                                                   ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v150-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v150-mkmlizer: Downloaded to shared memory in 55.018s
mistralai-mistral-nemo-9330-v150-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_verp6lc, device:0
mistralai-mistral-nemo-9330-v150-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v150-mkmlizer: quantized model in 36.200s
mistralai-mistral-nemo-9330-v150-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 91.218s
mistralai-mistral-nemo-9330-v150-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v150-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v150-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150
mistralai-mistral-nemo-9330-v150-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150/config.json
mistralai-mistral-nemo-9330-v150-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150/special_tokens_map.json
mistralai-mistral-nemo-9330-v150-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150/tokenizer_config.json
mistralai-mistral-nemo-9330-v150-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150/tokenizer.json
mistralai-mistral-nemo-9330-v150-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v150/flywheel_model.0.safetensors
Job mistralai-mistral-nemo-9330-v150-mkmlizer completed after 164.96s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v150-mkmlizer
Pipeline stage MKMLizer completed in 165.54s
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 mistralai-mistral-nemo-9330-v150
Waiting for inference service mistralai-mistral-nemo-9330-v150 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service mistralai-mistral-nemo-9330-v150 ready after 130.95012855529785s
Pipeline stage MKMLDeployer completed in 131.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6166353225708008s
Received healthy response to inference request in 1.296574354171753s
Received healthy response to inference request in 0.9021263122558594s
Received healthy response to inference request in 1.198387622833252s
Received healthy response to inference request in 1.3598308563232422s
5 requests
0 failed requests
5th percentile: 0.9613785743713379
10th percentile: 1.0206308364868164
20th percentile: 1.1391353607177734
30th percentile: 1.2180249691009521
40th percentile: 1.2572996616363525
50th percentile: 1.296574354171753
60th percentile: 1.3218769550323486
70th percentile: 1.3471795558929442
80th percentile: 1.411191749572754
90th percentile: 1.5139135360717773
95th percentile: 1.565274429321289
99th percentile: 1.6063631439208985
mean time: 1.2747108936309814
Pipeline stage StressChecker completed in 7.71s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v150 status is now deployed due to DeploymentManager action
mistralai-mistral-nemo_9330_v150 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo_9330_v150 status is now torndown due to DeploymentManager action