developer_uid: azuruce
submission_id: chaiml-nemo-20241015-dar_3550_v1
model_name: chaiml-nemo-20241015-dar_3550_v1
model_group: ChaiML/nemo-20241015-dar
status: torndown
timestamp: 2024-10-17T04:51:14+00:00
num_battles: 8104
num_wins: 4110
celo_rating: 1262.57
family_friendly_score: 0.55165135608049
family_friendly_standard_error: 0.005663827467094135
submission_type: basic
model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241015-dar_3550_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-16
win_ratio: 0.5071569595261599
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_of_text|>', 'You:'], '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': '### Response:\n{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 chaiml-nemo-20241015-dar-3550-v1-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-3550-v1-mkmlizer to finish
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: Downloaded to shared memory in 49.413s
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxlncdlg1, device:0
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: quantized model in 39.422s
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-albert in 88.835s
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v1
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v1/special_tokens_map.json
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v1/config.json
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v1/tokenizer_config.json
chaiml-nemo-20241015-dar-3550-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v1/tokenizer.json
Job chaiml-nemo-20241015-dar-3550-v1-mkmlizer completed after 129.09s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-3550-v1-mkmlizer
Pipeline stage MKMLizer completed in 129.61s
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 chaiml-nemo-20241015-dar-3550-v1
Waiting for inference service chaiml-nemo-20241015-dar-3550-v1 to be ready
Inference service chaiml-nemo-20241015-dar-3550-v1 ready after 160.57661151885986s
Pipeline stage MKMLDeployer completed in 161.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7860751152038574s
Received healthy response to inference request in 1.4525752067565918s
Received healthy response to inference request in 1.494023323059082s
Received healthy response to inference request in 1.5696966648101807s
Received healthy response to inference request in 1.3879950046539307s
5 requests
0 failed requests
5th percentile: 1.4009110450744628
10th percentile: 1.413827085494995
20th percentile: 1.4396591663360596
30th percentile: 1.4608648300170899
40th percentile: 1.4774440765380858
50th percentile: 1.494023323059082
60th percentile: 1.5242926597595214
70th percentile: 1.5545619964599608
80th percentile: 1.612972354888916
90th percentile: 1.6995237350463868
95th percentile: 1.742799425125122
99th percentile: 1.7774199771881103
mean time: 1.5380730628967285
Pipeline stage StressChecker completed in 9.22s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_3550_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_3550_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_3550_v1 status is now torndown due to DeploymentManager action