developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v12
model_name: chaiml-nemo-20241010-ti_5991_v12
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-12T05:00:41+00:00
num_battles: 6068
num_wins: 3106
celo_rating: 1263.48
family_friendly_score: 0.5445308002302821
family_friendly_standard_error: 0.006516955187109288
submission_type: basic
model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241010-ti_5991_v12
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-11
win_ratio: 0.511865524060646
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-20241010-ti-5991-v12-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v12-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: Downloaded to shared memory in 29.294s
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaj8uaeap, device:0
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: quantized model in 36.388s
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 65.682s
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12/config.json
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12/tokenizer.json
chaiml-nemo-20241010-ti-5991-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v12/flywheel_model.0.safetensors
Job chaiml-nemo-20241010-ti-5991-v12-mkmlizer completed after 93.66s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v12-mkmlizer
Pipeline stage MKMLizer completed in 94.18s
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-20241010-ti-5991-v12
Waiting for inference service chaiml-nemo-20241010-ti-5991-v12 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v12 ready after 160.97597336769104s
Pipeline stage MKMLDeployer completed in 161.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.291062355041504s
Received healthy response to inference request in 1.596832036972046s
Received healthy response to inference request in 1.5075724124908447s
Received healthy response to inference request in 1.4388582706451416s
Received healthy response to inference request in 1.9513332843780518s
5 requests
0 failed requests
5th percentile: 1.4526010990142821
10th percentile: 1.466343927383423
20th percentile: 1.4938295841217042
30th percentile: 1.525424337387085
40th percentile: 1.5611281871795655
50th percentile: 1.596832036972046
60th percentile: 1.7386325359344483
70th percentile: 1.8804330348968505
80th percentile: 2.0192790985107423
90th percentile: 2.155170726776123
95th percentile: 2.2231165409088134
99th percentile: 2.277473192214966
mean time: 1.7571316719055177
Pipeline stage StressChecker completed in 10.34s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v12 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v12 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v12 status is now torndown due to DeploymentManager action