developer_uid: chai_backend_admin
submission_id: chaiml-nemo-20241010-ti_5991_v79
model_name: chaiml-nemo-20241010-ti_5991_v79
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-13T21:00:59+00:00
num_battles: 10788
num_wins: 5505
celo_rating: 1261.89
family_friendly_score: 0.5934470820969338
family_friendly_standard_error: 0.004859499362479567
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_v79
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v4-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-13
win_ratio: 0.5102892102335929
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-v79-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v79-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: Downloaded to shared memory in 39.108s
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbqbo_2hy, device:0
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: quantized model in 36.516s
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 75.624s
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79/config.json
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79/tokenizer.json
chaiml-nemo-20241010-ti-5991-v79-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v79/flywheel_model.0.safetensors
Job chaiml-nemo-20241010-ti-5991-v79-mkmlizer completed after 104.17s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v79-mkmlizer
Pipeline stage MKMLizer completed in 104.73s
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-v79
Waiting for inference service chaiml-nemo-20241010-ti-5991-v79 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241010-ti-5991-v79 ready after 170.60206651687622s
Pipeline stage MKMLDeployer completed in 171.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8612523078918457s
Received healthy response to inference request in 1.6109321117401123s
Received healthy response to inference request in 1.512277364730835s
Received healthy response to inference request in 2.4218504428863525s
Received healthy response to inference request in 1.3973057270050049s
5 requests
0 failed requests
5th percentile: 1.420300054550171
10th percentile: 1.443294382095337
20th percentile: 1.489283037185669
30th percentile: 1.5320083141326903
40th percentile: 1.5714702129364013
50th percentile: 1.6109321117401123
60th percentile: 1.7110601902008056
70th percentile: 1.811188268661499
80th percentile: 1.9733719348907472
90th percentile: 2.19761118888855
95th percentile: 2.309730815887451
99th percentile: 2.3994265174865723
mean time: 1.76072359085083
Pipeline stage StressChecker completed in 10.10s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v79 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v79 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v79 status is now torndown due to DeploymentManager action