developer_uid: robert_irvine
submission_id: chaiml-llama-8b-pairwis_8189_v33
model_name: chaiml-llama-8b-pairwis_8189_v33
model_group: ChaiML/llama_8b_pairwise
status: torndown
timestamp: 2024-10-13T22:24:20+00:00
num_battles: 7875
num_wins: 3888
celo_rating: 1243.58
family_friendly_score: 0.5784313725490196
family_friendly_standard_error: 0.005684460018393254
submission_type: basic
model_repo: ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-pairwis_8189_v33
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984
model_size: 8B
ranking_group: single
us_pacific_date: 2024-10-13
win_ratio: 0.4937142857142857
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'], 'max_input_tokens': 256, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-llama-8b-pairwis-8189-v33-mkmlizer
Waiting for job on chaiml-llama-8b-pairwis-8189-v33-mkmlizer to finish
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║                                                                     ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║                                                                     ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║                                                                     ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ║                                                                     ║
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: Downloaded to shared memory in 22.096s
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp9vmrzajc, device:0
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: quantized model in 85.346s
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: Processed model ChaiML/llama_8b_pairwise_64m_256_tokens_step_249984 in 107.442s
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33/config.json
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33/special_tokens_map.json
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33/tokenizer_config.json
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33/tokenizer.json
chaiml-llama-8b-pairwis-8189-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-pairwis-8189-v33/flywheel_model.0.safetensors
Job chaiml-llama-8b-pairwis-8189-v33-mkmlizer completed after 135.75s with status: succeeded
Stopping job with name chaiml-llama-8b-pairwis-8189-v33-mkmlizer
Pipeline stage MKMLizer completed in 136.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-pairwis-8189-v33
Waiting for inference service chaiml-llama-8b-pairwis-8189-v33 to be ready
Inference service chaiml-llama-8b-pairwis-8189-v33 ready after 170.92183375358582s
Pipeline stage MKMLDeployer completed in 171.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.986342191696167s
Received healthy response to inference request in 2.561152458190918s
Received healthy response to inference request in 1.785153865814209s
Received healthy response to inference request in 2.654161214828491s
Received healthy response to inference request in 2.0610177516937256s
5 requests
0 failed requests
5th percentile: 1.8403266429901124
10th percentile: 1.8954994201660156
20th percentile: 2.005844974517822
30th percentile: 2.161044692993164
40th percentile: 2.361098575592041
50th percentile: 2.561152458190918
60th percentile: 2.5983559608459474
70th percentile: 2.6355594635009765
80th percentile: 2.7205974102020263
90th percentile: 2.853469800949097
95th percentile: 2.919905996322632
99th percentile: 2.97305495262146
mean time: 2.409565496444702
Pipeline stage StressChecker completed in 13.61s
Shutdown handler de-registered
chaiml-llama-8b-pairwis_8189_v33 status is now deployed due to DeploymentManager action
chaiml-llama-8b-pairwis_8189_v33 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-pairwis_8189_v33 status is now torndown due to DeploymentManager action