developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_3527_v1
model_name: sanchuanhehe-adjusted-co_3527_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:10:24+00:00
num_battles: 11098
num_wins: 4735
celo_rating: 1122.45
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_15_l
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 1.1218412864604457, 'latency_mean': 0.8913269758224487, 'latency_p50': 0.9023903608322144, 'latency_p90': 0.9893661499023437}, {'batch_size': 5, 'throughput': 3.73129517492877, 'latency_mean': 1.3300739908218384, 'latency_p50': 1.3322590589523315, 'latency_p90': 1.4954580068588257}, {'batch_size': 10, 'throughput': 5.482373655477997, 'latency_mean': 1.7975195944309235, 'latency_p50': 1.7826956510543823, 'latency_p90': 2.078432559967041}, {'batch_size': 15, 'throughput': 6.489855222350246, 'latency_mean': 2.2615202081203463, 'latency_p50': 2.2680187225341797, 'latency_p90': 2.613528251647949}, {'batch_size': 20, 'throughput': 7.063594324639862, 'latency_mean': 2.793442953824997, 'latency_p50': 2.808182954788208, 'latency_p90': 3.201350998878479}, {'batch_size': 25, 'throughput': 7.408439324713707, 'latency_mean': 3.300793906450272, 'latency_p50': 3.293712019920349, 'latency_p90': 3.911192488670349}, {'batch_size': 30, 'throughput': 7.751348337006749, 'latency_mean': 3.7823433792591095, 'latency_p50': 3.7559266090393066, 'latency_p90': 4.320758485794068}, {'batch_size': 35, 'throughput': 7.791744550212301, 'latency_mean': 4.3609173405170445, 'latency_p50': 4.260810375213623, 'latency_p90': 5.254087305068969}, {'batch_size': 40, 'throughput': 7.858945929977051, 'latency_mean': 4.927092105150223, 'latency_p50': 4.8764060735702515, 'latency_p90': 5.971726894378662}, {'batch_size': 45, 'throughput': 7.7559195599313595, 'latency_mean': 5.563453415632248, 'latency_p50': 5.619353413581848, 'latency_p90': 6.3927729845047}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_3527_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_15_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.88
us_pacific_date: 2024-09-17
win_ratio: 0.42665345107226527
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': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 sanchuanhehe-adjusted-co-3527-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-3527-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: Downloaded to shared memory in 31.480s
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3t5zsu3n, device:0
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: quantized model in 17.706s
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_15_l in 49.186s
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/config.json
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/tokenizer.model
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/tokenizer.json
sanchuanhehe-adjusted-co-3527-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3527-v1/flywheel_model.0.safetensors
Job sanchuanhehe-adjusted-co-3527-v1-mkmlizer completed after 73.22s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-3527-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-3527-v1
Waiting for inference service sanchuanhehe-adjusted-co-3527-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sanchuanhehe-adjusted-co-3527-v1 ready after 180.80920457839966s
Pipeline stage MKMLDeployer completed in 181.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.917738676071167s
Received healthy response to inference request in 1.0918409824371338s
Received healthy response to inference request in 0.6789040565490723s
Received healthy response to inference request in 1.1421301364898682s
Received healthy response to inference request in 1.3719024658203125s
5 requests
0 failed requests
5th percentile: 0.7614914417266846
10th percentile: 0.8440788269042969
20th percentile: 1.0092535972595216
30th percentile: 1.1018988132476806
40th percentile: 1.1220144748687744
50th percentile: 1.1421301364898682
60th percentile: 1.234039068222046
70th percentile: 1.3259479999542236
80th percentile: 1.4810697078704835
90th percentile: 1.6994041919708252
95th percentile: 1.808571434020996
99th percentile: 1.8959052276611328
mean time: 1.2405032634735107
Pipeline stage StressChecker completed in 8.59s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.24s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3527_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-3527-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-3527-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-3527-v1-profiler ready after 190.44773077964783s
Pipeline stage MKMLProfilerDeployer completed in 190.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste1339d552308d667ffb7bc2f436fe2aa4-deplogfllx:/code/chaiverse_profiler_1726579122 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste1339d552308d667ffb7bc2f436fe2aa4-deplogfllx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579122 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726579122/summary.json'
kubectl exec -it sanchuanhehe-adjuste1339d552308d667ffb7bc2f436fe2aa4-deplogfllx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579122/summary.json'
Pipeline stage MKMLProfilerRunner completed in 462.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-3527-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-3527-v1-profiler
Service sanchuanhehe-adjusted-co-3527-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.04s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3527_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_3527_v1 status is now torndown due to DeploymentManager action