submission_id: sao10k-lyra-4-2-chai_v3
developer_uid: sao10k
best_of: 8
celo_rating: 1261.92
display_name: lyra42x
family_friendly_score: 0.5671367962389635
family_friendly_standard_error: 0.009167182716100815
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: Sao10K/lyra-4-2-chai
latencies: [{'batch_size': 1, 'throughput': 0.6935030307821071, 'latency_mean': 1.441895625591278, 'latency_p50': 1.4416394233703613, 'latency_p90': 1.5959074735641479}, {'batch_size': 3, 'throughput': 1.3180947649240267, 'latency_mean': 2.2676336801052095, 'latency_p50': 2.2751269340515137, 'latency_p90': 2.5242862701416016}, {'batch_size': 5, 'throughput': 1.5523801766877363, 'latency_mean': 3.2088024842739107, 'latency_p50': 3.231033205986023, 'latency_p90': 3.6588056802749636}, {'batch_size': 6, 'throughput': 1.5952244161759184, 'latency_mean': 3.73923330783844, 'latency_p50': 3.7287819385528564, 'latency_p90': 4.268093895912171}, {'batch_size': 8, 'throughput': 1.5859515027549211, 'latency_mean': 5.021073160171508, 'latency_p50': 5.034155011177063, 'latency_p90': 5.671038269996643}, {'batch_size': 10, 'throughput': 1.539461751860951, 'latency_mean': 6.4540984416008, 'latency_p50': 6.55182421207428, 'latency_p90': 7.355883145332337}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Sao10K/lyra-4-2-chai
model_name: lyra42x
model_num_parameters: 12772070400.0
model_repo: Sao10K/lyra-4-2-chai
model_size: 13B
num_battles: 2987
num_wins: 1531
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.6
timestamp: 2024-09-26T06:35:42+00:00
us_pacific_date: 2024-09-25
win_ratio: 0.5125544024104453
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 sao10k-lyra-4-2-chai-v3-mkmlizer
Waiting for job on sao10k-lyra-4-2-chai-v3-mkmlizer to finish
sao10k-lyra-4-2-chai-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-lyra-4-2-chai-v3-mkmlizer: ║     _____            __           __                                ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║       /___/                                                         ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║                                                                     ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║                                                                     ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  belonging to:                                                      ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║                                                                     ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ║                                                                     ║
sao10k-lyra-4-2-chai-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-lyra-4-2-chai-v3-mkmlizer: Downloaded to shared memory in 48.961s
sao10k-lyra-4-2-chai-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8vt0745y, device:0
sao10k-lyra-4-2-chai-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-lyra-4-2-chai-v3-mkmlizer: quantized model in 37.619s
sao10k-lyra-4-2-chai-v3-mkmlizer: Processed model Sao10K/lyra-4-2-chai in 86.580s
sao10k-lyra-4-2-chai-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-lyra-4-2-chai-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-lyra-4-2-chai-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-lyra-4-2-chai-v3
sao10k-lyra-4-2-chai-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-lyra-4-2-chai-v3/config.json
sao10k-lyra-4-2-chai-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-lyra-4-2-chai-v3/special_tokens_map.json
sao10k-lyra-4-2-chai-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-lyra-4-2-chai-v3/tokenizer_config.json
sao10k-lyra-4-2-chai-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-lyra-4-2-chai-v3/tokenizer.json
Job sao10k-lyra-4-2-chai-v3-mkmlizer completed after 130.58s with status: succeeded
Stopping job with name sao10k-lyra-4-2-chai-v3-mkmlizer
Pipeline stage MKMLizer completed in 131.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-lyra-4-2-chai-v3
Waiting for inference service sao10k-lyra-4-2-chai-v3 to be ready
Inference service sao10k-lyra-4-2-chai-v3 ready after 210.48917031288147s
Pipeline stage MKMLDeployer completed in 210.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1069769859313965s
Received healthy response to inference request in 1.5816936492919922s
Received healthy response to inference request in 1.8250269889831543s
Received healthy response to inference request in 1.7622709274291992s
Received healthy response to inference request in 1.626274824142456s
5 requests
0 failed requests
5th percentile: 1.590609884262085
10th percentile: 1.5995261192321777
20th percentile: 1.6173585891723632
30th percentile: 1.6534740447998046
40th percentile: 1.707872486114502
50th percentile: 1.7622709274291992
60th percentile: 1.7873733520507813
70th percentile: 1.8124757766723634
80th percentile: 1.8814169883728027
90th percentile: 1.9941969871520997
95th percentile: 2.050586986541748
99th percentile: 2.095698986053467
mean time: 1.7804486751556396
Pipeline stage StressChecker completed in 9.52s
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 8.66s
Shutdown handler de-registered
sao10k-lyra-4-2-chai_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-lyra-4-2-chai-v3-profiler
Waiting for inference service sao10k-lyra-4-2-chai-v3-profiler to be ready
Inference service sao10k-lyra-4-2-chai-v3-profiler ready after 220.5096938610077s
Pipeline stage MKMLProfilerDeployer completed in 220.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-lyra-4-2-chai-v3-profiler-predictor-00001-deploymenj5dgk:/code/chaiverse_profiler_1727333173 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-lyra-4-2-chai-v3-profiler-predictor-00001-deploymenj5dgk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727333173 && python profiles.py profile --best_of_n 8 --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_1727333173/summary.json'
kubectl exec -it sao10k-lyra-4-2-chai-v3-profiler-predictor-00001-deploymenj5dgk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727333173/summary.json'
Pipeline stage MKMLProfilerRunner completed in 956.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-lyra-4-2-chai-v3-profiler is running
Tearing down inference service sao10k-lyra-4-2-chai-v3-profiler
Service sao10k-lyra-4-2-chai-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.31s
Shutdown handler de-registered
sao10k-lyra-4-2-chai_v3 status is now inactive due to auto deactivation removed underperforming models
Cleaning model data from S3
admin requested tearing down of blend_rofur_2024-10-03
Ignoring service blend-rofur-2024-10-03 already deployed
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of sao10k-lyra-4-2-chai_v3
Cleaning model data from model cache
Shutdown handler not registered because Python interpreter is not running in the main thread
Waiting for inference service blend-rofur-2024-10-03 to be ready
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key rica40325-mistral-3678-v4/config.json from bucket guanaco-mkml-models
admin requested tearing down of sao10k-lyra-4-2-chai_v4
run pipeline %s
run pipeline stage %s
run pipeline %s
Deleting key rica40325-mistral-3678-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Running pipeline stage MKMLDeleter
admin requested tearing down of blend_rofur_2024-10-03
sao10k-lyra-4-2-chai_v3 status is now torndown due to DeploymentManager action
Tearing down inference service blend-rofur-2024-10-03
Creating inference service blend-rofur-2024-10-03
sao10k-lyra-4-2-chai_v3 status is now torndown due to DeploymentManager action
run pipeline stage %s
Deleting key chaiml-nemo-slerp-esao-b-7186-v1/config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 65.90s
Running pipeline stage MKMLDeployer
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 58.76s
Skipping teardown as no inference service was successfully deployed
sao10k-lyra-4-2-chai_v3 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLModelDeleter
sao10k-lyra-4-2-chai_v3 status is now torndown due to DeploymentManager action