chaiml-season-4-top-solution

developer_uid: realhusoyun

submission_id: chaiml-season-4-top-solution_v19

model_name: season-2-model

model_group: ChaiML/season_4_top_solu

status: torndown

timestamp: 2024-09-23T17:59:38+00:00

num_battles: 18696

num_wins: 8006

celo_rating: 1188.4

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/season_4_top_solution

model_architecture: LlamaForCausalLM

model_num_parameters: 13015864320.0

best_of: 4

max_input_tokens: 2048

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.42250814558749294, 'latency_mean': 2.3667147278785707, 'latency_p50': 2.366331934928894, 'latency_p90': 2.564563679695129}, {'batch_size': 2, 'throughput': 0.5611156929488117, 'latency_mean': 3.560696552991867, 'latency_p50': 3.5612261295318604, 'latency_p90': 3.86608350276947}, {'batch_size': 3, 'throughput': 0.6429239245368216, 'latency_mean': 4.650762449502945, 'latency_p50': 4.650888442993164, 'latency_p90': 5.1379303455352785}, {'batch_size': 4, 'throughput': 0.6943247608045575, 'latency_mean': 5.743450077772141, 'latency_p50': 5.69587254524231, 'latency_p90': 6.417233991622925}, {'batch_size': 5, 'throughput': 0.7225056928986202, 'latency_mean': 6.888751139640808, 'latency_p50': 6.823786973953247, 'latency_p90': 7.896916103363036}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: season-2-model

is_internal_developer: False

language_model: ChaiML/season_4_top_solution

model_size: 13B

ranking_group: single

throughput_3p7s: 0.58

us_pacific_date: 2024-09-23

win_ratio: 0.4282199400941378

generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|im_end|>'], 'max_input_tokens': 2048, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': "### Instruction:\nAs the assistant, your task is to fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}\n", 'prompt_template': '### Input:\n{prompt}\n', '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-season-4-top-solution-v19-mkmlizer
Waiting for job on chaiml-season-4-top-solution-v19-mkmlizer to finish
chaiml-season-4-top-solution-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-season-4-top-solution-v19-mkmlizer: ║     _____            __           __                                ║
chaiml-season-4-top-solution-v19-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-season-4-top-solution-v19-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-season-4-top-solution-v19-mkmlizer: ║       /___/                                                         ║
chaiml-season-4-top-solution-v19-mkmlizer: ║                                                                     ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-season-4-top-solution-v19-mkmlizer: ║                                                                     ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  belonging to:                                                      ║
chaiml-season-4-top-solution-v19-mkmlizer: ║                                                                     ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-season-4-top-solution-v19-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-season-4-top-solution-v19-mkmlizer: ║                                                                     ║
chaiml-season-4-top-solution-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-season-4-top-solution-v19-mkmlizer: Downloaded to shared memory in 74.290s
chaiml-season-4-top-solution-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptcef4knt, device:0
chaiml-season-4-top-solution-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-season-4-top-solution-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-season-4-top-solution-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/special_tokens_map.json
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/config.json
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/tokenizer_config.json
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/added_tokens.json
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/tokenizer.model
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/tokenizer.json
chaiml-season-4-top-solution-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-season-4-top-solution-v19/flywheel_model.0.safetensors
Job chaiml-season-4-top-solution-v19-mkmlizer completed after 136.72s with status: succeeded
Stopping job with name chaiml-season-4-top-solution-v19-mkmlizer
Pipeline stage MKMLizer completed in 137.52s
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 chaiml-season-4-top-solution-v19
Waiting for inference service chaiml-season-4-top-solution-v19 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
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
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
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
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 chaiml-season-4-top-solution-v19 ready after 191.94118785858154s
Pipeline stage MKMLDeployer completed in 192.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3376898765563965s
Received healthy response to inference request in 2.580598831176758s
Received healthy response to inference request in 2.2332255840301514s
Received healthy response to inference request in 1.9544644355773926s
Received healthy response to inference request in 2.359760284423828s
5 requests
0 failed requests
5th percentile: 2.0102166652679445
10th percentile: 2.065968894958496
20th percentile: 2.1774733543395994
30th percentile: 2.2541184425354004
40th percentile: 2.2959041595458984
50th percentile: 2.3376898765563965
60th percentile: 2.346518039703369
70th percentile: 2.355346202850342
80th percentile: 2.4039279937744142
90th percentile: 2.492263412475586
95th percentile: 2.5364311218261717
99th percentile: 2.5717652893066405
mean time: 2.2931478023529053
Pipeline stage StressChecker completed in 13.43s
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 3.49s
Shutdown handler de-registered
chaiml-season-4-top-solution_v19 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-season-4-top-solution-v19-profiler
Waiting for inference service chaiml-season-4-top-solution-v19-profiler to be ready
Inference service chaiml-season-4-top-solution-v19-profiler ready after 190.46210479736328s
Pipeline stage MKMLProfilerDeployer completed in 190.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-season-4-top-0f3ab9d998a590c06e55c515f2574de4-deplokljsv:/code/chaiverse_profiler_1727114967 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-season-4-top-0f3ab9d998a590c06e55c515f2574de4-deplokljsv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727114967 && python profiles.py profile --best_of_n 4 --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 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1727114967/summary.json'
kubectl exec -it chaiml-season-4-top-0f3ab9d998a590c06e55c515f2574de4-deplokljsv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727114967/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1711.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-season-4-top-solution-v19-profiler is running
Tearing down inference service chaiml-season-4-top-solution-v19-profiler
Service chaiml-season-4-top-solution-v19-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.91s
Shutdown handler de-registered
chaiml-season-4-top-solution_v19 status is now inactive due to auto deactivation removed underperforming models
run pipeline %s
admin requested tearing down of chaiml-season-4-top-solution_v19
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
Shutdown handler de-registered
chaiml-season-4-top-solution_v19 status is now torndown due to DeploymentManager action