rica40325-feedback-retry-4500

developer_uid: rica40325
submission_id: rica40325-feedback-retry-4500_v1
model_name: rica40325-feedback-retry-4500_v1
model_group: rica40325/feedback-retry
status: torndown
timestamp: 2024-09-08T08:23:53+00:00
num_battles: 14940
num_wins: 7585
celo_rating: 1247.8
family_friendly_score: 0.0
submission_type: basic
model_repo: rica40325/feedback-retry-4500
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rica40325-feedback-retry-4500_v1
is_internal_developer: False
language_model: rica40325/feedback-retry-4500
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-08
win_ratio: 0.5076974564926372
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': 16, '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 rica40325-feedback-retry-4500-v1-mkmlizer
Waiting for job on rica40325-feedback-retry-4500-v1-mkmlizer to finish
rica40325-feedback-retry-4500-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-retry-4500-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║       /___/                                                         ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-feedback-retry-4500-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-retry-4500-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rica40325-feedback-retry-4500-v1-mkmlizer: Downloaded to shared memory in 63.200s
rica40325-feedback-retry-4500-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk6wqk2rk, device:0
rica40325-feedback-retry-4500-v1-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
rica40325-feedback-retry-4500-v1-mkmlizer: quantized model in 29.339s
rica40325-feedback-retry-4500-v1-mkmlizer: Processed model rica40325/feedback-retry-4500 in 92.540s
rica40325-feedback-retry-4500-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-retry-4500-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-retry-4500-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-retry-4500-v1
rica40325-feedback-retry-4500-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-retry-4500-v1/config.json
rica40325-feedback-retry-4500-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-retry-4500-v1/special_tokens_map.json
rica40325-feedback-retry-4500-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-retry-4500-v1/tokenizer_config.json
rica40325-feedback-retry-4500-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-retry-4500-v1/tokenizer.json
Job rica40325-feedback-retry-4500-v1-mkmlizer completed after 169.44s with status: succeeded
Stopping job with name rica40325-feedback-retry-4500-v1-mkmlizer
Pipeline stage MKMLizer completed in 170.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-retry-4500-v1
Waiting for inference service rica40325-feedback-retry-4500-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
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 rica40325-feedback-retry-4500-v1 ready after 150.77982115745544s
Pipeline stage MKMLDeployer completed in 151.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2579944133758545s
Received healthy response to inference request in 2.4407131671905518s
Received healthy response to inference request in 1.5943138599395752s
Received healthy response to inference request in 2.003019094467163s
Received healthy response to inference request in 2.4389379024505615s
5 requests
0 failed requests
5th percentile: 1.6760549068450927
10th percentile: 1.7577959537506103
20th percentile: 1.9212780475616456
30th percentile: 2.0540141582489015
40th percentile: 2.156004285812378
50th percentile: 2.2579944133758545
60th percentile: 2.3303718090057375
70th percentile: 2.40274920463562
80th percentile: 2.4392929553985594
90th percentile: 2.4400030612945556
95th percentile: 2.440358114242554
99th percentile: 2.440642156600952
mean time: 2.146995687484741
Pipeline stage StressChecker completed in 11.80s
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 3.87s
Shutdown handler de-registered
rica40325-feedback-retry-4500_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-feedback-retry-4500-v1-profiler
Waiting for inference service rica40325-feedback-retry-4500-v1-profiler to be ready
Inference service rica40325-feedback-retry-4500-v1-profiler ready after 150.40129280090332s
Pipeline stage MKMLProfilerDeployer completed in 150.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms:/code/chaiverse_profiler_1725784363 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725784363 && python profiles.py profile --best_of_n 16 --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_1725784363/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms:/code/chaiverse_profiler_1725785296 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725785296 && python profiles.py profile --best_of_n 16 --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_1725785296/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms:/code/chaiverse_profiler_1725785608 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-r8ebea7c3aa2ccadc6fd8be132f8f7412-deplorhjms --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725785608 && python profiles.py profile --best_of_n 16 --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_1725785608/summary.json'
clean up pipeline due to error=%s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-retry-4500-v1-profiler is running
Tearing down inference service rica40325-feedback-retry-4500-v1-profiler
Service rica40325-feedback-retry-4500-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.65s
Shutdown handler de-registered
rica40325-feedback-retry-4500_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedback-retry-4500_v1 status is now torndown due to DeploymentManager action