rinen0721-llama0903

submission_id: rinen0721-llama0903_v2

developer_uid: rinen0721

best_of: 16

celo_rating: 1216.97

display_name: rinen0721-llama0903_v2

family_friendly_score: 0.0

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}

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}

is_internal_developer: False

language_model: rinen0721/llama0903

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rinen0721/llama0903

model_name: rinen0721-llama0903_v2

model_num_parameters: 8030261248.0

model_repo: rinen0721/llama0903

model_size: 8B

num_battles: 12497

num_wins: 5816

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-09-03T07:43:11+00:00

us_pacific_date: 2024-09-03

win_ratio: 0.46539169400656155

Resubmit model

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rinen0721-llama0903-v2-mkmlizer
Waiting for job on rinen0721-llama0903-v2-mkmlizer to finish
rinen0721-llama0903-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-llama0903-v2-mkmlizer: ║     _____            __           __                                ║
rinen0721-llama0903-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-llama0903-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-llama0903-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-llama0903-v2-mkmlizer: ║       /___/                                                         ║
rinen0721-llama0903-v2-mkmlizer: ║                                                                     ║
rinen0721-llama0903-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
rinen0721-llama0903-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-llama0903-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-llama0903-v2-mkmlizer: ║                                                                     ║
rinen0721-llama0903-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-llama0903-v2-mkmlizer: ║  belonging to:                                                      ║
rinen0721-llama0903-v2-mkmlizer: ║                                                                     ║
rinen0721-llama0903-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-llama0903-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-llama0903-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rinen0721-llama0903-v2-mkmlizer: ║                                                                     ║
rinen0721-llama0903-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-llama0903-v2-mkmlizer: Downloaded to shared memory in 23.746s
rinen0721-llama0903-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv5fy9wtx, device:0
rinen0721-llama0903-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-llama0903-v2-mkmlizer: quantized model in 25.883s
rinen0721-llama0903-v2-mkmlizer: Processed model rinen0721/llama0903 in 49.630s
rinen0721-llama0903-v2-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-llama0903-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-llama0903-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-llama0903-v2
rinen0721-llama0903-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-llama0903-v2/special_tokens_map.json
rinen0721-llama0903-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-llama0903-v2/config.json
rinen0721-llama0903-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-llama0903-v2/tokenizer_config.json
rinen0721-llama0903-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-llama0903-v2/tokenizer.json
rinen0721-llama0903-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-llama0903-v2/flywheel_model.0.safetensors
Job rinen0721-llama0903-v2-mkmlizer completed after 74.19s with status: succeeded
Stopping job with name rinen0721-llama0903-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-llama0903-v2
Waiting for inference service rinen0721-llama0903-v2 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 rinen0721-llama0903-v2 ready after 140.639301776886s
Pipeline stage MKMLDeployer completed in 142.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.094050168991089s
Received healthy response to inference request in 1.585214614868164s
Received healthy response to inference request in 2.663114547729492s
Received healthy response to inference request in 1.7231109142303467s
Received healthy response to inference request in 1.853954553604126s
5 requests
0 failed requests
5th percentile: 1.6127938747406005
10th percentile: 1.640373134613037
20th percentile: 1.6955316543579102
30th percentile: 1.7492796421051025
40th percentile: 1.8016170978546142
50th percentile: 1.853954553604126
60th percentile: 1.949992799758911
70th percentile: 2.046031045913696
80th percentile: 2.2078630447387697
90th percentile: 2.435488796234131
95th percentile: 2.5493016719818113
99th percentile: 2.640351972579956
mean time: 1.9838889598846436
Pipeline stage StressChecker completed in 10.61s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.52s
rinen0721-llama0903_v2 status is now deployed due to DeploymentManager action
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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-llama0903-v2-profiler
Waiting for inference service rinen0721-llama0903-v2-profiler to be ready
Inference service rinen0721-llama0903-v2-profiler ready after 150.44227981567383s
Pipeline stage MKMLProfilerDeployer completed in 150.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rinen0721-llama0903-v2-profiler-predictor-00001-deploymentvxz6h:/code/chaiverse_profiler_1725349885 --namespace tenant-chaiml-guanaco
kubectl exec -it rinen0721-llama0903-v2-profiler-predictor-00001-deploymentvxz6h --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725349885 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --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_1725349885/summary.json'
rinen0721-llama0903_v2 status is now inactive due to auto deactivation removed underperforming models
rinen0721-llama0903_v2 status is now torndown due to DeploymentManager action