rirv938-llama-8b-mixtral_5510

developer_uid: robert_irvine

submission_id: rirv938-llama-8b-mixtral_5510_v1

model_name: rirv938-llama-8b-mixtral_5510_v1

model_group: rirv938/llama_8b_mixtral

status: torndown

timestamp: 2024-09-14T23:14:30+00:00

num_battles: 9713

num_wins: 4911

celo_rating: 1257.0

family_friendly_score: 0.0

submission_type: basic

model_repo: rirv938/llama_8b_mixtral_vs_mixtral_250k_679

model_architecture: LlamaForSequenceClassification

model_num_parameters: 8030261248.0

best_of: 1

max_input_tokens: 256

max_output_tokens: 1

latencies: [{'batch_size': 1, 'throughput': 0.1063313237702841, 'latency_mean': 9.40450733423233, 'latency_p50': 9.405229687690735, 'latency_p90': 9.51176142692566}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-llama-8b-mixtral_5510_v1

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: rirv938/llama_8b_mixtral_vs_mixtral_250k_679

model_size: 8B

ranking_group: single

us_pacific_date: 2024-09-14

win_ratio: 0.5056110367548646

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': 256, 'best_of': 1, 'max_output_tokens': 1}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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 rirv938-llama-8b-mixtral-5510-v1-mkmlizer
Waiting for job on rirv938-llama-8b-mixtral-5510-v1-mkmlizer to finish
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-mixtral-5510-v1-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
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: Downloaded to shared memory in 34.609s
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpkd_o8kyh, device:0
rirv938-llama-8b-mixtral-5510-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: quantized model in 85.015s
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: Processed model rirv938/llama_8b_mixtral_vs_mixtral_250k_679 in 119.625s
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-mixtral-5510-v1
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-mixtral-5510-v1/config.json
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-mixtral-5510-v1/special_tokens_map.json
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-mixtral-5510-v1/tokenizer_config.json
rirv938-llama-8b-mixtral-5510-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-mixtral-5510-v1/tokenizer.json
Job rirv938-llama-8b-mixtral-5510-v1-mkmlizer completed after 149.09s with status: succeeded
Stopping job with name rirv938-llama-8b-mixtral-5510-v1-mkmlizer
Pipeline stage MKMLizer completed in 152.97s
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 rirv938-llama-8b-mixtral-5510-v1
Waiting for inference service rirv938-llama-8b-mixtral-5510-v1 to be ready
Inference service rirv938-llama-8b-mixtral-5510-v1 ready after 170.56291580200195s
Pipeline stage MKMLDeployer completed in 170.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.771729230880737s
Received healthy response to inference request in 2.6954593658447266s
Received healthy response to inference request in 4.561097860336304s
Received healthy response to inference request in 3.375699520111084s
Received healthy response to inference request in 3.397996187210083s
5 requests
0 failed requests
5th percentile: 2.8315073966979982
10th percentile: 2.9675554275512694
20th percentile: 3.2396514892578123
30th percentile: 3.380158853530884
40th percentile: 3.3890775203704835
50th percentile: 3.397996187210083
60th percentile: 3.863236856460571
70th percentile: 4.328477525711059
80th percentile: 4.60322413444519
90th percentile: 4.687476682662964
95th percentile: 4.729602956771851
99th percentile: 4.76330397605896
mean time: 3.760396432876587
Pipeline stage StressChecker completed in 19.57s
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 6.13s
Shutdown handler de-registered
rirv938-llama-8b-mixtral_5510_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-mixtral-5510-v1-profiler
Waiting for inference service rirv938-llama-8b-mixtral-5510-v1-profiler to be ready
Inference service rirv938-llama-8b-mixtral-5510-v1-profiler ready after 270.6251721382141s
Pipeline stage MKMLProfilerDeployer completed in 271.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mix3ac0a51aa48bd6ee6bdf43f5b6d72b7a-deploxpjf7:/code/chaiverse_profiler_1726356351 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mix3ac0a51aa48bd6ee6bdf43f5b6d72b7a-deploxpjf7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726356351 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1726356351/summary.json'
kubectl exec -it rirv938-llama-8b-mix3ac0a51aa48bd6ee6bdf43f5b6d72b7a-deploxpjf7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726356351/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1891.41s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-mixtral-5510-v1-profiler is running
Tearing down inference service rirv938-llama-8b-mixtral-5510-v1-profiler
Service rirv938-llama-8b-mixtral-5510-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.84s
Shutdown handler de-registered
rirv938-llama-8b-mixtral_5510_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-mixtral_5510_v1 status is now torndown due to DeploymentManager action