developer_uid: rirv938
submission_id: rirv938-mistral-24b-bon_31129_v5
model_name: rirv938-mistral-24b-bon_31129_v5
model_group: rirv938/mistral_24b_bon_
status: torndown
timestamp: 2025-03-06T20:15:25+00:00
num_battles: 8503
num_wins: 4129
celo_rating: 1272.04
family_friendly_score: 0.5916
family_friendly_standard_error: 0.006951394680206268
submission_type: basic
model_repo: rirv938/mistral_24b_bon_dataset_1200_450_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3843040947472452, 'latency_mean': 2.602033656835556, 'latency_p50': 2.627434015274048, 'latency_p90': 2.880437135696411}, {'batch_size': 3, 'throughput': 0.7924517260584152, 'latency_mean': 3.7791294252872465, 'latency_p50': 3.7558854818344116, 'latency_p90': 4.210998749732971}, {'batch_size': 5, 'throughput': 1.0427974072530355, 'latency_mean': 4.78064583659172, 'latency_p50': 4.782323598861694, 'latency_p90': 5.3154041290283205}, {'batch_size': 6, 'throughput': 1.1262055710288628, 'latency_mean': 5.305958088636398, 'latency_p50': 5.259220242500305, 'latency_p90': 6.032571101188659}, {'batch_size': 10, 'throughput': 1.2849056866248, 'latency_mean': 7.7327933490276335, 'latency_p50': 7.708912014961243, 'latency_p90': 8.726393985748292}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-bon_31129_v5
is_internal_developer: True
language_model: rirv938/mistral_24b_bon_dataset_1200_450_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.77
us_pacific_date: 2025-03-06
win_ratio: 0.48559332000470423
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-mistral-24b-bon-31129-v5-mkmlizer
Waiting for job on rirv938-mistral-24b-bon-31129-v5-mkmlizer to finish
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-bon-31129-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-bon-31129-v5-mkmlizer: Downloaded to shared memory in 127.961s
rirv938-mistral-24b-bon-31129-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0pgn11ws, device:0
rirv938-mistral-24b-bon-31129-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-bon-31129-v5-mkmlizer: quantized model in 63.543s
rirv938-mistral-24b-bon-31129-v5-mkmlizer: Processed model rirv938/mistral_24b_bon_dataset_1200_450_v2 in 191.505s
rirv938-mistral-24b-bon-31129-v5-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-bon-31129-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-bon-31129-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/config.json
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/special_tokens_map.json
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/tokenizer_config.json
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/tokenizer.json
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/flywheel_model.1.safetensors
rirv938-mistral-24b-bon-31129-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-bon-31129-v5/flywheel_model.0.safetensors
Job rirv938-mistral-24b-bon-31129-v5-mkmlizer completed after 226.69s with status: succeeded
Stopping job with name rirv938-mistral-24b-bon-31129-v5-mkmlizer
Pipeline stage MKMLizer completed in 227.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-bon-31129-v5
Waiting for inference service rirv938-mistral-24b-bon-31129-v5 to be ready
Inference service rirv938-mistral-24b-bon-31129-v5 ready after 100.37529873847961s
Pipeline stage MKMLDeployer completed in 100.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.225368022918701s
Received healthy response to inference request in 2.5556564331054688s
Received healthy response to inference request in 2.589829444885254s
Received healthy response to inference request in 2.6458475589752197s
Received healthy response to inference request in 2.6937239170074463s
5 requests
0 failed requests
5th percentile: 2.562491035461426
10th percentile: 2.569325637817383
20th percentile: 2.582994842529297
30th percentile: 2.601033067703247
40th percentile: 2.623440313339233
50th percentile: 2.6458475589752197
60th percentile: 2.66499810218811
70th percentile: 2.684148645401001
80th percentile: 2.8000527381896974
90th percentile: 3.012710380554199
95th percentile: 3.11903920173645
99th percentile: 3.204102258682251
mean time: 2.742085075378418
Pipeline stage StressChecker completed in 15.05s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.67s
Shutdown handler de-registered
rirv938-mistral-24b-bon_31129_v5 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-bon-31129-v5-profiler
Waiting for inference service rirv938-mistral-24b-bon-31129-v5-profiler to be ready
Inference service rirv938-mistral-24b-bon-31129-v5-profiler ready after 90.4853241443634s
Pipeline stage MKMLProfilerDeployer completed in 90.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-mistral-24b-aae75232757da65f1c4fd9260f5b9c6f-deplof6w7c:/code/chaiverse_profiler_1741292659 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-mistral-24b-aae75232757da65f1c4fd9260f5b9c6f-deplof6w7c --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741292659 && 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 768 --output_tokens 64 --summary /code/chaiverse_profiler_1741292659/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2514.25s
Shutdown handler de-registered
rirv938-mistral-24b-bon_31129_v5 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-bon_31129_v5 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1