submission_id: rinen0721-mistral12b-1117_v1
developer_uid: rinen0721
best_of: 8
celo_rating: 1232.3
display_name: rinen0721-mistral12b-1117_v1
family_friendly_score: 0.5618000000000001
family_friendly_standard_error: 0.007016847725296595
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/Mistral12b-1117
latencies: [{'batch_size': 1, 'throughput': 0.6279106993300202, 'latency_mean': 1.592490358352661, 'latency_p50': 1.5891696214675903, 'latency_p90': 1.7513392925262452}, {'batch_size': 3, 'throughput': 1.1586528205701008, 'latency_mean': 2.583242371082306, 'latency_p50': 2.578278064727783, 'latency_p90': 2.8125112056732178}, {'batch_size': 5, 'throughput': 1.40982986541472, 'latency_mean': 3.534833163022995, 'latency_p50': 3.545200228691101, 'latency_p90': 3.987066626548767}, {'batch_size': 6, 'throughput': 1.4754067581272237, 'latency_mean': 4.042546565532684, 'latency_p50': 4.075942754745483, 'latency_p90': 4.539682483673095}, {'batch_size': 8, 'throughput': 1.562404597648382, 'latency_mean': 5.081499450206756, 'latency_p50': 5.092275381088257, 'latency_p90': 5.709834480285645}, {'batch_size': 10, 'throughput': 1.6027532678717218, 'latency_mean': 6.186428083181381, 'latency_p50': 6.241159081459045, 'latency_p90': 6.940048575401306}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/Mistral12b-111
model_name: rinen0721-mistral12b-1117_v1
model_num_parameters: 12772070400.0
model_repo: rinen0721/Mistral12b-1117
model_size: 13B
num_battles: 9846
num_wins: 4603
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.44
timestamp: 2024-11-19T14:29:08+00:00
us_pacific_date: 2024-11-19
win_ratio: 0.4674994921795653
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 rinen0721-mistral12b-1117-v1-mkmlizer
Waiting for job on rinen0721-mistral12b-1117-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
rinen0721-mistral12b-1117-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral12b-1117-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rinen0721-mistral12b-1117-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral12b-1117-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
rinen0721-mistral12b-1117-v1-mkmlizer: Downloaded to shared memory in 48.904s
rinen0721-mistral12b-1117-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe9e0tbxw, device:0
rinen0721-mistral12b-1117-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral12b-1117-v1-mkmlizer: quantized model in 36.549s
rinen0721-mistral12b-1117-v1-mkmlizer: Processed model rinen0721/Mistral12b-1117 in 85.453s
rinen0721-mistral12b-1117-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral12b-1117-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral12b-1117-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1
rinen0721-mistral12b-1117-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1/config.json
rinen0721-mistral12b-1117-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1/special_tokens_map.json
rinen0721-mistral12b-1117-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1/tokenizer_config.json
rinen0721-mistral12b-1117-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1/tokenizer.json
rinen0721-mistral12b-1117-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral12b-1117-v1/flywheel_model.0.safetensors
Job rinen0721-mistral12b-1117-v1-mkmlizer completed after 114.66s with status: succeeded
Stopping job with name rinen0721-mistral12b-1117-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral12b-1117-v1
Waiting for inference service rinen0721-mistral12b-1117-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
Inference service rinen0721-mistral12b-1117-v1 ready after 201.21984457969666s
Pipeline stage MKMLDeployer completed in 201.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5284130573272705s
Received healthy response to inference request in 1.7333648204803467s
Received healthy response to inference request in 1.9394402503967285s
Received healthy response to inference request in 1.7831642627716064s
Received healthy response to inference request in 1.6547467708587646s
5 requests
0 failed requests
5th percentile: 1.670470380783081
10th percentile: 1.6861939907073975
20th percentile: 1.7176412105560304
30th percentile: 1.7433247089385986
40th percentile: 1.7632444858551026
50th percentile: 1.7831642627716064
60th percentile: 1.8456746578216552
70th percentile: 1.9081850528717041
80th percentile: 2.057234811782837
90th percentile: 2.2928239345550536
95th percentile: 2.410618495941162
99th percentile: 2.5048541450500488
mean time: 1.9278258323669433
Pipeline stage StressChecker completed in 11.81s
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 2.80s
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 2.71s
Shutdown handler de-registered
rinen0721-mistral12b-1117_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 rinen0721-mistral12b-1117-v1-profiler
Waiting for inference service rinen0721-mistral12b-1117-v1-profiler to be ready
Inference service rinen0721-mistral12b-1117-v1-profiler ready after 210.49337768554688s
Pipeline stage MKMLProfilerDeployer completed in 210.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rinen0721-mistral12bdd480618f85a2333e2c138c285189a2a-deplon5g7z:/code/chaiverse_profiler_1732027125 --namespace tenant-chaiml-guanaco
kubectl exec -it rinen0721-mistral12bdd480618f85a2333e2c138c285189a2a-deplon5g7z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732027125 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1732027125/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 2700.27s
Shutdown handler de-registered
rinen0721-mistral12b-1117_v1 status is now inactive due to auto deactivation removed underperforming models