submission_id: zonemercy-vingt-deux-v0-1e5_v24
developer_uid: chai_backend_admin
best_of: 1
celo_rating: 1198.35
display_name: temp-4
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.1235, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v0-1e5
latencies: [{'batch_size': 1, 'throughput': 0.40012468618573854, 'latency_mean': 2.4991539561748506, 'latency_p50': 2.5119545459747314, 'latency_p90': 2.7572992563247682}, {'batch_size': 3, 'throughput': 0.8616865802283796, 'latency_mean': 3.4677988076210022, 'latency_p50': 3.4435088634490967, 'latency_p90': 3.825423216819763}, {'batch_size': 5, 'throughput': 1.1641869727071845, 'latency_mean': 4.277625213861466, 'latency_p50': 4.259309411048889, 'latency_p90': 4.752777242660523}, {'batch_size': 6, 'throughput': 1.2713533982017373, 'latency_mean': 4.673040015697479, 'latency_p50': 4.699426174163818, 'latency_p90': 5.184358930587768}, {'batch_size': 8, 'throughput': 1.457632439041544, 'latency_mean': 5.455273699760437, 'latency_p50': 5.4653366804122925, 'latency_p90': 6.110021090507507}, {'batch_size': 10, 'throughput': 1.576262471145993, 'latency_mean': 6.284562064409256, 'latency_p50': 6.234900951385498, 'latency_p90': 7.047063136100769}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-v0-
model_name: temp-4
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-v0-1e5
model_size: 22B
num_battles: 18098
num_wins: 7994
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.97
timestamp: 2024-09-23T18:22:59+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.44170626588573325
Download Preference Data
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 zonemercy-vingt-deux-v0-1e5-v24-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v24-mkmlizer to finish
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: Downloaded to shared memory in 47.056s
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwmlh1q_o, device:0
zonemercy-vingt-deux-v0-1e5-v24-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
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
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v24
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v24/config.json
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v24/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v24/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v24/tokenizer.json
Job zonemercy-vingt-deux-v0-1e5-v24-mkmlizer completed after 156.95s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v24-mkmlizer
Pipeline stage MKMLizer completed in 160.70s
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 zonemercy-vingt-deux-v0-1e5-v24
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v24 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
Inference service zonemercy-vingt-deux-v0-1e5-v24 ready after 203.22640299797058s
Pipeline stage MKMLDeployer completed in 207.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0029022693634033s
Received healthy response to inference request in 2.0255093574523926s
Received healthy response to inference request in 2.0487709045410156s
Received healthy response to inference request in 2.089367628097534s
Received healthy response to inference request in 1.9152352809906006s
5 requests
0 failed requests
5th percentile: 1.9327686786651612
10th percentile: 1.9503020763397216
20th percentile: 1.9853688716888427
30th percentile: 2.007423686981201
40th percentile: 2.016466522216797
50th percentile: 2.0255093574523926
60th percentile: 2.034813976287842
70th percentile: 2.044118595123291
80th percentile: 2.0568902492523193
90th percentile: 2.0731289386749268
95th percentile: 2.0812482833862305
99th percentile: 2.0877437591552734
mean time: 2.016357088088989
Pipeline stage StressChecker completed in 12.02s
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 7.38s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v24 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 0.13s
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 zonemercy-vingt-deux-v0-1e5-v24-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v24-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v24-profiler ready after 200.48445081710815s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux5e844cd3fc45b4d645b63cce82918769-deplo787c7:/code/chaiverse_profiler_1727116409 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux5e844cd3fc45b4d645b63cce82918769-deplo787c7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727116409 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727116409/summary.json'
kubectl exec -it zonemercy-vingt-deux5e844cd3fc45b4d645b63cce82918769-deplo787c7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727116409/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1330.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v24-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v24-profiler
Service zonemercy-vingt-deux-v0-1e5-v24-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v24 status is now inactive due to auto deactivation removed underperforming models
Deleting key zonemercy-vingt-deux-v0-1e5-v25/tokenizer_config.json from bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5_v24 status is now torndown due to DeploymentManager action