developer_uid: stark2000s
submission_id: stark2000s-10-14-reproduction_v1
model_name: stark2000s-10-14-reproduction_v1
model_group: stark2000s/10_14_reprodu
status: inactive
timestamp: 2024-12-19T08:25:51+00:00
num_battles: 14089
num_wins: 7010
celo_rating: 1260.25
family_friendly_score: 0.5873999999999999
family_friendly_standard_error: 0.006962201376001702
submission_type: basic
model_repo: stark2000s/10_14_reproduction
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6069966459643087, 'latency_mean': 1.6473865294456482, 'latency_p50': 1.654695987701416, 'latency_p90': 1.807360792160034}, {'batch_size': 3, 'throughput': 1.1185522766874068, 'latency_mean': 2.670513015985489, 'latency_p50': 2.6811145544052124, 'latency_p90': 2.9382069587707518}, {'batch_size': 5, 'throughput': 1.3653382977958288, 'latency_mean': 3.643159489631653, 'latency_p50': 3.655635118484497, 'latency_p90': 3.991709280014038}, {'batch_size': 6, 'throughput': 1.4339816722868872, 'latency_mean': 4.165138053894043, 'latency_p50': 4.121568441390991, 'latency_p90': 4.712480235099792}, {'batch_size': 8, 'throughput': 1.504836842303008, 'latency_mean': 5.287280535697937, 'latency_p50': 5.279812574386597, 'latency_p90': 5.890802264213562}, {'batch_size': 10, 'throughput': 1.5467682039140602, 'latency_mean': 6.4076953291893, 'latency_p50': 6.318491339683533, 'latency_p90': 7.3019571781158445}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: stark2000s-10-14-reproduction_v1
is_internal_developer: False
language_model: stark2000s/10_14_reproduction
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2024-12-19
win_ratio: 0.4975512811413159
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}
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}
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 stark2000s-10-14-reproduction-v1-mkmlizer
Waiting for job on stark2000s-10-14-reproduction-v1-mkmlizer to finish
stark2000s-10-14-reproduction-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-10-14-reproduction-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║                                                                     ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║                                                                     ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║                                                                     ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
stark2000s-10-14-reproduction-v1-mkmlizer: ║                                                                     ║
stark2000s-10-14-reproduction-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-10-14-reproduction-v1-mkmlizer: Downloaded to shared memory in 84.354s
stark2000s-10-14-reproduction-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwiy01ohw, device:0
stark2000s-10-14-reproduction-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-10-14-reproduction-v1-mkmlizer: quantized model in 41.157s
stark2000s-10-14-reproduction-v1-mkmlizer: Processed model stark2000s/10_14_reproduction in 125.511s
stark2000s-10-14-reproduction-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-10-14-reproduction-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-10-14-reproduction-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1
stark2000s-10-14-reproduction-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1/config.json
stark2000s-10-14-reproduction-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1/special_tokens_map.json
stark2000s-10-14-reproduction-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1/tokenizer_config.json
stark2000s-10-14-reproduction-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1/tokenizer.json
stark2000s-10-14-reproduction-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-10-14-reproduction-v1/flywheel_model.0.safetensors
Job stark2000s-10-14-reproduction-v1-mkmlizer completed after 155.34s with status: succeeded
Stopping job with name stark2000s-10-14-reproduction-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.83s
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 stark2000s-10-14-reproduction-v1
Waiting for inference service stark2000s-10-14-reproduction-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
Inference service stark2000s-10-14-reproduction-v1 ready after 251.33759331703186s
Pipeline stage MKMLDeployer completed in 251.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.1619596481323242s
Received healthy response to inference request in 1.0810480117797852s
Received healthy response to inference request in 1.6624293327331543s
Received healthy response to inference request in 1.3645052909851074s
Received healthy response to inference request in 1.8386495113372803s
5 requests
0 failed requests
5th percentile: 1.0972303390502929
10th percentile: 1.1134126663208008
20th percentile: 1.1457773208618165
30th percentile: 1.2024687767028808
40th percentile: 1.283487033843994
50th percentile: 1.3645052909851074
60th percentile: 1.483674907684326
70th percentile: 1.602844524383545
80th percentile: 1.6976733684539795
90th percentile: 1.7681614398956298
95th percentile: 1.803405475616455
99th percentile: 1.8316007041931153
mean time: 1.4217183589935303
Pipeline stage StressChecker completed in 8.48s
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 2.50s
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 2.27s
Shutdown handler de-registered
stark2000s-10-14-reproduction_v1 status is now deployed due to DeploymentManager action
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 3254.16s
Shutdown handler de-registered
stark2000s-10-14-reproduction_v1 status is now inactive due to auto deactivation removed underperforming models