developer_uid: Sao10K
submission_id: sao10k-l3-1-8b-steertama-run2_v1
model_name: Steertama-L3-run2
model_group: Sao10K/L3.1-8B-Steertama
status: inactive
timestamp: 2024-12-03T16:02:34+00:00
num_battles: 15278
num_wins: 7269
celo_rating: 1243.22
family_friendly_score: 0.5731999999999999
family_friendly_standard_error: 0.00699488041355962
submission_type: basic
model_repo: Sao10K/L3.1-8B-Steertama-run2
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8573010708401274, 'latency_mean': 1.1663733911514282, 'latency_p50': 1.164633870124817, 'latency_p90': 1.2858581781387328}, {'batch_size': 4, 'throughput': 1.8373501391229703, 'latency_mean': 2.1730740129947663, 'latency_p50': 2.181992530822754, 'latency_p90': 2.406327486038208}, {'batch_size': 5, 'throughput': 1.9874018327999055, 'latency_mean': 2.5063758289813993, 'latency_p50': 2.519634485244751, 'latency_p90': 2.8375303030014036}, {'batch_size': 8, 'throughput': 2.1967068994699255, 'latency_mean': 3.6181919300556182, 'latency_p50': 3.6220223903656006, 'latency_p90': 4.029410552978516}, {'batch_size': 10, 'throughput': 2.230821947618406, 'latency_mean': 4.454635190963745, 'latency_p50': 4.490024209022522, 'latency_p90': 5.019030380249023}, {'batch_size': 12, 'throughput': 2.2792501245440575, 'latency_mean': 5.21784082531929, 'latency_p50': 5.240201830863953, 'latency_p90': 5.904541063308716}, {'batch_size': 15, 'throughput': 2.3019021949291267, 'latency_mean': 6.427517811059952, 'latency_p50': 6.5474008321762085, 'latency_p90': 7.10434205532074}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: Steertama-L3-run2
is_internal_developer: False
language_model: Sao10K/L3.1-8B-Steertama-run2
model_size: 8B
ranking_group: single
throughput_3p7s: 2.22
us_pacific_date: 2024-12-03
win_ratio: 0.4757821704411572
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '\nYou:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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 sao10k-l3-1-8b-steertama-run2-v1-mkmlizer
Waiting for job on sao10k-l3-1-8b-steertama-run2-v1-mkmlizer to finish
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
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: ║                                                                     ║
sao10k-l3-1-8b-steertama-run2-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
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
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: Downloaded to shared memory in 36.642s
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4ze4a2gk, device:0
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: quantized model in 27.625s
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: Processed model Sao10K/L3.1-8B-Steertama-run2 in 64.267s
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-1-8b-steertama-run2-v1
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-1-8b-steertama-run2-v1/config.json
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-1-8b-steertama-run2-v1/special_tokens_map.json
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-1-8b-steertama-run2-v1/tokenizer_config.json
sao10k-l3-1-8b-steertama-run2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-1-8b-steertama-run2-v1/tokenizer.json
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
Job sao10k-l3-1-8b-steertama-run2-v1-mkmlizer completed after 104.01s with status: succeeded
Stopping job with name sao10k-l3-1-8b-steertama-run2-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-l3-1-8b-steertama-run2-v1
Waiting for inference service sao10k-l3-1-8b-steertama-run2-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
Inference service sao10k-l3-1-8b-steertama-run2-v1 ready after 140.8970184326172s
Pipeline stage MKMLDeployer completed in 141.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9559717178344727s
Received healthy response to inference request in 1.2900364398956299s
Received healthy response to inference request in 1.2606253623962402s
Received healthy response to inference request in 1.2665538787841797s
Received healthy response to inference request in 1.6736087799072266s
5 requests
0 failed requests
5th percentile: 1.2618110656738282
10th percentile: 1.262996768951416
20th percentile: 1.2653681755065918
30th percentile: 1.2712503910064696
40th percentile: 1.2806434154510498
50th percentile: 1.2900364398956299
60th percentile: 1.4434653759002685
70th percentile: 1.596894311904907
80th percentile: 1.7300813674926758
90th percentile: 1.8430265426635741
95th percentile: 1.8994991302490234
99th percentile: 1.944677200317383
mean time: 1.48935923576355
Pipeline stage StressChecker completed in 9.50s
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 2.52s
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 2.41s
Shutdown handler de-registered
sao10k-l3-1-8b-steertama-run2_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-l3-1-8b-steertama-run2-v1-profiler
Waiting for inference service sao10k-l3-1-8b-steertama-run2-v1-profiler to be ready
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 2468.97s
Shutdown handler de-registered
sao10k-l3-1-8b-steertama-run2_v1 status is now inactive due to auto deactivation removed underperforming models