developer_uid: azuruce
submission_id: sao10k-mn-12b-lyra-v4a1_v43
model_name: sao10k-mn-12b-lyra-v4a1_v43
model_group: Sao10K/MN-12B-Lyra-v4a1
status: torndown
timestamp: 2024-11-13T21:56:59+00:00
num_battles: 8940
num_wins: 4502
celo_rating: 1251.26
family_friendly_score: 0.5816
family_friendly_standard_error: 0.006976266049972578
submission_type: basic
model_repo: Sao10K/MN-12B-Lyra-v4a1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.727129743964899, 'latency_mean': 1.3751820015907288, 'latency_p50': 1.369105339050293, 'latency_p90': 1.5370900869369506}, {'batch_size': 5, 'throughput': 2.1705767059951766, 'latency_mean': 2.2870457899570464, 'latency_p50': 2.277905225753784, 'latency_p90': 2.53346529006958}, {'batch_size': 10, 'throughput': 2.8971086920126563, 'latency_mean': 3.403344238996506, 'latency_p50': 3.4363443851470947, 'latency_p90': 3.801277422904968}, {'batch_size': 15, 'throughput': 3.1615037972475117, 'latency_mean': 4.686160035133362, 'latency_p50': 4.740007996559143, 'latency_p90': 5.306549048423767}, {'batch_size': 20, 'throughput': 3.2776926847240793, 'latency_mean': 5.998662593364716, 'latency_p50': 5.998138666152954, 'latency_p90': 6.87197859287262}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sao10k-mn-12b-lyra-v4a1_v43
is_internal_developer: True
language_model: Sao10K/MN-12B-Lyra-v4a1
model_size: 13B
ranking_group: single
throughput_3p7s: 3.02
us_pacific_date: 2024-11-13
win_ratio: 0.503579418344519
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-mn-12b-lyra-v4a1-v43-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v43-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ Version: 0.11.12 ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v43-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
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: Downloaded to shared memory in 56.989s
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw25ghc34, device:0
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: quantized model in 36.633s
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 93.622s
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43/config.json
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43/tokenizer.json
sao10k-mn-12b-lyra-v4a1-v43-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v43/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job sao10k-mn-12b-lyra-v4a1-v43-mkmlizer completed after 124.31s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v43-mkmlizer
Pipeline stage MKMLizer completed in 124.80s
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-mn-12b-lyra-v4a1-v43
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v43 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 sao10k-mn-12b-lyra-v4a1-v43 ready after 191.11052894592285s
Pipeline stage MKMLDeployer completed in 191.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.529038667678833s
Received healthy response to inference request in 1.7708203792572021s
Received healthy response to inference request in 1.2508838176727295s
Received healthy response to inference request in 2.306788921356201s
Received healthy response to inference request in 1.1270873546600342s
5 requests
0 failed requests
5th percentile: 1.1518466472625732
10th percentile: 1.1766059398651123
20th percentile: 1.2261245250701904
30th percentile: 1.3548711299896241
40th percentile: 1.5628457546234131
50th percentile: 1.7708203792572021
60th percentile: 1.9852077960968018
70th percentile: 2.1995952129364014
80th percentile: 2.3512388706207275
90th percentile: 2.4401387691497805
95th percentile: 2.4845887184143067
99th percentile: 2.5201486778259277
mean time: 1.796923828125
Pipeline stage StressChecker completed in 10.74s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.25s
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
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %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 2.18s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v43 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 2029.81s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v43 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v43 status is now torndown due to DeploymentManager action