developer_uid: huohuo12
submission_id: yamatazen-ayla-light-12b-v2_v12
model_name: yamatazen-ayla-light-12b-v2_v2
model_group: yamatazen/Ayla-Light-12B
status: torndown
timestamp: 2025-02-26T09:50:52+00:00
num_battles: 6814
num_wins: 3282
celo_rating: 1251.51
family_friendly_score: 0.5598000000000001
family_friendly_standard_error: 0.007020312813543283
submission_type: basic
model_repo: yamatazen/Ayla-Light-12B-v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6052169400852156, 'latency_mean': 1.6522298324108124, 'latency_p50': 1.6547331809997559, 'latency_p90': 1.819441556930542}, {'batch_size': 3, 'throughput': 1.1068276370879224, 'latency_mean': 2.7048867309093474, 'latency_p50': 2.6994354724884033, 'latency_p90': 2.9414071798324586}, {'batch_size': 5, 'throughput': 1.3378207320716604, 'latency_mean': 3.7178740298748014, 'latency_p50': 3.731407642364502, 'latency_p90': 4.13978111743927}, {'batch_size': 6, 'throughput': 1.4135907992801542, 'latency_mean': 4.220178679227829, 'latency_p50': 4.254408478736877, 'latency_p90': 4.764702200889587}, {'batch_size': 8, 'throughput': 1.4800213774545434, 'latency_mean': 5.366029566526413, 'latency_p50': 5.346720814704895, 'latency_p90': 6.109363675117493}, {'batch_size': 10, 'throughput': 1.505013496299626, 'latency_mean': 6.600710562467575, 'latency_p50': 6.638326048851013, 'latency_p90': 7.364141821861267}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: yamatazen-ayla-light-12b-v2_v2
is_internal_developer: False
language_model: yamatazen/Ayla-Light-12B-v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-02-26
win_ratio: 0.4816554153213971
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 70, 'presence_penalty': 0.35, 'frequency_penalty': 0.2, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, '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 yamatazen-ayla-light-12b-v2-v12-mkmlizer
Waiting for job on yamatazen-ayla-light-12b-v2-v12-mkmlizer to finish
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ _____ __ __ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ /___/ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ Version: 0.12.8 ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ https://mk1.ai ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ The license key for the current software has been verified as ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ belonging to: ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ Chai Research Corp. ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-ayla-light-12b-v2-v12-mkmlizer: Downloaded to shared memory in 32.060s
yamatazen-ayla-light-12b-v2-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_zyt14r8, device:0
yamatazen-ayla-light-12b-v2-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-ayla-light-12b-v2-v12-mkmlizer: quantized model in 36.295s
yamatazen-ayla-light-12b-v2-v12-mkmlizer: Processed model yamatazen/Ayla-Light-12B-v2 in 68.356s
yamatazen-ayla-light-12b-v2-v12-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-12b-v2-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-12b-v2-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v12
yamatazen-ayla-light-12b-v2-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v12/config.json
yamatazen-ayla-light-12b-v2-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v12/special_tokens_map.json
yamatazen-ayla-light-12b-v2-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v12/tokenizer_config.json
yamatazen-ayla-light-12b-v2-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v12/tokenizer.json
Job yamatazen-ayla-light-12b-v2-v12-mkmlizer completed after 106.88s with status: succeeded
Stopping job with name yamatazen-ayla-light-12b-v2-v12-mkmlizer
Pipeline stage MKMLizer completed in 107.34s
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 yamatazen-ayla-light-12b-v2-v12
Waiting for inference service yamatazen-ayla-light-12b-v2-v12 to be ready
Failed to get response for submission nischaydnk-exp16-mistra_31861_v2: HTTPConnectionPool(host='nischaydnk-exp16-mistra-31861-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp16-mistra_31861_v2: HTTPConnectionPool(host='nischaydnk-exp16-mistra-31861-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service yamatazen-ayla-light-12b-v2-v12 ready after 261.04300022125244s
Pipeline stage MKMLDeployer completed in 261.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.209942579269409s
Received healthy response to inference request in 1.5150847434997559s
Received healthy response to inference request in 1.5078544616699219s
Received healthy response to inference request in 1.696030616760254s
Received healthy response to inference request in 1.4016335010528564s
5 requests
0 failed requests
5th percentile: 1.4228776931762694
10th percentile: 1.4441218852996827
20th percentile: 1.4866102695465089
30th percentile: 1.5093005180358887
40th percentile: 1.5121926307678222
50th percentile: 1.5150847434997559
60th percentile: 1.587463092803955
70th percentile: 1.6598414421081542
80th percentile: 1.798813009262085
90th percentile: 2.0043777942657472
95th percentile: 2.107160186767578
99th percentile: 2.189386100769043
mean time: 1.6661091804504395
Pipeline stage StressChecker completed in 9.60s
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 0.64s
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 0.64s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v12 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service yamatazen-ayla-light-12b-v2-v12-profiler
Waiting for inference service yamatazen-ayla-light-12b-v2-v12-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 2560.26s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v12 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-12b-v2_v12 status is now torndown due to DeploymentManager action