submission_id: cycy233-l3-p-v4-c1_v1
developer_uid: shiroe40
alignment_samples: 10383
alignment_score: 0.25439060306365185
best_of: 16
celo_rating: 1249.87
display_name: auto
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}
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-p-v4-c1
latencies: [{'batch_size': 1, 'throughput': 0.9041786756678538, 'latency_mean': 1.105915765762329, 'latency_p50': 1.1005918979644775, 'latency_p90': 1.2423787117004395}, {'batch_size': 4, 'throughput': 1.8089813169171738, 'latency_mean': 2.200504150390625, 'latency_p50': 2.1787039041519165, 'latency_p90': 2.524139165878296}, {'batch_size': 5, 'throughput': 1.8742952826490942, 'latency_mean': 2.6530987417697904, 'latency_p50': 2.659836173057556, 'latency_p90': 2.9565185546875}, {'batch_size': 8, 'throughput': 1.9943646212768293, 'latency_mean': 3.984754989147186, 'latency_p50': 3.992251992225647, 'latency_p90': 4.483180594444275}, {'batch_size': 10, 'throughput': 2.01448827925604, 'latency_mean': 4.912209231853485, 'latency_p50': 4.876551985740662, 'latency_p90': 5.57101674079895}, {'batch_size': 12, 'throughput': 2.0235987682261882, 'latency_mean': 5.848695582151413, 'latency_p50': 5.8558759689331055, 'latency_p90': 6.676494932174682}, {'batch_size': 15, 'throughput': 2.0161133801517934, 'latency_mean': 7.295335454940796, 'latency_p50': 7.400796890258789, 'latency_p90': 8.184788537025451}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v4-c1
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v4-c1
model_size: 8B
num_battles: 10383
num_wins: 5267
propriety_score: 0.7147401908801697
propriety_total_count: 943.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.99
timestamp: 2024-09-13T02:19:50+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.5072715014928249
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 cycy233-l3-p-v4-c1-v1-mkmlizer
Waiting for job on cycy233-l3-p-v4-c1-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
cycy233-l3-p-v4-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v4-c1-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v4-c1-v1-mkmlizer: Downloaded to shared memory in 35.423s
cycy233-l3-p-v4-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcjbw2grc, device:0
cycy233-l3-p-v4-c1-v1-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
cycy233-l3-p-v4-c1-v1-mkmlizer: quantized model in 25.847s
cycy233-l3-p-v4-c1-v1-mkmlizer: Processed model cycy233/L3-p-v4-c1 in 61.271s
cycy233-l3-p-v4-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v4-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v4-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v4-c1-v1
cycy233-l3-p-v4-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c1-v1/config.json
cycy233-l3-p-v4-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c1-v1/special_tokens_map.json
cycy233-l3-p-v4-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c1-v1/tokenizer_config.json
cycy233-l3-p-v4-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c1-v1/tokenizer.json
Job cycy233-l3-p-v4-c1-v1-mkmlizer completed after 86.0s with status: succeeded
Stopping job with name cycy233-l3-p-v4-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v4-c1-v1
Waiting for inference service cycy233-l3-p-v4-c1-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
Inference service cycy233-l3-p-v4-c1-v1 ready after 161.05349040031433s
Pipeline stage MKMLDeployer completed in 161.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.134166717529297s
Received healthy response to inference request in 1.6631379127502441s
Received healthy response to inference request in 1.7102432250976562s
Received healthy response to inference request in 2.1853885650634766s
Received healthy response to inference request in 1.7119512557983398s
5 requests
0 failed requests
5th percentile: 1.6725589752197265
10th percentile: 1.681980037689209
20th percentile: 1.7008221626281739
30th percentile: 1.710584831237793
40th percentile: 1.7112680435180665
50th percentile: 1.7119512557983398
60th percentile: 1.8808374404907227
70th percentile: 2.0497236251831055
80th percentile: 2.144411087036133
90th percentile: 2.1648998260498047
95th percentile: 2.1751441955566406
99th percentile: 2.1833396911621095
mean time: 1.8809775352478026
Pipeline stage StressChecker completed in 10.25s
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 6.29s
Shutdown handler de-registered
cycy233-l3-p-v4-c1_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v4-c1-v1-profiler
Waiting for inference service cycy233-l3-p-v4-c1-v1-profiler to be ready
Inference service cycy233-l3-p-v4-c1-v1-profiler ready after 170.40005493164062s
Pipeline stage MKMLProfilerDeployer completed in 170.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v4-c1-v1-profiler-predictor-00001-deployment-6ts5v:/code/chaiverse_profiler_1726194474 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v4-c1-v1-profiler-predictor-00001-deployment-6ts5v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726194474 && python profiles.py profile --best_of_n 16 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726194474/summary.json'
kubectl exec -it cycy233-l3-p-v4-c1-v1-profiler-predictor-00001-deployment-6ts5v --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726194474/summary.json'
Pipeline stage MKMLProfilerRunner completed in 842.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v4-c1-v1-profiler is running
Tearing down inference service cycy233-l3-p-v4-c1-v1-profiler
Service cycy233-l3-p-v4-c1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.03s
Shutdown handler de-registered
cycy233-l3-p-v4-c1_v1 status is now inactive due to auto deactivation removed underperforming models