cycy233-l3-p-v1-c3

submission_id: cycy233-l3-p-v1-c3_v1

developer_uid: shiroe40

alignment_samples: 11162

alignment_score: -0.20197071058162003

best_of: 16

celo_rating: 1255.54

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-v1-c3

latencies: [{'batch_size': 1, 'throughput': 0.9140784430455685, 'latency_mean': 1.093916379213333, 'latency_p50': 1.0809693336486816, 'latency_p90': 1.2149394035339356}, {'batch_size': 4, 'throughput': 1.7834085712580245, 'latency_mean': 2.2341138994693757, 'latency_p50': 2.2172439098358154, 'latency_p90': 2.5033737897872923}, {'batch_size': 5, 'throughput': 1.8892946634127448, 'latency_mean': 2.6291275596618653, 'latency_p50': 2.6508848667144775, 'latency_p90': 2.9075836896896363}, {'batch_size': 8, 'throughput': 1.9852325543323655, 'latency_mean': 4.000191297531128, 'latency_p50': 4.044477462768555, 'latency_p90': 4.496584272384643}, {'batch_size': 10, 'throughput': 2.0505362219461762, 'latency_mean': 4.828626983165741, 'latency_p50': 4.853576183319092, 'latency_p90': 5.472363233566284}, {'batch_size': 12, 'throughput': 2.023611338329398, 'latency_mean': 5.852564693689346, 'latency_p50': 5.823601603507996, 'latency_p90': 6.843926000595093}, {'batch_size': 15, 'throughput': 2.0331659990304236, 'latency_mean': 7.229267910718918, 'latency_p50': 7.359904170036316, 'latency_p90': 8.07015881538391}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v1-c3

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v1-c3

model_size: 8B

num_battles: 11162

num_wins: 5748

propriety_score: 0.7188434695912264

propriety_total_count: 1003.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.98

timestamp: 2024-09-09T03:22:56+00:00

us_pacific_date: 2024-09-08

win_ratio: 0.5149614764379143

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-v1-c3-v1-mkmlizer
Waiting for job on cycy233-l3-p-v1-c3-v1-mkmlizer to finish
cycy233-l3-p-v1-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v1-c3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v1-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v1-c3-v1-mkmlizer: Downloaded to shared memory in 42.653s
cycy233-l3-p-v1-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8ohat0mm, device:0
cycy233-l3-p-v1-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v1-c3-v1-mkmlizer: quantized model in 25.343s
cycy233-l3-p-v1-c3-v1-mkmlizer: Processed model cycy233/L3-p-v1-c3 in 67.996s
cycy233-l3-p-v1-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v1-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v1-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1
cycy233-l3-p-v1-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1/config.json
cycy233-l3-p-v1-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1/special_tokens_map.json
cycy233-l3-p-v1-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1/tokenizer_config.json
cycy233-l3-p-v1-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1/tokenizer.json
cycy233-l3-p-v1-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v1-c3-v1/flywheel_model.0.safetensors
cycy233-l3-p-v1-c3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.52it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 73.87it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 84.89it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 83.65it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 82.30it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 83.42it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 83.30it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 84.27it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:08, 22.83it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 29.24it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 36.25it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 43.32it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.84it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 56.12it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 62.75it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 68.29it/s]
Loading 0:  55%|█████▍    | 160/291 [00:02<00:01, 71.91it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 73.75it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 76.01it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 22.22it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 32.96it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 40.82it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 48.79it/s]
Loading 0:  80%|████████  | 233/291 [00:04<00:01, 54.45it/s]
Loading 0:  83%|████████▎ | 242/291 [00:04<00:00, 60.37it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 70.82it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 74.36it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 76.11it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 78.76it/s]
                                                            
Job cycy233-l3-p-v1-c3-v1-mkmlizer completed after 136.41s with status: succeeded
Stopping job with name cycy233-l3-p-v1-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.18s
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-v1-c3-v1
Waiting for inference service cycy233-l3-p-v1-c3-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-p-v1-c3-v1 ready after 150.42672657966614s
Pipeline stage MKMLDeployer completed in 151.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6557774543762207s
Received healthy response to inference request in 1.7169334888458252s
Received healthy response to inference request in 1.6011652946472168s
Received healthy response to inference request in 1.9463167190551758s
Received healthy response to inference request in 2.3145933151245117s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
5 requests
0 failed requests
5th percentile: 1.6243189334869386
10th percentile: 1.6474725723266601
20th percentile: 1.6937798500061034
30th percentile: 1.7628101348876952
40th percentile: 1.8545634269714355
50th percentile: 1.9463167190551758
60th percentile: 2.09362735748291
70th percentile: 2.2409379959106444
80th percentile: 2.3828301429748535
90th percentile: 2.519303798675537
95th percentile: 2.587540626525879
99th percentile: 2.6421300888061525
mean time: 2.04695725440979
Pipeline stage StressChecker completed in 11.27s
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 4.50s
Shutdown handler de-registered
cycy233-l3-p-v1-c3_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-p-v1-c3-v1-profiler
Waiting for inference service cycy233-l3-p-v1-c3-v1-profiler to be ready
Inference service cycy233-l3-p-v1-c3-v1-profiler ready after 150.35350012779236s
Pipeline stage MKMLProfilerDeployer completed in 150.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v1-c3-v1-profiler-predictor-00001-deployment-l4xxp:/code/chaiverse_profiler_1725852670 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v1-c3-v1-profiler-predictor-00001-deployment-l4xxp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725852670 && 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_1725852670/summary.json'
kubectl exec -it cycy233-l3-p-v1-c3-v1-profiler-predictor-00001-deployment-l4xxp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725852670/summary.json'
Pipeline stage MKMLProfilerRunner completed in 837.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v1-c3-v1-profiler is running
Tearing down inference service cycy233-l3-p-v1-c3-v1-profiler
Service cycy233-l3-p-v1-c3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.76s
Shutdown handler de-registered
cycy233-l3-p-v1-c3_v1 status is now inactive due to auto deactivation removed underperforming models