submission_id: cycy233-l3-p-v2_v1
developer_uid: shiroe40
alignment_samples: 12819
alignment_score: -0.3255256095095162
best_of: 16
celo_rating: 1227.92
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-v2
latencies: [{'batch_size': 1, 'throughput': 0.9025490898828723, 'latency_mean': 1.1079128730297088, 'latency_p50': 1.097986102104187, 'latency_p90': 1.2378568410873414}, {'batch_size': 3, 'throughput': 1.586044713568985, 'latency_mean': 1.884366592168808, 'latency_p50': 1.8858022689819336, 'latency_p90': 2.0808999300003053}, {'batch_size': 5, 'throughput': 1.8388757055475322, 'latency_mean': 2.705629924535751, 'latency_p50': 2.694033980369568, 'latency_p90': 3.044875454902649}, {'batch_size': 6, 'throughput': 1.885612442149437, 'latency_mean': 3.1657810842990877, 'latency_p50': 3.1736550331115723, 'latency_p90': 3.5678307056427}, {'batch_size': 8, 'throughput': 1.9740006575901363, 'latency_mean': 4.025255389213562, 'latency_p50': 4.02961266040802, 'latency_p90': 4.541726160049438}, {'batch_size': 10, 'throughput': 1.9580800040858068, 'latency_mean': 5.058344192504883, 'latency_p50': 5.075490474700928, 'latency_p90': 5.7182636737823485}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v2
model_size: 8B
num_battles: 12814
num_wins: 6117
propriety_score: 0.706280193236715
propriety_total_count: 1035.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.96
timestamp: 2024-09-11T02:55:55+00:00
us_pacific_date: 2024-09-10
win_ratio: 0.4773685031996254
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-v2-v1-mkmlizer
Waiting for job on cycy233-l3-p-v2-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-p-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v2-v1-mkmlizer: Downloaded to shared memory in 39.467s
cycy233-l3-p-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc4nfszs3, device:0
cycy233-l3-p-v2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v2-v1-mkmlizer: quantized model in 25.257s
cycy233-l3-p-v2-v1-mkmlizer: Processed model cycy233/L3-p-v2 in 64.724s
cycy233-l3-p-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v2-v1
cycy233-l3-p-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-v1/config.json
cycy233-l3-p-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-v1/tokenizer_config.json
cycy233-l3-p-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v2-v1/special_tokens_map.json
cycy233-l3-p-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v2-v1/tokenizer.json
cycy233-l3-p-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v2-v1/flywheel_model.0.safetensors
cycy233-l3-p-v2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.57it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 72.09it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 93.82it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 94.93it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 103.23it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 97.11it/s] 
Loading 0:  29%|██▊       | 83/291 [00:01<00:07, 28.06it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:06, 31.59it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 41.29it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 50.24it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 63.48it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 70.31it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 82.37it/s]
Loading 0:  58%|█████▊    | 169/291 [00:02<00:01, 85.13it/s]
Loading 0:  63%|██████▎   | 184/291 [00:02<00:01, 94.52it/s]
Loading 0:  67%|██████▋   | 195/291 [00:03<00:03, 29.89it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 35.16it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 45.95it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 54.41it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 55.35it/s]
Loading 0:  88%|████████▊ | 256/291 [00:04<00:00, 68.00it/s]
Loading 0:  92%|█████████▏| 268/291 [00:04<00:00, 72.98it/s]
Loading 0:  97%|█████████▋| 283/291 [00:04<00:00, 82.43it/s]
                                                            

Job cycy233-l3-p-v2-v1-mkmlizer completed after 83.61s with status: succeeded
Stopping job with name cycy233-l3-p-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v2-v1
Waiting for inference service cycy233-l3-p-v2-v1 to be ready
Inference service cycy233-l3-p-v2-v1 ready after 160.60012674331665s
Pipeline stage MKMLDeployer completed in 160.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.055384874343872s
Received healthy response to inference request in 1.8341996669769287s
Received healthy response to inference request in 1.582505226135254s
Received healthy response to inference request in 1.7569398880004883s
Received healthy response to inference request in 1.5035350322723389s
5 requests
0 failed requests
5th percentile: 1.5193290710449219
10th percentile: 1.5351231098175049
20th percentile: 1.566711187362671
30th percentile: 1.6173921585083009
40th percentile: 1.6871660232543946
50th percentile: 1.7569398880004883
60th percentile: 1.7878437995910645
70th percentile: 1.8187477111816406
80th percentile: 1.8784367084503175
90th percentile: 1.9669107913970947
95th percentile: 2.0111478328704835
99th percentile: 2.046537466049194
mean time: 1.7465129375457764
Pipeline stage StressChecker completed in 9.28s
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 4.68s
Shutdown handler de-registered
cycy233-l3-p-v2_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-v2-v1-profiler
Waiting for inference service cycy233-l3-p-v2-v1-profiler to be ready
Inference service cycy233-l3-p-v2-v1-profiler ready after 160.46148800849915s
Pipeline stage MKMLProfilerDeployer completed in 160.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v2-v1-profiler-predictor-00001-deployment-54dfdc5b:/code/chaiverse_profiler_1726023827 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v2-v1-profiler-predictor-00001-deployment-54dfdc5b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726023827 && 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_1726023827/summary.json'
kubectl exec -it cycy233-l3-p-v2-v1-profiler-predictor-00001-deployment-54dfdc5b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726023827/summary.json'
Pipeline stage MKMLProfilerRunner completed in 771.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v2-v1-profiler is running
Tearing down inference service cycy233-l3-p-v2-v1-profiler
Service cycy233-l3-p-v2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.97s
Shutdown handler de-registered
cycy233-l3-p-v2_v1 status is now inactive due to auto deactivation removed underperforming models