submission_id: cycy233-l3-p-v2_v1
developer_uid: shiroe40
best_of: 16
celo_rating: 1228.1
display_name: auto
family_friendly_score: 0.0
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
ranking_group: single
status: torndown
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
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
cycy233-l3-p-v2_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 3.38s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
admin requested tearing down of cycy233-l3-p-v2_v1
Pipeline stage MKMLDeleter completed in 3.78s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c2_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.70s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v3-c1_v1
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c3_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
run pipeline %s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 3.51s
Running pipeline stage MKMLDeleter
Pipeline stage MKMLDeleter completed in 3.26s
admin requested tearing down of cycy233-l3-p-v3-c2_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 3.42s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
admin requested tearing down of cycy233-l3-p-v3-c3_v1
Pipeline stage MKMLDeleter completed in 3.76s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.26s
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v1-c4_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.29s
Running pipeline stage MKMLModelDeleter
run pipeline %s
run pipeline stage %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v3-c4_v1
cycy233-l3-p-v1-c4_v3 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.72s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLModelDeleter
run pipeline %s
Pipeline stage MKMLDeleter completed in 3.21s
Shutdown handler not registered because Python interpreter is not running in the main thread
cycy233-l3-p-v1-c4_v4 status is now torndown due to DeploymentManager action
admin requested tearing down of cycy233-l3-p-v4-c1_v1
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 3.27s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v4-c1_v2
Shutdown handler de-registered
cycy233-l3-p-v2-c1_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.54s
Pipeline stage MKMLModelDeleter completed in 3.50s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 3.04s
admin requested tearing down of cycy233-l3-p-v4-c2_v2
cycy233-l3-p-v2-c2_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.33s
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler de-registered
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
admin requested tearing down of cycy233-l3-p-v4-c2_v3
cycy233-l3-p-v2-c3_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.45s
Pipeline stage MKMLModelDeleter completed in 3.37s
Pipeline stage %s skipped, reason=%s
run pipeline %s
cycy233-l3-p-v2-c4_v2 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v4-c3_v1
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 3.68s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 3.53s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-l3-p-v4-c4_v1
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 3.53s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-l3-p-v4-c4_v1
cycy233-l3-p-v2_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.19s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
cycy233-l3-p-v2-c4_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 5.76s
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
admin requested tearing down of cycy233-l3-p-v4-c4_v1
Pipeline stage %s skipped, reason=%s
cycy233-l3-p-v2_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 6.14s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
run pipeline stage %s
run pipeline %s