submission_id: sicarius-prototyping-var_8179_v1
developer_uid: SicariusSicariiStuff
alignment_samples: 11510
alignment_score: 0.4949159932156733
best_of: 2
celo_rating: 1183.12
display_name: sicarius-prototyping-var_8179_v1
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 2, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Sicarius-Prototyping/Variety_RP_Alpha
latencies: [{'batch_size': 1, 'throughput': 1.027419796642479, 'latency_mean': 0.973231338262558, 'latency_p50': 0.979394793510437, 'latency_p90': 1.0805418729782104}, {'batch_size': 5, 'throughput': 3.321748328333906, 'latency_mean': 1.4930519664287567, 'latency_p50': 1.506403923034668, 'latency_p90': 1.6498680114746094}, {'batch_size': 10, 'throughput': 4.7533022559329146, 'latency_mean': 2.082922065258026, 'latency_p50': 2.095589518547058, 'latency_p90': 2.350452351570129}, {'batch_size': 15, 'throughput': 5.425179176386075, 'latency_mean': 2.7145562779903414, 'latency_p50': 2.7397907972335815, 'latency_p90': 3.0561681270599363}, {'batch_size': 20, 'throughput': 5.830172881912812, 'latency_mean': 3.375443927049637, 'latency_p50': 3.3882769346237183, 'latency_p90': 3.864976692199707}, {'batch_size': 25, 'throughput': 6.029863010766256, 'latency_mean': 4.083269695043564, 'latency_p50': 4.07396674156189, 'latency_p90': 4.703074550628662}, {'batch_size': 30, 'throughput': 6.121591582227774, 'latency_mean': 4.790837872028351, 'latency_p50': 4.828047275543213, 'latency_p90': 5.502080416679382}, {'batch_size': 35, 'throughput': 6.1481724566372895, 'latency_mean': 5.535209767818451, 'latency_p50': 5.52951443195343, 'latency_p90': 6.351951217651367}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sicarius-Prototyping/Var
model_name: sicarius-prototyping-var_8179_v1
model_num_parameters: 8030277632.0
model_repo: Sicarius-Prototyping/Variety_RP_Alpha
model_size: 8B
num_battles: 11510
num_wins: 4997
propriety_score: 0.7367387033398821
propriety_total_count: 1018.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 6.03
timestamp: 2024-09-05T22:10:58+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.43414422241529105
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 sicarius-prototyping-var-8179-v1-mkmlizer
Waiting for job on sicarius-prototyping-var-8179-v1-mkmlizer to finish
sicarius-prototyping-var-8179-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sicarius-prototyping-var-8179-v1-mkmlizer: ║     _____            __           __                                ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║       /___/                                                         ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  belonging to:                                                      ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sicarius-prototyping-var-8179-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-var-8179-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sicarius-prototyping-var-8179-v1-mkmlizer: Downloaded to shared memory in 36.502s
sicarius-prototyping-var-8179-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzo6hxqw4, device:0
sicarius-prototyping-var-8179-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sicarius-prototyping-var-8179-v1-mkmlizer: quantized model in 26.421s
sicarius-prototyping-var-8179-v1-mkmlizer: Processed model Sicarius-Prototyping/Variety_RP_Alpha in 62.924s
sicarius-prototyping-var-8179-v1-mkmlizer: creating bucket guanaco-mkml-models
sicarius-prototyping-var-8179-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sicarius-prototyping-var-8179-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1
sicarius-prototyping-var-8179-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1/config.json
sicarius-prototyping-var-8179-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1/special_tokens_map.json
sicarius-prototyping-var-8179-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1/tokenizer_config.json
sicarius-prototyping-var-8179-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1/tokenizer.json
sicarius-prototyping-var-8179-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sicarius-prototyping-var-8179-v1/flywheel_model.0.safetensors
sicarius-prototyping-var-8179-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.41it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 52.68it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 47.88it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 46.37it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 52.53it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 45.82it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.49it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 47.83it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 51.52it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 51.18it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:03, 55.27it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:03, 54.71it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:05, 35.41it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:04, 39.82it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 43.65it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.32it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 45.47it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 42.97it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 42.66it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 46.35it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:03, 44.90it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 45.24it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 43.30it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 43.07it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 49.30it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 48.34it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 47.82it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 47.59it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.80it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 50.84it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.56it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 35.28it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.39it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 39.97it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.36it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 44.79it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 44.67it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 44.07it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 43.73it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 42.62it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 46.31it/s]
Loading 0:  87%|████████▋ | 252/291 [00:05<00:00, 49.14it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 45.43it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 51.20it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 45.08it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 45.16it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 41.37it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.27it/s]
                                                            

Job sicarius-prototyping-var-8179-v1-mkmlizer completed after 86.57s with status: succeeded
Stopping job with name sicarius-prototyping-var-8179-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sicarius-prototyping-var-8179-v1
Waiting for inference service sicarius-prototyping-var-8179-v1 to be ready
Failed to get response for submission blend_sehof_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service sicarius-prototyping-var-8179-v1 ready after 150.53002333641052s
Pipeline stage MKMLDeployer completed in 150.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.183375358581543s
Received healthy response to inference request in 1.2552335262298584s
Received healthy response to inference request in 0.8914787769317627s
Received healthy response to inference request in 1.4397087097167969s
Received healthy response to inference request in 1.661693811416626s
5 requests
0 failed requests
5th percentile: 0.9642297267913819
10th percentile: 1.036980676651001
20th percentile: 1.1824825763702393
30th percentile: 1.292128562927246
40th percentile: 1.3659186363220215
50th percentile: 1.4397087097167969
60th percentile: 1.5285027503967286
70th percentile: 1.61729679107666
80th percentile: 1.7660301208496094
90th percentile: 1.9747027397155763
95th percentile: 2.0790390491485593
99th percentile: 2.162508096694946
mean time: 1.4862980365753173
Pipeline stage StressChecker completed in 9.34s
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 7.24s
Shutdown handler de-registered
sicarius-prototyping-var_8179_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sicarius-prototyping-var-8179-v1-profiler
Waiting for inference service sicarius-prototyping-var-8179-v1-profiler to be ready
Inference service sicarius-prototyping-var-8179-v1-profiler ready after 140.36005544662476s
Pipeline stage MKMLProfilerDeployer completed in 140.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sicarius--deplodqjsw:/code/chaiverse_profiler_1725574701 --namespace tenant-chaiml-guanaco
kubectl exec -it sicarius--deplodqjsw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725574701 && python profiles.py profile --best_of_n 2 --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_1725574701/summary.json'
kubectl exec -it sicarius--deplodqjsw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725574701/summary.json'
Pipeline stage MKMLProfilerRunner completed in 472.63s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sicarius-prototyping-var-8179-v1-profiler is running
Tearing down inference service sicarius-prototyping-var-8179-v1-profiler
Service sicarius-prototyping-var-8179-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
sicarius-prototyping-var_8179_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics