rica40325-dpo0903-1300

submission_id: rica40325-dpo0903-1300_v1

developer_uid: rica40325

best_of: 16

celo_rating: 1182.33

display_name: rica40325-dpo0903-1300_v1

family_friendly_score: 0.0

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': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: rica40325/dpo0903-1300

latencies: [{'batch_size': 1, 'throughput': 0.9114409243608039, 'latency_mean': 1.0971040856838226, 'latency_p50': 1.0991665124893188, 'latency_p90': 1.224856686592102}, {'batch_size': 4, 'throughput': 1.7868304717290997, 'latency_mean': 2.22366925239563, 'latency_p50': 2.226734757423401, 'latency_p90': 2.473489260673523}, {'batch_size': 5, 'throughput': 1.895461954193833, 'latency_mean': 2.6227510726451873, 'latency_p50': 2.617081642150879, 'latency_p90': 2.954130268096924}, {'batch_size': 8, 'throughput': 2.020233527656336, 'latency_mean': 3.9364895713329315, 'latency_p50': 3.9572131633758545, 'latency_p90': 4.423591208457947}, {'batch_size': 10, 'throughput': 2.0275583801555075, 'latency_mean': 4.879239919185639, 'latency_p50': 4.85245668888092, 'latency_p90': 5.568426132202148}, {'batch_size': 12, 'throughput': 2.0084960840481183, 'latency_mean': 5.896673389673233, 'latency_p50': 5.9853702783584595, 'latency_p90': 6.6760406494140625}, {'batch_size': 15, 'throughput': 2.038009905317322, 'latency_mean': 7.209387437105179, 'latency_p50': 7.33719527721405, 'latency_p90': 8.025400686264039}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: rica40325/dpo0903-1300

model_name: rica40325-dpo0903-1300_v1

model_num_parameters: 8030261248.0

model_repo: rica40325/dpo0903-1300

model_size: 8B

num_battles: 13167

num_wins: 5565

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.02

timestamp: 2024-09-05T06:44:40+00:00

us_pacific_date: 2024-09-04

win_ratio: 0.4226475279106858

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 rica40325-dpo0903-1300-v1-mkmlizer
Waiting for job on rica40325-dpo0903-1300-v1-mkmlizer to finish
rica40325-dpo0903-1300-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-dpo0903-1300-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-dpo0903-1300-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-dpo0903-1300-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-dpo0903-1300-v1-mkmlizer: ║       /___/                                                         ║
rica40325-dpo0903-1300-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-dpo0903-1300-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-dpo0903-1300-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-dpo0903-1300-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-dpo0903-1300-v1-mkmlizer: ║                                                                     ║
rica40325-dpo0903-1300-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-dpo0903-1300-v1-mkmlizer: Downloaded to shared memory in 65.344s
rica40325-dpo0903-1300-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppzt4mukw, device:0
rica40325-dpo0903-1300-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-dpo0903-1300-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-dpo0903-1300-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-dpo0903-1300-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1
rica40325-dpo0903-1300-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1/config.json
rica40325-dpo0903-1300-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1/special_tokens_map.json
rica40325-dpo0903-1300-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1/tokenizer_config.json
rica40325-dpo0903-1300-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1/tokenizer.json
rica40325-dpo0903-1300-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-dpo0903-1300-v1/flywheel_model.0.safetensors
rica40325-dpo0903-1300-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:09, 28.90it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:11, 25.24it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:09, 28.73it/s]
Loading 0:   5%|▌         | 15/291 [00:00<00:10, 26.41it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:09, 30.12it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:09, 26.92it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 39.48it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 22.16it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.91it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 30.24it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.24it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 33.31it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 31.53it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.04it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:07, 31.20it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:07, 30.43it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 31.00it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:10, 20.39it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:09, 21.66it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 25.48it/s]
Loading 0:  32%|███▏      | 93/291 [00:03<00:07, 24.97it/s]
Loading 0:  33%|███▎      | 97/291 [00:03<00:06, 27.94it/s]
Loading 0:  35%|███▍      | 101/291 [00:03<00:07, 26.20it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.51it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.55it/s]
Loading 0:  40%|███▉      | 116/291 [00:04<00:05, 32.97it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 37.97it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 36.12it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.34it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.04it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.26it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.11it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 32.44it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 35.61it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.01it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.49it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.89it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.82it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.10it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 37.42it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:03, 26.26it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.48it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 24.80it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:03, 29.68it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 29.92it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.49it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 32.20it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 34.37it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 31.94it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.89it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 32.45it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.32it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 24.44it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 31.35it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.35it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 32.53it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 30.70it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 31.94it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 30.08it/s]
Loading 0:  94%|█████████▍| 273/291 [00:09<00:00, 32.40it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 31.69it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 31.02it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.55it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  3.17it/s]
                                                            
Job rica40325-dpo0903-1300-v1-mkmlizer completed after 115.51s with status: succeeded
Stopping job with name rica40325-dpo0903-1300-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.53s
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 rica40325-dpo0903-1300-v1
Waiting for inference service rica40325-dpo0903-1300-v1 to be ready
Inference service rica40325-dpo0903-1300-v1 ready after 141.56394791603088s
Pipeline stage MKMLDeployer completed in 142.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8702971935272217s
Received healthy response to inference request in 1.7364835739135742s
Received healthy response to inference request in 1.8175110816955566s
Received healthy response to inference request in 1.735727310180664s
Received healthy response to inference request in 1.8523914813995361s
5 requests
0 failed requests
5th percentile: 1.7358785629272462
10th percentile: 1.736029815673828
20th percentile: 1.736332321166992
30th percentile: 1.7526890754699707
40th percentile: 1.7851000785827638
50th percentile: 1.8175110816955566
60th percentile: 1.8314632415771483
70th percentile: 1.8454154014587403
80th percentile: 1.8559726238250733
90th percentile: 1.8631349086761475
95th percentile: 1.8667160511016845
99th percentile: 1.8695809650421142
mean time: 1.8024821281433105
Pipeline stage StressChecker completed in 10.06s
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 6.60s
Shutdown handler de-registered
rica40325-dpo0903-1300_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-dpo0903-1300-v1-profiler
Waiting for inference service rica40325-dpo0903-1300-v1-profiler to be ready
Inference service rica40325-dpo0903-1300-v1-profiler ready after 140.37017607688904s
Pipeline stage MKMLProfilerDeployer completed in 140.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-dpo0903-1300-v1-profiler-predictor-00001-deploym4bv87:/code/chaiverse_profiler_1725519140 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-dpo0903-1300-v1-profiler-predictor-00001-deploym4bv87 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725519140 && 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_1725519140/summary.json'
kubectl exec -it rica40325-dpo0903-1300-v1-profiler-predictor-00001-deploym4bv87 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725519140/summary.json'
Pipeline stage MKMLProfilerRunner completed in 837.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-dpo0903-1300-v1-profiler is running
Tearing down inference service rica40325-dpo0903-1300-v1-profiler
Service rica40325-dpo0903-1300-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.63s
Shutdown handler de-registered
rica40325-dpo0903-1300_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-dpo0903-1300_v1 status is now torndown due to DeploymentManager action