epiculous-azure-dusk-v0-2

submission_id: epiculous-azure-dusk-v0-2_v1

developer_uid: Epiculous

best_of: 8

celo_rating: 1246.96

display_name: Azure_Dusk-v0-2-VT

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: Epiculous/Azure_Dusk-v0.2

latencies: [{'batch_size': 1, 'throughput': 0.6994590580782591, 'latency_mean': 1.4296178233623504, 'latency_p50': 1.429540753364563, 'latency_p90': 1.5880573987960815}, {'batch_size': 3, 'throughput': 1.3158091819002093, 'latency_mean': 2.2719916665554045, 'latency_p50': 2.2665045261383057, 'latency_p90': 2.5026118993759154}, {'batch_size': 5, 'throughput': 1.5703852058420236, 'latency_mean': 3.16495809674263, 'latency_p50': 3.1980167627334595, 'latency_p90': 3.5327499866485597}, {'batch_size': 6, 'throughput': 1.6251108937199585, 'latency_mean': 3.668463416099548, 'latency_p50': 3.7138158082962036, 'latency_p90': 4.130882096290589}, {'batch_size': 8, 'throughput': 1.6109153798322682, 'latency_mean': 4.942424048185348, 'latency_p50': 4.943863153457642, 'latency_p90': 5.570983576774597}, {'batch_size': 10, 'throughput': 1.563646486712016, 'latency_mean': 6.359816110134124, 'latency_p50': 6.376768350601196, 'latency_p90': 7.243695592880249}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Epiculous/Azure_Dusk-v0.

model_name: Azure_Dusk-v0-2-VT

model_num_parameters: 12772070400.0

model_repo: Epiculous/Azure_Dusk-v0.2

model_size: 13B

num_battles: 12621

num_wins: 6485

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.64

timestamp: 2024-09-09T16:31:49+00:00

us_pacific_date: 2024-09-09

win_ratio: 0.513826162744632

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 epiculous-azure-dusk-v0-2-v1-mkmlizer
Waiting for job on epiculous-azure-dusk-v0-2-v1-mkmlizer to finish
epiculous-azure-dusk-v0-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║     _____            __           __                                ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║       /___/                                                         ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  belonging to:                                                      ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
epiculous-azure-dusk-v0-2-v1-mkmlizer: quantized model in 36.542s
epiculous-azure-dusk-v0-2-v1-mkmlizer: Processed model Epiculous/Azure_Dusk-v0.2 in 82.480s
epiculous-azure-dusk-v0-2-v1-mkmlizer: creating bucket guanaco-mkml-models
epiculous-azure-dusk-v0-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
epiculous-azure-dusk-v0-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1
epiculous-azure-dusk-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1/config.json
epiculous-azure-dusk-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1/special_tokens_map.json
epiculous-azure-dusk-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1/tokenizer_config.json
epiculous-azure-dusk-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1/tokenizer.json
epiculous-azure-dusk-v0-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v1/flywheel_model.0.safetensors
epiculous-azure-dusk-v0-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.53it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.48it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.01it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.92it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 47.31it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 47.04it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:08, 37.28it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 45.99it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.22it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.15it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.46it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.08it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 36.05it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.07it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.82it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.41it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 45.52it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 45.80it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 43.50it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 43.71it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 35.14it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 40.63it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.91it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 27.33it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.88it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.37it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.41it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.81it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 36.66it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.28it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 36.32it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 40.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 40.24it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 39.01it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 42.77it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 43.39it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 42.50it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 42.33it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 42.72it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 27.43it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.90it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.99it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 36.55it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.27it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 37.53it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 37.74it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.82it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.45it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.63it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.09it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.27it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.46it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.40it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.22it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.19it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.19it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.25it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  8.45it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03, 10.70it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.38it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.77it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.54it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 28.37it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 31.23it/s]
                                                            
Job epiculous-azure-dusk-v0-2-v1-mkmlizer completed after 105.18s with status: succeeded
Stopping job with name epiculous-azure-dusk-v0-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.76s
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 epiculous-azure-dusk-v0-2-v1
Waiting for inference service epiculous-azure-dusk-v0-2-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
Inference service epiculous-azure-dusk-v0-2-v1 ready after 150.62637901306152s
Pipeline stage MKMLDeployer completed in 151.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.538109064102173s
Received healthy response to inference request in 2.048007011413574s
Received healthy response to inference request in 1.7887613773345947s
Received healthy response to inference request in 2.441253423690796s
Received healthy response to inference request in 2.749952793121338s
5 requests
0 failed requests
5th percentile: 1.8406105041503906
10th percentile: 1.8924596309661865
20th percentile: 1.9961578845977783
30th percentile: 2.1266562938690186
40th percentile: 2.2839548587799072
50th percentile: 2.441253423690796
60th percentile: 2.479995679855347
70th percentile: 2.5187379360198974
80th percentile: 2.580477809906006
90th percentile: 2.6652153015136717
95th percentile: 2.707584047317505
99th percentile: 2.741479043960571
mean time: 2.313216733932495
Pipeline stage StressChecker completed in 12.19s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
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
Pipeline stage TriggerMKMLProfilingPipeline completed in 8.44s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service epiculous-azure-dusk-v0-2-v1-profiler
Waiting for inference service epiculous-azure-dusk-v0-2-v1-profiler to be ready
Inference service epiculous-azure-dusk-v0-2-v1-profiler ready after 150.33491110801697s
Pipeline stage MKMLProfilerDeployer completed in 150.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/epiculous-azure-dusk15987d7b26bee69a27de9c86cf03fce6-deplo57n9n:/code/chaiverse_profiler_1725899979 --namespace tenant-chaiml-guanaco
kubectl exec -it epiculous-azure-dusk15987d7b26bee69a27de9c86cf03fce6-deplo57n9n --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725899979 && python profiles.py profile --best_of_n 8 --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_1725899979/summary.json'
kubectl exec -it epiculous-azure-dusk15987d7b26bee69a27de9c86cf03fce6-deplo57n9n --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725899979/summary.json'
Pipeline stage MKMLProfilerRunner completed in 946.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service epiculous-azure-dusk-v0-2-v1-profiler is running
Tearing down inference service epiculous-azure-dusk-v0-2-v1-profiler
Service epiculous-azure-dusk-v0-2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_v1 status is now inactive due to auto deactivation removed underperforming models
epiculous-azure-dusk-v0-2_v1 status is now torndown due to DeploymentManager action