epiculous-azure-dusk-bas_2210

submission_id: epiculous-azure-dusk-bas_2210_v1

developer_uid: Epiculous

alignment_samples: 12607

alignment_score: -0.48518306375304976

best_of: 8

celo_rating: 1245.67

display_name: Azure_Dusk-v0-2-NORP_VT

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-Base-Instruct-v0.2

latencies: [{'batch_size': 1, 'throughput': 0.7023891351029451, 'latency_mean': 1.423653531074524, 'latency_p50': 1.4138360023498535, 'latency_p90': 1.6003567934036256}, {'batch_size': 3, 'throughput': 1.3508482691330608, 'latency_mean': 2.2108935010433197, 'latency_p50': 2.198080539703369, 'latency_p90': 2.446429681777954}, {'batch_size': 5, 'throughput': 1.611367776016812, 'latency_mean': 3.081811366081238, 'latency_p50': 3.091226577758789, 'latency_p90': 3.5114348888397218}, {'batch_size': 6, 'throughput': 1.6433166879847458, 'latency_mean': 3.6401929163932802, 'latency_p50': 3.6475054025650024, 'latency_p90': 4.104503345489502}, {'batch_size': 8, 'throughput': 1.5961490827090135, 'latency_mean': 4.997523243427277, 'latency_p50': 4.984360098838806, 'latency_p90': 5.648513698577881}, {'batch_size': 10, 'throughput': 1.5418442305002469, 'latency_mean': 6.444088622331619, 'latency_p50': 6.483338356018066, 'latency_p90': 7.452718663215637}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Epiculous/Azure_Dusk-Bas

model_name: Azure_Dusk-v0-2-NORP_VT

model_num_parameters: 12772070400.0

model_repo: Epiculous/Azure_Dusk-Base-Instruct-v0.2

model_size: 13B

num_battles: 12604

num_wins: 6336

propriety_score: 0.7174887892376681

propriety_total_count: 1115.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.65

timestamp: 2024-09-11T00:45:13+00:00

us_pacific_date: 2024-09-10

win_ratio: 0.5026975563313234

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 epiculous-azure-dusk-bas-2210-v1-mkmlizer
Waiting for job on epiculous-azure-dusk-bas-2210-v1-mkmlizer to finish
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║     _____            __           __                                ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║       /___/                                                         ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  https://mk1.ai                                                     ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  belonging to:                                                      ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  Chai Research Corp.                                                ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-bas-2210-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
epiculous-azure-dusk-bas-2210-v1-mkmlizer: Downloaded to shared memory in 45.637s
epiculous-azure-dusk-bas-2210-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp89jrg3pn, device:0
epiculous-azure-dusk-bas-2210-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
epiculous-azure-dusk-bas-2210-v1-mkmlizer: quantized model in 35.403s
epiculous-azure-dusk-bas-2210-v1-mkmlizer: Processed model Epiculous/Azure_Dusk-Base-Instruct-v0.2 in 81.040s
epiculous-azure-dusk-bas-2210-v1-mkmlizer: creating bucket guanaco-mkml-models
epiculous-azure-dusk-bas-2210-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
epiculous-azure-dusk-bas-2210-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1
epiculous-azure-dusk-bas-2210-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1/config.json
epiculous-azure-dusk-bas-2210-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1/special_tokens_map.json
epiculous-azure-dusk-bas-2210-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1/tokenizer_config.json
epiculous-azure-dusk-bas-2210-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
epiculous-azure-dusk-bas-2210-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/epiculous-azure-dusk-bas-2210-v1/flywheel_model.0.safetensors
epiculous-azure-dusk-bas-2210-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.82it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 54.36it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.83it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 46.18it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.32it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.85it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.24it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.55it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.13it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:07, 38.10it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.49it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.31it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.33it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.71it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.42it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.81it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.90it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:05, 46.21it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.43it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 43.71it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 45.12it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:06, 37.56it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 43.88it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.25it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.91it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 30.50it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.27it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 39.16it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 40.58it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 42.64it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.01it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 44.03it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 42.43it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 41.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 45.07it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 44.60it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 44.19it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 42.20it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.70it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.98it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.16it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.25it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.91it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 42.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 41.68it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.32it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.95it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 45.25it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 45.55it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 42.74it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 42.28it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 46.78it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 45.89it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 45.63it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:16,  3.21it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:11,  4.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.33it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  8.55it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03, 10.80it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.38it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.02it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.38it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 29.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.42it/s]
                                                            
Job epiculous-azure-dusk-bas-2210-v1-mkmlizer completed after 106.08s with status: succeeded
Stopping job with name epiculous-azure-dusk-bas-2210-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service epiculous-azure-dusk-bas-2210-v1
Waiting for inference service epiculous-azure-dusk-bas-2210-v1 to be ready
Inference service epiculous-azure-dusk-bas-2210-v1 ready after 150.8796842098236s
Pipeline stage MKMLDeployer completed in 151.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2794485092163086s
Received healthy response to inference request in 2.003941059112549s
Received healthy response to inference request in 1.749812364578247s
Received healthy response to inference request in 2.016951560974121s
Received healthy response to inference request in 2.042680263519287s
5 requests
0 failed requests
5th percentile: 1.8006381034851073
10th percentile: 1.8514638423919678
20th percentile: 1.9531153202056886
30th percentile: 2.0065431594848633
40th percentile: 2.011747360229492
50th percentile: 2.016951560974121
60th percentile: 2.0272430419921874
70th percentile: 2.0375345230102537
80th percentile: 2.0900339126586913
90th percentile: 2.1847412109375
95th percentile: 2.2320948600769044
99th percentile: 2.269977779388428
mean time: 2.0185667514801025
Pipeline stage StressChecker completed in 11.07s
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 7.73s
Shutdown handler de-registered
epiculous-azure-dusk-bas_2210_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 0.11s
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-bas-2210-v1-profiler
Waiting for inference service epiculous-azure-dusk-bas-2210-v1-profiler to be ready
Inference service epiculous-azure-dusk-bas-2210-v1-profiler ready after 150.3674829006195s
Pipeline stage MKMLProfilerDeployer completed in 150.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/epiculous-azure-dusk84152fd1bbe77e6d523b72059ae6221d-deplolvmzj:/code/chaiverse_profiler_1726015982 --namespace tenant-chaiml-guanaco
kubectl exec -it epiculous-azure-dusk84152fd1bbe77e6d523b72059ae6221d-deplolvmzj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726015982 && 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_1726015982/summary.json'
kubectl exec -it epiculous-azure-dusk84152fd1bbe77e6d523b72059ae6221d-deplolvmzj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726015982/summary.json'
Pipeline stage MKMLProfilerRunner completed in 938.50s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service epiculous-azure-dusk-bas-2210-v1-profiler is running
Tearing down inference service epiculous-azure-dusk-bas-2210-v1-profiler
Service epiculous-azure-dusk-bas-2210-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
epiculous-azure-dusk-bas_2210_v1 status is now inactive due to auto deactivation removed underperforming models