epiculous-azure-dusk-v0-2

submission_id: epiculous-azure-dusk-v0-2_v3

developer_uid: Epiculous

alignment_samples: 11161

alignment_score: -0.8544836128158145

best_of: 8

celo_rating: 1237.28

display_name: Azure_Dusk-v0-2-High-T

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': 5.0, 'top_p': 1.0, 'min_p': 0.55, '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': 0.6928966622324219, 'latency_mean': 1.4431406140327454, 'latency_p50': 1.450502872467041, 'latency_p90': 1.6023399114608765}, {'batch_size': 3, 'throughput': 1.3218736788770697, 'latency_mean': 2.262002750635147, 'latency_p50': 2.2537933588027954, 'latency_p90': 2.5402179956436157}, {'batch_size': 5, 'throughput': 1.5683417248646823, 'latency_mean': 3.1799762165546417, 'latency_p50': 3.1902142763137817, 'latency_p90': 3.568867015838623}, {'batch_size': 6, 'throughput': 1.5843580542589175, 'latency_mean': 3.761807914972305, 'latency_p50': 3.7472647428512573, 'latency_p90': 4.248544645309448}, {'batch_size': 8, 'throughput': 1.5991771415424245, 'latency_mean': 4.981467424631119, 'latency_p50': 4.970952153205872, 'latency_p90': 5.69578914642334}, {'batch_size': 10, 'throughput': 1.490537792207101, 'latency_mean': 6.668754514455795, 'latency_p50': 6.73370099067688, 'latency_p90': 7.533791565895081}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Epiculous/Azure_Dusk-v0.

model_name: Azure_Dusk-v0-2-High-T

model_num_parameters: 12772070400.0

model_repo: Epiculous/Azure_Dusk-v0.2

model_size: 13B

num_battles: 11161

num_wins: 5531

propriety_score: 0.7509920634920635

propriety_total_count: 1008.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.59

timestamp: 2024-09-09T18:12:42+00:00

us_pacific_date: 2024-09-09

win_ratio: 0.4955649135382134

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-v0-2-v3-mkmlizer
Waiting for job on epiculous-azure-dusk-v0-2-v3-mkmlizer to finish
epiculous-azure-dusk-v0-2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║     _____            __           __                                ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║       /___/                                                         ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  belonging to:                                                      ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
epiculous-azure-dusk-v0-2-v3-mkmlizer: Downloaded to shared memory in 27.372s
epiculous-azure-dusk-v0-2-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppn7e0vae, device:0
epiculous-azure-dusk-v0-2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
Failed to get response for submission blend_katim_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', 'read tcp 127.0.0.1:53566->127.0.0.1:8080: read: connection reset by peer\n')
epiculous-azure-dusk-v0-2-v3-mkmlizer: quantized model in 37.105s
epiculous-azure-dusk-v0-2-v3-mkmlizer: Processed model Epiculous/Azure_Dusk-v0.2 in 64.477s
epiculous-azure-dusk-v0-2-v3-mkmlizer: creating bucket guanaco-mkml-models
epiculous-azure-dusk-v0-2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
epiculous-azure-dusk-v0-2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3
epiculous-azure-dusk-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3/config.json
epiculous-azure-dusk-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3/special_tokens_map.json
epiculous-azure-dusk-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3/tokenizer_config.json
epiculous-azure-dusk-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3/tokenizer.json
epiculous-azure-dusk-v0-2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v3/flywheel_model.0.safetensors
epiculous-azure-dusk-v0-2-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.51it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.91it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.08it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.54it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 46.40it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 44.77it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 44.77it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:06, 45.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.65it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.23it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.12it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.58it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.46it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.49it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.95it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.56it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.08it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.08it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.04it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 33.94it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.22it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.72it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.85it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.85it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.80it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.03it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.40it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.95it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.96it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.61it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 37.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 36.19it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.23it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 39.36it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 39.43it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 40.81it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 33.92it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.72it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.22it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.07it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 27.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.45it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.18it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.35it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.46it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.63it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 40.96it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 40.50it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.40it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 40.38it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.22it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.63it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 40.23it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 41.95it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.45it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.17it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:11,  4.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:06,  6.17it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:04,  7.84it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 10.52it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 13.87it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.14it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 22.69it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 25.93it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.41it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 33.25it/s]
                                                            
Job epiculous-azure-dusk-v0-2-v3-mkmlizer completed after 94.99s with status: succeeded
Stopping job with name epiculous-azure-dusk-v0-2-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.89s
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 epiculous-azure-dusk-v0-2-v3
Waiting for inference service epiculous-azure-dusk-v0-2-v3 to be ready
Inference service epiculous-azure-dusk-v0-2-v3 ready after 150.5230269432068s
Pipeline stage MKMLDeployer completed in 150.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6970300674438477s
Received healthy response to inference request in 3.1001148223876953s
Received healthy response to inference request in 1.376887559890747s
Received healthy response to inference request in 2.0371997356414795s
Received healthy response to inference request in 2.01115083694458s
5 requests
0 failed requests
5th percentile: 1.5037402153015136
10th percentile: 1.6305928707122803
20th percentile: 1.8842981815338136
30th percentile: 2.01636061668396
40th percentile: 2.0267801761627195
50th percentile: 2.0371997356414795
60th percentile: 2.3011318683624267
70th percentile: 2.565064001083374
80th percentile: 2.777647018432617
90th percentile: 2.9388809204101562
95th percentile: 3.019497871398926
99th percentile: 3.0839914321899413
mean time: 2.2444766044616697
Pipeline stage StressChecker completed in 11.88s
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 4.83s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service epiculous-azure-dusk-v0-2-v3-profiler
Waiting for inference service epiculous-azure-dusk-v0-2-v3-profiler to be ready
Inference service epiculous-azure-dusk-v0-2-v3-profiler ready after 150.34942483901978s
Pipeline stage MKMLProfilerDeployer completed in 150.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/epiculous-azure-duska8c2cf81de275fc2eed45cd233152edc-deplov9ssn:/code/chaiverse_profiler_1725906028 --namespace tenant-chaiml-guanaco
kubectl exec -it epiculous-azure-duska8c2cf81de275fc2eed45cd233152edc-deplov9ssn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725906028 && 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_1725906028/summary.json'
kubectl exec -it epiculous-azure-duska8c2cf81de275fc2eed45cd233152edc-deplov9ssn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725906028/summary.json'
Pipeline stage MKMLProfilerRunner completed in 958.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service epiculous-azure-dusk-v0-2-v3-profiler is running
Tearing down inference service epiculous-azure-dusk-v0-2-v3-profiler
Service epiculous-azure-dusk-v0-2-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.62s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_v3 status is now inactive due to auto deactivation removed underperforming models