epiculous-azure-dusk-v0-2

submission_id: epiculous-azure-dusk-v0-2_v2

developer_uid: Epiculous

alignment_samples: 11172

alignment_score: -0.7962123343499529

best_of: 8

celo_rating: 1246.13

display_name: Crimson_Dawn-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': 0.6982217587413417, 'latency_mean': 1.4321405148506166, 'latency_p50': 1.4448496103286743, 'latency_p90': 1.580601978302002}, {'batch_size': 3, 'throughput': 1.3400265181420001, 'latency_mean': 2.23737602353096, 'latency_p50': 2.236678957939148, 'latency_p90': 2.4740915536880492}, {'batch_size': 5, 'throughput': 1.5977884431759366, 'latency_mean': 3.1137713599205017, 'latency_p50': 3.1044241189956665, 'latency_p90': 3.5714045763015747}, {'batch_size': 6, 'throughput': 1.6272300667198414, 'latency_mean': 3.6642264020442963, 'latency_p50': 3.631811261177063, 'latency_p90': 4.147841954231263}, {'batch_size': 8, 'throughput': 1.596197692741306, 'latency_mean': 4.971453963518143, 'latency_p50': 5.03224241733551, 'latency_p90': 5.572181820869446}, {'batch_size': 10, 'throughput': 1.5419534498950456, 'latency_mean': 6.439809455871582, 'latency_p50': 6.474263668060303, 'latency_p90': 7.227451372146606}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: Epiculous/Azure_Dusk-v0.

model_name: Crimson_Dawn-v0-2-High-T

model_num_parameters: 12772070400.0

model_repo: Epiculous/Azure_Dusk-v0.2

model_size: 13B

num_battles: 11172

num_wins: 5676

propriety_score: 0.7619521912350598

propriety_total_count: 1004.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.64

timestamp: 2024-09-09T18:12:41+00:00

us_pacific_date: 2024-09-09

win_ratio: 0.5080558539205156

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-v2-mkmlizer
Waiting for job on epiculous-azure-dusk-v0-2-v2-mkmlizer to finish
epiculous-azure-dusk-v0-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║     _____            __           __                                ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║       /___/                                                         ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  belonging to:                                                      ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ║                                                                     ║
epiculous-azure-dusk-v0-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
epiculous-azure-dusk-v0-2-v2-mkmlizer: Downloaded to shared memory in 29.277s
epiculous-azure-dusk-v0-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_z9fh0nk, device:0
epiculous-azure-dusk-v0-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
epiculous-azure-dusk-v0-2-v2-mkmlizer: quantized model in 37.627s
epiculous-azure-dusk-v0-2-v2-mkmlizer: Processed model Epiculous/Azure_Dusk-v0.2 in 66.904s
epiculous-azure-dusk-v0-2-v2-mkmlizer: creating bucket guanaco-mkml-models
epiculous-azure-dusk-v0-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
epiculous-azure-dusk-v0-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2
epiculous-azure-dusk-v0-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2/config.json
epiculous-azure-dusk-v0-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2/special_tokens_map.json
epiculous-azure-dusk-v0-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2/tokenizer_config.json
epiculous-azure-dusk-v0-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2/tokenizer.json
epiculous-azure-dusk-v0-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/epiculous-azure-dusk-v0-2-v2/flywheel_model.0.safetensors
epiculous-azure-dusk-v0-2-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.01it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 49.15it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.99it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.10it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.48it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.22it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.25it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.35it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.20it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.00it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.30it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.49it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.40it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.55it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.74it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 32.25it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.57it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 38.46it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 40.03it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 35.18it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.11it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.68it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.87it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.85it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 40.81it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.20it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.48it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 30.77it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:06, 29.65it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.02it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 37.41it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 38.53it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 40.21it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.53it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 40.42it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 40.12it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 40.66it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 41.52it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 34.39it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 38.71it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 30.11it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 31.13it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 30.26it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:04, 31.74it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:04, 30.43it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.29it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.25it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 37.88it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 37.03it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.56it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 38.89it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.78it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 37.61it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.73it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 37.67it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 40.14it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 39.27it/s]
Loading 0:  83%|████████▎ | 300/363 [00:08<00:01, 38.24it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:28,  2.04it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.58it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.83it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  6.28it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:04,  8.39it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 11.02it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 14.25it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.28it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 22.76it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 26.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.25it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 33.19it/s]
                                                            
Job epiculous-azure-dusk-v0-2-v2-mkmlizer completed after 96.29s with status: succeeded
Stopping job with name epiculous-azure-dusk-v0-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service epiculous-azure-dusk-v0-2-v2
Waiting for inference service epiculous-azure-dusk-v0-2-v2 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
Inference service epiculous-azure-dusk-v0-2-v2 ready after 150.89455103874207s
Pipeline stage MKMLDeployer completed in 151.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1315019130706787s
Received healthy response to inference request in 2.7322654724121094s
Received healthy response to inference request in 1.9917032718658447s
Received healthy response to inference request in 2.0577714443206787s
Received healthy response to inference request in 1.9871294498443604s
5 requests
0 failed requests
5th percentile: 1.9880442142486572
10th percentile: 1.988958978652954
20th percentile: 1.990788507461548
30th percentile: 2.0049169063568115
40th percentile: 2.031344175338745
50th percentile: 2.0577714443206787
60th percentile: 2.0872636318206785
70th percentile: 2.116755819320679
80th percentile: 2.251654624938965
90th percentile: 2.491960048675537
95th percentile: 2.6121127605438232
99th percentile: 2.708234930038452
mean time: 2.1800743103027345
Pipeline stage StressChecker completed in 12.21s
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 6.81s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_v2 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 0.15s
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-v2-profiler
Waiting for inference service epiculous-azure-dusk-v0-2-v2-profiler to be ready
Inference service epiculous-azure-dusk-v0-2-v2-profiler ready after 150.36097621917725s
Pipeline stage MKMLProfilerDeployer completed in 151.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/epiculous-azure-dusk8c7190ef9b659e37df236f0fc44f45fb-deploq4w6f:/code/chaiverse_profiler_1725906028 --namespace tenant-chaiml-guanaco
kubectl exec -it epiculous-azure-dusk8c7190ef9b659e37df236f0fc44f45fb-deploq4w6f --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-dusk8c7190ef9b659e37df236f0fc44f45fb-deploq4w6f --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725906028/summary.json'
Pipeline stage MKMLProfilerRunner completed in 945.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service epiculous-azure-dusk-v0-2-v2-profiler is running
Tearing down inference service epiculous-azure-dusk-v0-2-v2-profiler
Service epiculous-azure-dusk-v0-2-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.68s
Shutdown handler de-registered
epiculous-azure-dusk-v0-2_v2 status is now inactive due to auto deactivation removed underperforming models