zonemercy-elite-pref-v3-1e5

developer_uid: zonemercy

submission_id: zonemercy-elite-pref-v3-1e5_v1

model_name: zonemercy-elite-pref-v3-1e5_v1

model_group: zonemercy/Elite-Pref-v3-

status: torndown

timestamp: 2024-09-13T20:33:38+00:00

num_battles: 11570

num_wins: 5748

celo_rating: 1243.93

family_friendly_score: 0.0

submission_type: basic

model_repo: zonemercy/Elite-Pref-v3-1e5

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.615267749840818, 'latency_mean': 1.625240433216095, 'latency_p50': 1.6145697832107544, 'latency_p90': 1.7999722719192506}, {'batch_size': 3, 'throughput': 1.078837338805823, 'latency_mean': 2.7741006898880003, 'latency_p50': 2.7804410457611084, 'latency_p90': 3.047774744033813}, {'batch_size': 5, 'throughput': 1.2223720426133997, 'latency_mean': 4.069674600362777, 'latency_p50': 4.060562968254089, 'latency_p90': 4.544685244560242}, {'batch_size': 6, 'throughput': 1.2491405893839531, 'latency_mean': 4.784555287361145, 'latency_p50': 4.794906377792358, 'latency_p90': 5.34844605922699}, {'batch_size': 8, 'throughput': 1.237458124711314, 'latency_mean': 6.426220020055771, 'latency_p50': 6.432458400726318, 'latency_p90': 7.222341728210449}, {'batch_size': 10, 'throughput': 1.2069277737778612, 'latency_mean': 8.23491923213005, 'latency_p50': 8.271465182304382, 'latency_p90': 9.330485916137695}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: zonemercy-elite-pref-v3-1e5_v1

is_internal_developer: True

language_model: zonemercy/Elite-Pref-v3-1e5

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-13

win_ratio: 0.4968020743301642

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '{user_name}: {message}</s>', 'response_template': '{bot_name}:', 'truncate_by_message': False}

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 zonemercy-elite-pref-v3-1e5-v1-mkmlizer
Waiting for job on zonemercy-elite-pref-v3-1e5-v1-mkmlizer to finish
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: Downloaded to shared memory in 95.052s
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp86zn640u, device:0
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: quantized model in 40.255s
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: Processed model zonemercy/Elite-Pref-v3-1e5 in 135.307s
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1/config.json
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1/special_tokens_map.json
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1/tokenizer_config.json
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1/tokenizer.json
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-elite-pref-v3-1e5-v1/flywheel_model.0.safetensors
zonemercy-elite-pref-v3-1e5-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.44it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.12it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 26.33it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 35.03it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 22.79it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.45it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.58it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.09it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.70it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.73it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.75it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.41it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 25.09it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.36it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.57it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.02it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 28.47it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.20it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.48it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.76it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.42it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.52it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.18it/s]
Loading 0:  30%|███       | 109/363 [00:03<00:09, 27.52it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:09, 25.07it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.14it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.48it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.52it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.82it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.54it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.46it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 29.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:07, 26.30it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.85it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.81it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.18it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.32it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.68it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.25it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.32it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.46it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.42it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.92it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 31.48it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.06it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.65it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.13it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.96it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 29.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 26.86it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.89it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 31.40it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 33.33it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 31.78it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 26.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 23.21it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:02, 30.12it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 29.65it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 31.67it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.49it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.95it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.95it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.08it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 25.47it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.19it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.52it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.69it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.53it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.85it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.43it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.72it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 31.36it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.70it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.91it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.08it/s]
                                                            
Job zonemercy-elite-pref-v3-1e5-v1-mkmlizer completed after 160.84s with status: succeeded
Stopping job with name zonemercy-elite-pref-v3-1e5-v1-mkmlizer
Pipeline stage MKMLizer completed in 161.82s
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 zonemercy-elite-pref-v3-1e5-v1
Waiting for inference service zonemercy-elite-pref-v3-1e5-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-elite-pref-v3-1e5-v1 ready after 182.4088215827942s
Pipeline stage MKMLDeployer completed in 183.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.430386781692505s
Received healthy response to inference request in 2.106916666030884s
Received healthy response to inference request in 2.1563570499420166s
Received healthy response to inference request in 2.1358728408813477s
Received healthy response to inference request in 1.9239556789398193s
5 requests
0 failed requests
5th percentile: 1.9605478763580322
10th percentile: 1.997140073776245
20th percentile: 2.0703244686126707
30th percentile: 2.1127079010009764
40th percentile: 2.124290370941162
50th percentile: 2.1358728408813477
60th percentile: 2.1440665245056154
70th percentile: 2.1522602081298827
80th percentile: 2.2111629962921144
90th percentile: 2.3207748889923097
95th percentile: 2.375580835342407
99th percentile: 2.4194255924224852
mean time: 2.1506978034973145
Pipeline stage StressChecker completed in 12.04s
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 7.47s
Shutdown handler de-registered
zonemercy-elite-pref-v3-1e5_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-elite-pref-v3-1e5-v1-profiler
Waiting for inference service zonemercy-elite-pref-v3-1e5-v1-profiler to be ready
Inference service zonemercy-elite-pref-v3-1e5-v1-profiler ready after 180.41608428955078s
Pipeline stage MKMLProfilerDeployer completed in 180.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-elite-pref2df7c00e090513d8cfc0f72356c03a16-deplohscpt:/code/chaiverse_profiler_1726260204 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-elite-pref2df7c00e090513d8cfc0f72356c03a16-deplohscpt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726260204 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726260204/summary.json'
kubectl exec -it zonemercy-elite-pref2df7c00e090513d8cfc0f72356c03a16-deplohscpt --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726260204/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1168.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-elite-pref-v3-1e5-v1-profiler is running
Tearing down inference service zonemercy-elite-pref-v3-1e5-v1-profiler
Service zonemercy-elite-pref-v3-1e5-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
Shutdown handler de-registered
zonemercy-elite-pref-v3-1e5_v1 status is now inactive due to auto deactivation removed underperforming models
zonemercy-elite-pref-v3-1e5_v1 status is now torndown due to DeploymentManager action