zonemercy-elite-edit-v1ep1

developer_uid: zonemercy

submission_id: zonemercy-elite-edit-v1ep1_v1

model_name: zonemercy-elite-edit-v1ep1_v1

model_group: zonemercy/Elite-Edit-v1e

status: torndown

timestamp: 2024-09-13T10:46:00+00:00

num_battles: 11249

num_wins: 5645

celo_rating: 1242.75

family_friendly_score: 0.0

submission_type: basic

model_repo: zonemercy/Elite-Edit-v1ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.617027556866772, 'latency_mean': 1.6206070411205291, 'latency_p50': 1.6223220825195312, 'latency_p90': 1.7818991422653199}, {'batch_size': 3, 'throughput': 1.0848782109686046, 'latency_mean': 2.760540224313736, 'latency_p50': 2.7698484659194946, 'latency_p90': 3.047167110443115}, {'batch_size': 5, 'throughput': 1.2199989685444015, 'latency_mean': 4.077194739580154, 'latency_p50': 4.067635655403137, 'latency_p90': 4.638349843025208}, {'batch_size': 6, 'throughput': 1.25264066759678, 'latency_mean': 4.7768803513050075, 'latency_p50': 4.787747621536255, 'latency_p90': 5.421133089065552}, {'batch_size': 8, 'throughput': 1.2304124519135087, 'latency_mean': 6.47463733792305, 'latency_p50': 6.5244529247283936, 'latency_p90': 7.326561045646668}, {'batch_size': 10, 'throughput': 1.1900644509810805, 'latency_mean': 8.366128926277161, 'latency_p50': 8.327866792678833, 'latency_p90': 9.503484058380128}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: zonemercy-elite-edit-v1ep1_v1

is_internal_developer: True

language_model: zonemercy/Elite-Edit-v1ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-13

win_ratio: 0.5018223842119299

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': True}

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-edit-v1ep1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Waiting for job on zonemercy-elite-edit-v1ep1-v1-mkmlizer to finish
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-elite-edit-v1ep1-v1-mkmlizer: ║                                                                     ║
zonemercy-elite-edit-v1ep1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-elite-edit-v1ep1-v1-mkmlizer: Downloaded to shared memory in 92.132s
zonemercy-elite-edit-v1ep1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjtelfuas, device:0
zonemercy-elite-edit-v1ep1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-elite-edit-v1ep1-v1-mkmlizer: quantized model in 39.376s
zonemercy-elite-edit-v1ep1-v1-mkmlizer: Processed model zonemercy/Elite-Edit-v1ep1 in 131.509s
zonemercy-elite-edit-v1ep1-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-elite-edit-v1ep1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-elite-edit-v1ep1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1
zonemercy-elite-edit-v1ep1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1/config.json
zonemercy-elite-edit-v1ep1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1/special_tokens_map.json
zonemercy-elite-edit-v1ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1/tokenizer_config.json
zonemercy-elite-edit-v1ep1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1/tokenizer.json
zonemercy-elite-edit-v1ep1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-elite-edit-v1ep1-v1/flywheel_model.0.safetensors
zonemercy-elite-edit-v1ep1-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.80it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 30.57it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:12, 27.06it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 37.87it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:14, 22.54it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 24.59it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.64it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.09it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.11it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 31.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.00it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.61it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.64it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 30.20it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.13it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.04it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.11it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.78it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.96it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 25.41it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.78it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 30.20it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:08, 29.56it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.87it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 29.90it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.23it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.61it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.30it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.25it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.68it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.09it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:06, 31.39it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:07, 27.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.27it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.77it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.13it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.64it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.48it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 22.54it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:06, 27.83it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:06, 25.87it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 32.54it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.84it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 33.35it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 32.04it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 32.25it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 28.36it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 28.17it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.97it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.87it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.55it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 30.52it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 32.55it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:03, 30.29it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.05it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.79it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.20it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:02, 29.00it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 31.96it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 31.02it/s]
Loading 0:  80%|████████  | 291/363 [00:09<00:02, 33.27it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.57it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.84it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 27.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 25.96it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:02, 24.57it/s]
Loading 0:  88%|████████▊ | 318/363 [00:10<00:01, 31.09it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 30.25it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.41it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.99it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.87it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 31.03it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.00it/s]
Loading 0:  96%|█████████▌| 348/363 [00:18<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:18<00:02,  3.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.10it/s]
                                                            
Job zonemercy-elite-edit-v1ep1-v1-mkmlizer completed after 157.05s with status: succeeded
Stopping job with name zonemercy-elite-edit-v1ep1-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-elite-edit-v1ep1-v1
Waiting for inference service zonemercy-elite-edit-v1ep1-v1 to be ready
Inference service zonemercy-elite-edit-v1ep1-v1 ready after 181.65208101272583s
Pipeline stage MKMLDeployer completed in 182.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.99558687210083s
Received healthy response to inference request in 1.842663288116455s
Received healthy response to inference request in 2.288234233856201s
Received healthy response to inference request in 2.244483709335327s
Received healthy response to inference request in 1.781219482421875s
5 requests
0 failed requests
5th percentile: 1.793508243560791
10th percentile: 1.805797004699707
20th percentile: 1.830374526977539
30th percentile: 1.9230273723602296
40th percentile: 2.083755540847778
50th percentile: 2.244483709335327
60th percentile: 2.2619839191436766
70th percentile: 2.2794841289520265
80th percentile: 2.429704761505127
90th percentile: 2.7126458168029783
95th percentile: 2.854116344451904
99th percentile: 2.967292766571045
mean time: 2.2304375171661377
Pipeline stage StressChecker completed in 14.73s
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 7.37s
Shutdown handler de-registered
zonemercy-elite-edit-v1ep1_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-elite-edit-v1ep1-v1-profiler
Waiting for inference service zonemercy-elite-edit-v1ep1-v1-profiler to be ready
Inference service zonemercy-elite-edit-v1ep1-v1-profiler ready after 180.44298267364502s
Pipeline stage MKMLProfilerDeployer completed in 181.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-elite-editf68348a08944a39aacb6508a22c6aebd-deplo524nk:/code/chaiverse_profiler_1726224945 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-elite-editf68348a08944a39aacb6508a22c6aebd-deplo524nk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726224945 && 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_1726224945/summary.json'
kubectl exec -it zonemercy-elite-editf68348a08944a39aacb6508a22c6aebd-deplo524nk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726224945/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1171.00s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-elite-edit-v1ep1-v1-profiler is running
Tearing down inference service zonemercy-elite-edit-v1ep1-v1-profiler
Service zonemercy-elite-edit-v1ep1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
zonemercy-elite-edit-v1ep1_v1 status is now inactive due to auto deactivation removed underperforming models
zonemercy-elite-edit-v1ep1_v1 status is now torndown due to DeploymentManager action