chaiml-0918-horror-retor_3693

developer_uid: azuruce

submission_id: chaiml-0918-horror-retor_3693_v4

model_name: horror-retort

model_group: ChaiML/0918_horror_retor

status: torndown

timestamp: 2024-09-20T01:54:49+00:00

num_battles: 14071

num_wins: 7092

celo_rating: 1254.5

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/0918_horror_retort_albert

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6104882547749341, 'latency_mean': 1.6379527568817138, 'latency_p50': 1.6477398872375488, 'latency_p90': 1.807578730583191}, {'batch_size': 3, 'throughput': 1.0745967312070919, 'latency_mean': 2.7839358580112457, 'latency_p50': 2.755465030670166, 'latency_p90': 3.087920880317688}, {'batch_size': 5, 'throughput': 1.2265127585234024, 'latency_mean': 4.0591169404983525, 'latency_p50': 4.038105130195618, 'latency_p90': 4.548490071296691}, {'batch_size': 6, 'throughput': 1.2517478265548194, 'latency_mean': 4.76725594162941, 'latency_p50': 4.758797645568848, 'latency_p90': 5.2715349197387695}, {'batch_size': 8, 'throughput': 1.256771686995735, 'latency_mean': 6.319846878051758, 'latency_p50': 6.349033236503601, 'latency_p90': 7.136085200309753}, {'batch_size': 10, 'throughput': 1.2106069444559817, 'latency_mean': 8.21602199435234, 'latency_p50': 8.228159070014954, 'latency_p90': 9.265300965309143}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: horror-retort

is_internal_developer: True

language_model: ChaiML/0918_horror_retort_albert

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-19

win_ratio: 0.5040153507213417

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', '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 chaiml-0918-horror-retor-3693-v4-mkmlizer
Waiting for job on chaiml-0918-horror-retor-3693-v4-mkmlizer to finish
chaiml-0918-horror-retor-3693-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║       /___/                                                         ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-0918-horror-retor-3693-v4-mkmlizer: Downloaded to shared memory in 87.722s
chaiml-0918-horror-retor-3693-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2xaud0ri, device:0
chaiml-0918-horror-retor-3693-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0918-horror-retor-3693-v4-mkmlizer: quantized model in 41.150s
chaiml-0918-horror-retor-3693-v4-mkmlizer: Processed model ChaiML/0918_horror_retort_albert in 128.873s
chaiml-0918-horror-retor-3693-v4-mkmlizer: creating bucket guanaco-mkml-models
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-0918-horror-retor-3693-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0918-horror-retor-3693-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4
chaiml-0918-horror-retor-3693-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4/config.json
chaiml-0918-horror-retor-3693-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4/special_tokens_map.json
chaiml-0918-horror-retor-3693-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4/tokenizer_config.json
chaiml-0918-horror-retor-3693-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4/tokenizer.json
chaiml-0918-horror-retor-3693-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v4/flywheel_model.0.safetensors
chaiml-0918-horror-retor-3693-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.66it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.58it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.27it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.24it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.83it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.57it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 28.16it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.15it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.17it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.77it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 29.87it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.02it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.50it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 29.03it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.85it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.50it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.61it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.21it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.29it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.49it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.31it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 20.51it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 25.77it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.49it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.01it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.64it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.25it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.46it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.72it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:08, 27.89it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.67it/s]
Loading 0:  40%|███▉      | 144/363 [00:05<00:11, 18.62it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:09, 21.91it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 22.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 25.71it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:08, 23.50it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 28.20it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.46it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.15it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 24.33it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 29.18it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.10it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 25.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.76it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 28.95it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 28.29it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.87it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.55it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.42it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 31.26it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 22.25it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.58it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.33it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 27.74it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 29.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:04, 28.10it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 29.63it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.44it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.44it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.07it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.93it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.95it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.14it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.75it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 29.54it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.13it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.69it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.06it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.62it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.21it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.73it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.36it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.97it/s]
                                                            
Job chaiml-0918-horror-retor-3693-v4-mkmlizer completed after 156.96s with status: succeeded
Stopping job with name chaiml-0918-horror-retor-3693-v4-mkmlizer
Pipeline stage MKMLizer completed in 159.17s
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 chaiml-0918-horror-retor-3693-v4
Waiting for inference service chaiml-0918-horror-retor-3693-v4 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
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
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 chaiml-0918-horror-retor-3693-v4 ready after 200.98856616020203s
Pipeline stage MKMLDeployer completed in 201.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1608030796051025s
Received healthy response to inference request in 1.572204351425171s
Received healthy response to inference request in 3.0338263511657715s
Received healthy response to inference request in 2.448698043823242s
Received healthy response to inference request in 1.5311369895935059s
5 requests
0 failed requests
5th percentile: 1.5393504619598388
10th percentile: 1.5475639343261718
20th percentile: 1.563990879058838
30th percentile: 1.6899240970611573
40th percentile: 1.92536358833313
50th percentile: 2.1608030796051025
60th percentile: 2.2759610652923583
70th percentile: 2.391119050979614
80th percentile: 2.5657237052917483
90th percentile: 2.7997750282287597
95th percentile: 2.9168006896972654
99th percentile: 3.0104212188720703
mean time: 2.1493337631225584
Pipeline stage StressChecker completed in 11.53s
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 7.36s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v4 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0918-horror-retor-3693-v4-profiler
Waiting for inference service chaiml-0918-horror-retor-3693-v4-profiler to be ready
Inference service chaiml-0918-horror-retor-3693-v4-profiler ready after 210.79549884796143s
Pipeline stage MKMLProfilerDeployer completed in 211.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-0918-horror-r6f1af45df575ba4b9b5070e60706f9d9-deplohqh5w:/code/chaiverse_profiler_1726797923 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-0918-horror-r6f1af45df575ba4b9b5070e60706f9d9-deplohqh5w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726797923 && 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_1726797923/summary.json'
kubectl exec -it chaiml-0918-horror-r6f1af45df575ba4b9b5070e60706f9d9-deplohqh5w --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726797923/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1165.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-0918-horror-retor-3693-v4-profiler is running
Tearing down inference service chaiml-0918-horror-retor-3693-v4-profiler
Service chaiml-0918-horror-retor-3693-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.18s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v4 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler de-registered
Checking if service chaiml-albert-dpo-0912-v-5607-v2 is running
chaiml-0918-horror-retor_3693_v4 status is now torndown due to DeploymentManager action
run pipeline stage %s
chaiml-0919-virgo-top-bo_1691_v1 status is now torndown due to DeploymentManager action