chaiml-0918-horror-retor_3693

developer_uid: azuruce

submission_id: chaiml-0918-horror-retor_3693_v2

model_name: horror-retort

model_group: ChaiML/0918_horror_retor

status: torndown

timestamp: 2024-09-18T17:24:22+00:00

num_battles: 11790

num_wins: 5950

celo_rating: 1247.96

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: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6412931461601591, 'latency_mean': 1.5592525100708008, 'latency_p50': 1.5607585906982422, 'latency_p90': 1.7167394876480102}, {'batch_size': 3, 'throughput': 1.2479670790984214, 'latency_mean': 2.390788232088089, 'latency_p50': 2.3829392194747925, 'latency_p90': 2.6300514698028565}, {'batch_size': 5, 'throughput': 1.559966188826019, 'latency_mean': 3.194972152709961, 'latency_p50': 3.1762824058532715, 'latency_p90': 3.6569382190704345}, {'batch_size': 6, 'throughput': 1.6486642228058908, 'latency_mean': 3.6166401040554046, 'latency_p50': 3.6210362911224365, 'latency_p90': 4.086566925048828}, {'batch_size': 8, 'throughput': 1.757713716964669, 'latency_mean': 4.524649448394776, 'latency_p50': 4.495620608329773, 'latency_p90': 5.1258591413497925}, {'batch_size': 10, 'throughput': 1.791211526375178, 'latency_mean': 5.533935841321945, 'latency_p50': 5.586550831794739, 'latency_p90': 6.259087991714478}]

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: 1.67

us_pacific_date: 2024-09-18

win_ratio: 0.5046649703138253

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, '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-v2-mkmlizer
Waiting for job on chaiml-0918-horror-retor-3693-v2-mkmlizer to finish
chaiml-0918-horror-retor-3693-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║       /___/                                                         ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ║                                                                     ║
chaiml-0918-horror-retor-3693-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0918-horror-retor-3693-v2-mkmlizer: Downloaded to shared memory in 55.842s
chaiml-0918-horror-retor-3693-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_3c69b5t, device:0
chaiml-0918-horror-retor-3693-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0918-horror-retor-3693-v2-mkmlizer: quantized model in 41.915s
chaiml-0918-horror-retor-3693-v2-mkmlizer: Processed model ChaiML/0918_horror_retort_albert in 97.757s
chaiml-0918-horror-retor-3693-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0918-horror-retor-3693-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0918-horror-retor-3693-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v2
chaiml-0918-horror-retor-3693-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v2/config.json
chaiml-0918-horror-retor-3693-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v2/special_tokens_map.json
chaiml-0918-horror-retor-3693-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v2/tokenizer_config.json
chaiml-0918-horror-retor-3693-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0918-horror-retor-3693-v2/tokenizer.json
chaiml-0918-horror-retor-3693-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.61it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.85it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.08it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.84it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.59it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.27it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.92it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.07it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 26.95it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.77it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.31it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.34it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.21it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.06it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 29.16it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.16it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:10, 26.27it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.92it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.79it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:08, 30.92it/s]
Loading 0:  26%|██▋       | 96/363 [00:03<00:11, 23.54it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:10, 24.88it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:17, 15.09it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:15, 16.86it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 21.22it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.05it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.28it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.69it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 29.09it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.81it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:08, 27.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 23.95it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.81it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.45it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:07, 26.57it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.99it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:06, 28.91it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 25.47it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.40it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 25.14it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:07, 22.27it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 28.83it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.22it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.78it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.59it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.07it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:04, 30.40it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.39it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.40it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.24it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 29.37it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.46it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.16it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.91it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 22.14it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 29.11it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.43it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.18it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.55it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.00it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.46it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 30.32it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.27it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.62it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.26it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 31.24it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.85it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.84it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.17it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.83it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.95it/s]
                                                            
Job chaiml-0918-horror-retor-3693-v2-mkmlizer completed after 123.99s with status: succeeded
Stopping job with name chaiml-0918-horror-retor-3693-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.08s
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-v2
Waiting for inference service chaiml-0918-horror-retor-3693-v2 to be ready
Inference service chaiml-0918-horror-retor-3693-v2 ready after 190.45924639701843s
Pipeline stage MKMLDeployer completed in 190.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9578850269317627s
Received healthy response to inference request in 2.1540071964263916s
Received healthy response to inference request in 2.4273815155029297s
Received healthy response to inference request in 1.8021862506866455s
Received healthy response to inference request in 2.142073392868042s
5 requests
0 failed requests
5th percentile: 1.8333260059356689
10th percentile: 1.8644657611846924
20th percentile: 1.9267452716827393
30th percentile: 1.9947227001190186
40th percentile: 2.06839804649353
50th percentile: 2.142073392868042
60th percentile: 2.1468469142913817
70th percentile: 2.1516204357147215
80th percentile: 2.208682060241699
90th percentile: 2.3180317878723145
95th percentile: 2.372706651687622
99th percentile: 2.4164465427398683
mean time: 2.096706676483154
Pipeline stage StressChecker completed in 11.01s
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 3.97s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0918-horror-retor-3693-v2-profiler
Waiting for inference service chaiml-0918-horror-retor-3693-v2-profiler to be ready
Inference service chaiml-0918-horror-retor-3693-v2-profiler ready after 190.4717996120453s
Pipeline stage MKMLProfilerDeployer completed in 190.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-0918-horror-rc2fab1845d9c45e9e5b7fdd1754d2785-deplok4hcz:/code/chaiverse_profiler_1726680838 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-0918-horror-rc2fab1845d9c45e9e5b7fdd1754d2785-deplok4hcz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726680838 && python profiles.py profile --best_of_n 4 --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_1726680838/summary.json'
kubectl exec -it chaiml-0918-horror-rc2fab1845d9c45e9e5b7fdd1754d2785-deplok4hcz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726680838/summary.json'
Pipeline stage MKMLProfilerRunner completed in 953.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-0918-horror-retor-3693-v2-profiler is running
Tearing down inference service chaiml-0918-horror-retor-3693-v2-profiler
Service chaiml-0918-horror-retor-3693-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
Shutdown handler de-registered
chaiml-0918-horror-retor_3693_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 3.09s
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_5943_v1
Pipeline stage MKMLDeleter completed in 3.52s
Pipeline stage %s skipped, reason=%s
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 3.03s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0919-virgo-top-bo_5943_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 5.56s
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
run pipeline stage %s
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_9526_v1
admin requested tearing down of chaiml-0918-horror-retor_3693_v2
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
admin requested tearing down of chaiml-0918-horror-retor_3693_v3
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
run pipeline %s
Pipeline stage MKMLDeleter completed in 0.23s
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 0.21s
Pipeline stage MKMLModelDeleter completed in 0.22s
run pipeline stage %s
Shutdown handler de-registered
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 0.74s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0919-virgo-top-bo_5943_v1
Pipeline stage MKMLModelDeleter completed in 8.08s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 8.12s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
chaiml-0918-horror-retor_3693_v2 status is now torndown due to DeploymentManager action
run pipeline stage %s
run pipeline %s