chaiml-0919-virgo-top-bo_9296

developer_uid: azuruce

submission_id: chaiml-0919-virgo-top-bo_9296_v1

model_name: chaiml-0919-virgo-top-bo_9296_v1

model_group: ChaiML/0919-virgo-top-bo

status: torndown

timestamp: 2024-09-20T00:35:12+00:00

num_battles: 11628

num_wins: 5806

celo_rating: 1250.56

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/0919-virgo-top-bots5-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': 0.6151605354654444, 'latency_mean': 1.625518697500229, 'latency_p50': 1.6222189664840698, 'latency_p90': 1.7931740045547486}, {'batch_size': 3, 'throughput': 1.0716588511504093, 'latency_mean': 2.7943800723552705, 'latency_p50': 2.769507050514221, 'latency_p90': 3.0568461418151855}, {'batch_size': 5, 'throughput': 1.23380324445496, 'latency_mean': 4.040131614208222, 'latency_p50': 3.984107494354248, 'latency_p90': 4.550552415847778}, {'batch_size': 6, 'throughput': 1.2461678547786184, 'latency_mean': 4.786534571647644, 'latency_p50': 4.809285402297974, 'latency_p90': 5.402871537208557}, {'batch_size': 8, 'throughput': 1.2300341603002813, 'latency_mean': 6.474898910522461, 'latency_p50': 6.5514079332351685, 'latency_p90': 7.237283205986023}, {'batch_size': 10, 'throughput': 1.1966580425230318, 'latency_mean': 8.307400718927383, 'latency_p50': 8.377663850784302, 'latency_p90': 9.353014278411866}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-0919-virgo-top-bo_9296_v1

is_internal_developer: True

language_model: ChaiML/0919-virgo-top-bots5-albert

model_size: 13B

ranking_group: single

throughput_3p7s: 1.2

us_pacific_date: 2024-09-19

win_ratio: 0.499312005503956

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-0919-virgo-top-bo-9296-v1-mkmlizer
Waiting for job on chaiml-0919-virgo-top-bo-9296-v1-mkmlizer to finish
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║       /___/                                                         ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║                                                                     ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║                                                                     ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║                                                                     ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: ║                                                                     ║
chaiml-0919-virgo-top-bo-9296-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
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-0919-virgo-top-bo-9296-v1-mkmlizer: Downloaded to shared memory in 91.902s
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpasalam2v, device:0
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: quantized model in 41.007s
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: Processed model ChaiML/0919-virgo-top-bots5-albert in 132.909s
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1/config.json
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1/special_tokens_map.json
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1/tokenizer_config.json
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1/tokenizer.json
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0919-virgo-top-bo-9296-v1/flywheel_model.0.safetensors
chaiml-0919-virgo-top-bo-9296-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.84it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.70it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.80it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.67it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.05it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 22.09it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.71it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.00it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.50it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.00it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.83it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.64it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 29.28it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 28.84it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.03it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.76it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.20it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.17it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 27.58it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.72it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.11it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 25.45it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.36it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.73it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.42it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.41it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 28.41it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.19it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.20it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.79it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.23it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:06, 29.13it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 25.60it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.85it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.73it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 30.11it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.75it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.28it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 22.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 28.88it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 27.42it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:05, 29.45it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 27.89it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 27.76it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.55it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 22.69it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.91it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 26.69it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 24.70it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.15it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 28.73it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.81it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.89it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.32it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 22.39it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 29.70it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:02, 28.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.18it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.46it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.00it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 31.20it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 26.65it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.13it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.28it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.75it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.22it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.29it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 27.89it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 30.18it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.94it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.61it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.80it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.93it/s]
                                                            
Job chaiml-0919-virgo-top-bo-9296-v1-mkmlizer completed after 155.75s with status: succeeded
Stopping job with name chaiml-0919-virgo-top-bo-9296-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.31s
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 chaiml-0919-virgo-top-bo-9296-v1
Waiting for inference service chaiml-0919-virgo-top-bo-9296-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
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-0919-virgo-top-bo-9296-v1 ready after 201.5964412689209s
Pipeline stage MKMLDeployer completed in 202.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9980123043060303s
Received healthy response to inference request in 1.659053087234497s
Received healthy response to inference request in 2.3965067863464355s
Received healthy response to inference request in 1.7289865016937256s
Received healthy response to inference request in 2.2491960525512695s
5 requests
0 failed requests
5th percentile: 1.6730397701263429
10th percentile: 1.6870264530181884
20th percentile: 1.7149998188018798
30th percentile: 1.7827916622161866
40th percentile: 1.8904019832611083
50th percentile: 1.9980123043060303
60th percentile: 2.098485803604126
70th percentile: 2.198959302902222
80th percentile: 2.2786581993103026
90th percentile: 2.337582492828369
95th percentile: 2.3670446395874025
99th percentile: 2.3906143569946288
mean time: 2.006350946426392
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 5.89s
Shutdown handler de-registered
chaiml-0919-virgo-top-bo_9296_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 0.15s
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-0919-virgo-top-bo-9296-v1-profiler
Waiting for inference service chaiml-0919-virgo-top-bo-9296-v1-profiler to be ready
Inference service chaiml-0919-virgo-top-bo-9296-v1-profiler ready after 200.48563170433044s
Pipeline stage MKMLProfilerDeployer completed in 200.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-0919-virgo-to06bda69b26161246cf3faa8aaa0b9c63-deplos6kpf:/code/chaiverse_profiler_1726793133 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-0919-virgo-to06bda69b26161246cf3faa8aaa0b9c63-deplos6kpf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726793133 && 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_1726793133/summary.json'
kubectl exec -it chaiml-0919-virgo-to06bda69b26161246cf3faa8aaa0b9c63-deplos6kpf --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726793133/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1169.28s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-0919-virgo-top-bo-9296-v1-profiler is running
Tearing down inference service chaiml-0919-virgo-top-bo-9296-v1-profiler
Service chaiml-0919-virgo-top-bo-9296-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.18s
Shutdown handler de-registered
chaiml-0919-virgo-top-bo_9296_v1 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
chaiml-0919-virgo-top-bo_1691_v1 status is now torndown due to DeploymentManager action