sanchuanhehe-adjusted-co_9679

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_9679_v1

model_name: sanchuanhehe-adjusted-co_9679_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:13:54+00:00

num_battles: 10915

num_wins: 4455

celo_rating: 1110.27

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_28_l

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 1.107710698070783, 'latency_mean': 0.9026791405677795, 'latency_p50': 0.899345874786377, 'latency_p90': 0.9961178302764893}, {'batch_size': 5, 'throughput': 3.626532589104155, 'latency_mean': 1.365379923582077, 'latency_p50': 1.3592634201049805, 'latency_p90': 1.5414751529693604}, {'batch_size': 10, 'throughput': 5.355342596170271, 'latency_mean': 1.842676191329956, 'latency_p50': 1.8201149702072144, 'latency_p90': 2.0861425399780273}, {'batch_size': 15, 'throughput': 6.26367003090025, 'latency_mean': 2.358712248802185, 'latency_p50': 2.3569247722625732, 'latency_p90': 2.744546580314636}, {'batch_size': 20, 'throughput': 6.876672409217411, 'latency_mean': 2.8683947825431826, 'latency_p50': 2.8130615949630737, 'latency_p90': 3.3934433221817017}, {'batch_size': 25, 'throughput': 7.222459629071269, 'latency_mean': 3.392384387254715, 'latency_p50': 3.393323540687561, 'latency_p90': 4.024225354194641}, {'batch_size': 30, 'throughput': 7.4173802371348865, 'latency_mean': 3.973605362176895, 'latency_p50': 3.9713833332061768, 'latency_p90': 4.722550868988037}, {'batch_size': 35, 'throughput': 7.55608552411279, 'latency_mean': 4.50646693944931, 'latency_p50': 4.402765512466431, 'latency_p90': 5.445213222503662}, {'batch_size': 40, 'throughput': 7.601525729856916, 'latency_mean': 5.112474105358124, 'latency_p50': 5.1045098304748535, 'latency_p90': 5.916563248634338}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_9679_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_28_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.47

us_pacific_date: 2024-09-17

win_ratio: 0.4081539166284929

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 sanchuanhehe-adjusted-co-9679-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-9679-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: Downloaded to shared memory in 30.665s
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmped1eenmt, device:0
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: quantized model in 18.513s
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_28_l in 49.178s
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/config.json
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/tokenizer.model
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/tokenizer.json
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9679-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-9679-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 47.92it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:05, 54.85it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 61.45it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 65.46it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 69.09it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 68.79it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 67.71it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 67.03it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 64.83it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:03, 64.95it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:03, 64.06it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:10, 18.50it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 23.20it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:06, 27.17it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:05, 29.37it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 35.82it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 41.89it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:03, 45.23it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 50.19it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 54.97it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 57.34it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:01, 60.69it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:01, 61.96it/s]
Loading 0:  70%|███████   | 204/291 [00:05<00:04, 20.86it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 24.41it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 30.41it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 36.38it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 41.07it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 45.50it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 48.54it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 50.50it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 47.51it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 51.88it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 56.89it/s]
                                                            
Job sanchuanhehe-adjusted-co-9679-v1-mkmlizer completed after 75.23s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-9679-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-9679-v1
Waiting for inference service sanchuanhehe-adjusted-co-9679-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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service sanchuanhehe-adjusted-co-9679-v1 ready after 191.83483457565308s
Pipeline stage MKMLDeployer completed in 192.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.15376615524292s
Received healthy response to inference request in 1.0621037483215332s
Received healthy response to inference request in 0.645068883895874s
Received healthy response to inference request in 2.060297727584839s
Received healthy response to inference request in 2.250121831893921s
5 requests
0 failed requests
5th percentile: 0.7284758567810059
10th percentile: 0.8118828296661377
20th percentile: 0.9786967754364014
30th percentile: 1.0804362297058105
40th percentile: 1.1171011924743652
50th percentile: 1.15376615524292
60th percentile: 1.5163787841796874
70th percentile: 1.878991413116455
80th percentile: 2.0982625484466553
90th percentile: 2.174192190170288
95th percentile: 2.2121570110321045
99th percentile: 2.242528867721558
mean time: 1.4342716693878175
Pipeline stage StressChecker completed in 7.90s
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 3.94s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9679_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 0.13s
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 sanchuanhehe-adjusted-co-9679-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-9679-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-9679-v1-profiler ready after 190.4358615875244s
Pipeline stage MKMLProfilerDeployer completed in 190.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustea87284fcf09dccc489f226d03982a65f-deplo2gtt9:/code/chaiverse_profiler_1726579341 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustea87284fcf09dccc489f226d03982a65f-deplo2gtt9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579341 && python profiles.py profile --best_of_n 1 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726579341/summary.json'
kubectl exec -it sanchuanhehe-adjustea87284fcf09dccc489f226d03982a65f-deplo2gtt9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579341/summary.json'
Pipeline stage MKMLProfilerRunner completed in 445.68s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-9679-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-9679-v1-profiler
Service sanchuanhehe-adjusted-co-9679-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9679_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_9679_v1 status is now torndown due to DeploymentManager action