sanchuanhehe-adjusted-co_2116

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_2116_v1

model_name: sanchuanhehe-adjusted-co_2116_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:11:31+00:00

num_battles: 9661

num_wins: 4098

celo_rating: 1120.54

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_20_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': 1.1134239928723517, 'latency_mean': 0.8980409395694733, 'latency_p50': 0.902169942855835, 'latency_p90': 1.0051572799682618}, {'batch_size': 5, 'throughput': 3.615903264132154, 'latency_mean': 1.3719546949863435, 'latency_p50': 1.3705809116363525, 'latency_p90': 1.5189836978912352}, {'batch_size': 10, 'throughput': 5.3222141211886145, 'latency_mean': 1.856097184419632, 'latency_p50': 1.8632279634475708, 'latency_p90': 2.118638253211975}, {'batch_size': 15, 'throughput': 6.215747649748148, 'latency_mean': 2.369749779701233, 'latency_p50': 2.3647186756134033, 'latency_p90': 2.6555231571197506}, {'batch_size': 20, 'throughput': 6.843837134453875, 'latency_mean': 2.8788453578948974, 'latency_p50': 2.8953808546066284, 'latency_p90': 3.3364922761917115}, {'batch_size': 25, 'throughput': 7.155220437404078, 'latency_mean': 3.431371051073074, 'latency_p50': 3.4308664798736572, 'latency_p90': 3.9866423845291137}, {'batch_size': 30, 'throughput': 7.352825152910454, 'latency_mean': 3.9899368691444397, 'latency_p50': 4.024590849876404, 'latency_p90': 4.793725681304932}, {'batch_size': 35, 'throughput': 7.4908235133087855, 'latency_mean': 4.5642468392848965, 'latency_p50': 4.527248740196228, 'latency_p90': 5.483100199699402}, {'batch_size': 40, 'throughput': 7.38154084005209, 'latency_mean': 5.259912748336792, 'latency_p50': 5.158109784126282, 'latency_p90': 6.156328034400939}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_2116_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_20_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.41

us_pacific_date: 2024-09-17

win_ratio: 0.42417969154331847

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-2116-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2116-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: Downloaded to shared memory in 31.081s
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi6zw27w2, device:0
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: quantized model in 18.273s
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_20_l in 49.354s
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/config.json
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/tokenizer.model
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/tokenizer.json
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2116-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2116-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 44.06it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 61.71it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 81.64it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 74.31it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 76.47it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 73.63it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 69.13it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 67.09it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:03, 65.13it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 69.34it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:09, 20.94it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:07, 23.90it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 29.08it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:04, 35.14it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 41.20it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 47.73it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 51.64it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 53.05it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 53.78it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 60.01it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 60.98it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 65.58it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:04, 20.85it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 24.36it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 30.26it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 36.13it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 41.91it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 45.52it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 49.84it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 56.04it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 61.34it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 64.21it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.16it/s]
                                                            
Job sanchuanhehe-adjusted-co-2116-v1-mkmlizer completed after 75.54s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2116-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-2116-v1
Waiting for inference service sanchuanhehe-adjusted-co-2116-v1 to be ready
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', '')
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 sanchuanhehe-adjusted-co-2116-v1 ready after 190.92590379714966s
Pipeline stage MKMLDeployer completed in 191.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8741223812103271s
Received healthy response to inference request in 1.4976072311401367s
Received healthy response to inference request in 0.8023662567138672s
Received healthy response to inference request in 1.3640918731689453s
Received healthy response to inference request in 0.9132218360900879s
5 requests
0 failed requests
5th percentile: 0.8245373725891113
10th percentile: 0.8467084884643554
20th percentile: 0.8910507202148438
30th percentile: 1.0033958435058594
40th percentile: 1.1837438583374025
50th percentile: 1.3640918731689453
60th percentile: 1.4174980163574218
70th percentile: 1.4709041595458985
80th percentile: 1.572910261154175
90th percentile: 1.723516321182251
95th percentile: 1.7988193511962889
99th percentile: 1.8590617752075196
mean time: 1.2902819156646728
Pipeline stage StressChecker completed in 7.26s
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 5.20s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2116_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 sanchuanhehe-adjusted-co-2116-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-2116-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-2116-v1-profiler ready after 200.45461416244507s
Pipeline stage MKMLProfilerDeployer completed in 200.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste066e6c76a7218c4d101b03785d08baf9-deplodw8k2:/code/chaiverse_profiler_1726579213 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste066e6c76a7218c4d101b03785d08baf9-deplodw8k2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579213 && 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_1726579213/summary.json'
kubectl exec -it sanchuanhehe-adjuste066e6c76a7218c4d101b03785d08baf9-deplodw8k2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579213/summary.json'
Pipeline stage MKMLProfilerRunner completed in 448.63s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-2116-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-2116-v1-profiler
Service sanchuanhehe-adjusted-co-2116-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2116_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_2116_v1 status is now torndown due to DeploymentManager action