sanchuanhehe-adjusted-co_8423

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_8423_v1

model_name: sanchuanhehe-adjusted-co_8423_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:14:49+00:00

num_battles: 10673

num_wins: 4432

celo_rating: 1114.48

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_32_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': 1.105702537627083, 'latency_mean': 0.9043247473239898, 'latency_p50': 0.9057915210723877, 'latency_p90': 1.0116939783096313}, {'batch_size': 5, 'throughput': 3.6228583443180877, 'latency_mean': 1.3670395922660827, 'latency_p50': 1.3624823093414307, 'latency_p90': 1.508504319190979}, {'batch_size': 10, 'throughput': 5.327556279396407, 'latency_mean': 1.8596353471279143, 'latency_p50': 1.8526408672332764, 'latency_p90': 2.133730387687683}, {'batch_size': 15, 'throughput': 6.260740462948052, 'latency_mean': 2.360952970981598, 'latency_p50': 2.3487820625305176, 'latency_p90': 2.699637937545776}, {'batch_size': 20, 'throughput': 6.713256985306652, 'latency_mean': 2.935704505443573, 'latency_p50': 2.92724871635437, 'latency_p90': 3.4330140352249146}, {'batch_size': 25, 'throughput': 7.164487223578173, 'latency_mean': 3.4302661442756652, 'latency_p50': 3.399585247039795, 'latency_p90': 3.9442123174667354}, {'batch_size': 30, 'throughput': 7.262217323226089, 'latency_mean': 4.039518556594849, 'latency_p50': 4.038622856140137, 'latency_p90': 4.77670874595642}, {'batch_size': 35, 'throughput': 7.416824371806998, 'latency_mean': 4.601713176965713, 'latency_p50': 4.465876221656799, 'latency_p90': 5.7071738719940175}, {'batch_size': 40, 'throughput': 7.472072525370693, 'latency_mean': 5.181148021221161, 'latency_p50': 5.15518581867218, 'latency_p90': 6.035632133483887}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_8423_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_32_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.36

us_pacific_date: 2024-09-17

win_ratio: 0.4152534432680596

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-8423-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-8423-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8423-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
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: Downloaded to shared memory in 30.552s
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeuhu7wnq, device:0
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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', '')
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: quantized model in 18.237s
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_32_l in 48.789s
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/config.json
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/tokenizer.model
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/tokenizer.json
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8423-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-8423-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 42.85it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 56.95it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 63.99it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 67.25it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 66.74it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 68.98it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 71.99it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 70.54it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 70.01it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 68.57it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 68.67it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:10, 18.63it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 23.98it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 31.10it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:04, 38.50it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 45.53it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:02, 55.32it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 60.80it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 65.43it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 70.87it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:01, 77.68it/s]
Loading 0:  68%|██████▊   | 197/291 [00:03<00:01, 77.38it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:03, 21.71it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 31.20it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 37.21it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 42.36it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 47.93it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.88it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 60.52it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 64.64it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 68.99it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.88it/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
Job sanchuanhehe-adjusted-co-8423-v1-mkmlizer completed after 83.54s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-8423-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-8423-v1
Waiting for inference service sanchuanhehe-adjusted-co-8423-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
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
Inference service sanchuanhehe-adjusted-co-8423-v1 ready after 191.07191920280457s
Pipeline stage MKMLDeployer completed in 191.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0880701541900635s
Received healthy response to inference request in 1.2165460586547852s
Received healthy response to inference request in 0.8250961303710938s
Received healthy response to inference request in 0.629340648651123s
Received healthy response to inference request in 1.2901532649993896s
5 requests
0 failed requests
5th percentile: 0.6684917449951172
10th percentile: 0.7076428413391114
20th percentile: 0.7859450340270996
30th percentile: 0.903386116027832
40th percentile: 1.0599660873413086
50th percentile: 1.2165460586547852
60th percentile: 1.245988941192627
70th percentile: 1.2754318237304687
80th percentile: 1.4497366428375247
90th percentile: 1.768903398513794
95th percentile: 1.9284867763519284
99th percentile: 2.0561534786224365
mean time: 1.209841251373291
Pipeline stage StressChecker completed in 7.71s
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 4.42s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8423_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-8423-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-8423-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-8423-v1-profiler ready after 190.47020387649536s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste07b78f2cbdbfe85dab310e346d2afc22-deplo2svrd:/code/chaiverse_profiler_1726579405 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste07b78f2cbdbfe85dab310e346d2afc22-deplo2svrd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579405 && 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_1726579405/summary.json'
kubectl exec -it sanchuanhehe-adjuste07b78f2cbdbfe85dab310e346d2afc22-deplo2svrd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579405/summary.json'
Pipeline stage MKMLProfilerRunner completed in 450.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-8423-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-8423-v1-profiler
Service sanchuanhehe-adjusted-co-8423-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8423_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_8423_v1 status is now torndown due to DeploymentManager action