sanchuanhehe-adjusted-co_183

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_183_v2

model_name: sanchuanhehe-adjusted-co_183_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:08:26+00:00

num_battles: 11231

num_wins: 4662

celo_rating: 1115.73

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_9_le

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 1.1324413919378093, 'latency_mean': 0.8829878449440003, 'latency_p50': 0.8926295042037964, 'latency_p90': 0.9819699287414551}, {'batch_size': 5, 'throughput': 3.6805268047427284, 'latency_mean': 1.3501086556911468, 'latency_p50': 1.3547332286834717, 'latency_p90': 1.5033868312835692}, {'batch_size': 10, 'throughput': 5.452501984026081, 'latency_mean': 1.8054018270969392, 'latency_p50': 1.808843970298767, 'latency_p90': 2.021467852592468}, {'batch_size': 15, 'throughput': 6.426903981513249, 'latency_mean': 2.290811403989792, 'latency_p50': 2.2760742902755737, 'latency_p90': 2.616520071029663}, {'batch_size': 20, 'throughput': 6.934826883826202, 'latency_mean': 2.844189782142639, 'latency_p50': 2.8345569372177124, 'latency_p90': 3.3186866283416747}, {'batch_size': 25, 'throughput': 7.326397766075275, 'latency_mean': 3.3442444002628324, 'latency_p50': 3.325712203979492, 'latency_p90': 3.8244467973709106}, {'batch_size': 30, 'throughput': 7.616406584507322, 'latency_mean': 3.8410782873630525, 'latency_p50': 3.7651283740997314, 'latency_p90': 4.626934480667113}, {'batch_size': 35, 'throughput': 7.821948213206005, 'latency_mean': 4.370950957536698, 'latency_p50': 4.333155155181885, 'latency_p90': 5.168414354324341}, {'batch_size': 40, 'throughput': 7.7310756124481825, 'latency_mean': 5.016719764471054, 'latency_p50': 5.047407031059265, 'latency_p90': 5.865268015861511}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_183_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_9_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.72

us_pacific_date: 2024-09-17

win_ratio: 0.41510105956726917

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-183-v2-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-183-v2-mkmlizer to finish
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
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-183-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-183-v2-mkmlizer: Downloaded to shared memory in 19.367s
sanchuanhehe-adjusted-co-183-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmvc0m4t_, device:0
sanchuanhehe-adjusted-co-183-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-183-v2-mkmlizer: quantized model in 18.435s
sanchuanhehe-adjusted-co-183-v2-mkmlizer: Processed model sanchuanhehe/adjusted_config_9_le in 37.802s
sanchuanhehe-adjusted-co-183-v2-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-183-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-183-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/config.json
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/tokenizer_config.json
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/special_tokens_map.json
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/tokenizer.model
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/tokenizer.json
sanchuanhehe-adjusted-co-183-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-183-v2/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-183-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.89it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 59.24it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 68.13it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 68.34it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 66.51it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 64.21it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 66.85it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 67.45it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 67.66it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:03, 67.96it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 70.24it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:09, 19.15it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:08, 21.93it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:06, 26.80it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:05, 32.44it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 38.56it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 43.97it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 48.26it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 54.05it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 60.16it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 64.42it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 65.69it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:01, 64.99it/s]
Loading 0:  70%|███████   | 204/291 [00:05<00:04, 21.00it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 24.30it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 31.12it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 37.49it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 43.53it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 48.88it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.01it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 56.07it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 63.94it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 21.30it/s]
                                                            
Job sanchuanhehe-adjusted-co-183-v2-mkmlizer completed after 62.78s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-183-v2-mkmlizer
Pipeline stage MKMLizer completed in 63.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-183-v2
Waiting for inference service sanchuanhehe-adjusted-co-183-v2 to be ready
Inference service sanchuanhehe-adjusted-co-183-v2 ready after 191.22916078567505s
Pipeline stage MKMLDeployer completed in 191.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5037856101989746s
Received healthy response to inference request in 1.0486705303192139s
Received healthy response to inference request in 1.936100959777832s
Received healthy response to inference request in 0.7745616436004639s
Received healthy response to inference request in 0.7798504829406738s
5 requests
0 failed requests
5th percentile: 0.7756194114685059
10th percentile: 0.7766771793365479
20th percentile: 0.7787927150726318
30th percentile: 0.8336144924163819
40th percentile: 0.9411425113677979
50th percentile: 1.0486705303192139
60th percentile: 1.230716562271118
70th percentile: 1.4127625942230224
80th percentile: 1.5902486801147462
90th percentile: 1.763174819946289
95th percentile: 1.8496378898620605
99th percentile: 1.9188083457946776
mean time: 1.2085938453674316
Pipeline stage StressChecker completed in 7.47s
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 4.08s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_183_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 0.14s
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-183-v2-profiler
Waiting for inference service sanchuanhehe-adjusted-co-183-v2-profiler to be ready
Inference service sanchuanhehe-adjusted-co-183-v2-profiler ready after 180.42725205421448s
Pipeline stage MKMLProfilerDeployer completed in 180.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustee5c85821731fbd2560f263aacfee5928-deplo6tqfs:/code/chaiverse_profiler_1726578998 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustee5c85821731fbd2560f263aacfee5928-deplo6tqfs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578998 && 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_1726578998/summary.json'
kubectl exec -it sanchuanhehe-adjustee5c85821731fbd2560f263aacfee5928-deplo6tqfs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578998/summary.json'
Pipeline stage MKMLProfilerRunner completed in 438.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-183-v2-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-183-v2-profiler
Service sanchuanhehe-adjusted-co-183-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_183_v2 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_183_v2 status is now torndown due to DeploymentManager action