sanchuanhehe-adjusted-co_6142

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_6142_v1

model_name: sanchuanhehe-adjusted-co_6142_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:10:37+00:00

num_battles: 11018

num_wins: 4566

celo_rating: 1114.66

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_16_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': 1.1129817422595014, 'latency_mean': 0.8983872306346893, 'latency_p50': 0.8980762958526611, 'latency_p90': 1.0011521100997924}, {'batch_size': 5, 'throughput': 3.647972827790285, 'latency_mean': 1.3550310492515565, 'latency_p50': 1.3578320741653442, 'latency_p90': 1.5074618339538575}, {'batch_size': 10, 'throughput': 5.327104518940745, 'latency_mean': 1.8549659955501556, 'latency_p50': 1.8369970321655273, 'latency_p90': 2.1014143943786623}, {'batch_size': 15, 'throughput': 6.386644967554914, 'latency_mean': 2.3176378798484802, 'latency_p50': 2.287696957588196, 'latency_p90': 2.7003160238265993}, {'batch_size': 20, 'throughput': 6.883581415201314, 'latency_mean': 2.8573743784427643, 'latency_p50': 2.85165274143219, 'latency_p90': 3.2761717796325684}, {'batch_size': 25, 'throughput': 7.196586745361032, 'latency_mean': 3.401470220088959, 'latency_p50': 3.3572328090667725, 'latency_p90': 4.005573964118957}, {'batch_size': 30, 'throughput': 7.55576306077017, 'latency_mean': 3.872570550441742, 'latency_p50': 3.8559317588806152, 'latency_p90': 4.536614871025085}, {'batch_size': 35, 'throughput': 7.64843652142006, 'latency_mean': 4.459520574808121, 'latency_p50': 4.467439413070679, 'latency_p90': 5.279999661445617}, {'batch_size': 40, 'throughput': 7.601975493145134, 'latency_mean': 5.097286603450775, 'latency_p50': 5.054346561431885, 'latency_p90': 6.023025608062744}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_6142_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_16_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.61

us_pacific_date: 2024-09-17

win_ratio: 0.41441277908876384

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-6142-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-6142-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: Downloaded to shared memory in 40.729s
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpasmuznud, device:0
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: quantized model in 17.994s
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_16_l in 58.723s
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/config.json
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/tokenizer.model
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/tokenizer.json
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6142-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-6142-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 38.67it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 57.69it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 67.04it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 72.39it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 76.23it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 77.78it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 73.90it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 77.38it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:02, 75.29it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:02, 76.81it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 80.12it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:09, 20.70it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:06, 26.78it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 33.57it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 40.80it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 48.23it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 54.86it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 60.84it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 66.53it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 68.60it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 69.57it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:01, 70.42it/s]
Loading 0:  69%|██████▉   | 202/291 [00:03<00:01, 72.06it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:03, 21.43it/s]
Loading 0:  74%|███████▍  | 216/291 [00:04<00:03, 24.03it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 28.36it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 36.25it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 44.06it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 50.64it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 58.42it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 65.03it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 70.67it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 70.49it/s]
                                                            
Job sanchuanhehe-adjusted-co-6142-v1-mkmlizer completed after 84.02s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-6142-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.02s
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 sanchuanhehe-adjusted-co-6142-v1
Waiting for inference service sanchuanhehe-adjusted-co-6142-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
Inference service sanchuanhehe-adjusted-co-6142-v1 ready after 181.20409488677979s
Pipeline stage MKMLDeployer completed in 181.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.071568489074707s
Received healthy response to inference request in 1.3233811855316162s
Received healthy response to inference request in 1.0034661293029785s
Received healthy response to inference request in 0.7419817447662354s
Received healthy response to inference request in 0.5558006763458252s
5 requests
0 failed requests
5th percentile: 0.5930368900299072
10th percentile: 0.6302731037139893
20th percentile: 0.7047455310821533
30th percentile: 0.794278621673584
40th percentile: 0.8988723754882812
50th percentile: 1.0034661293029785
60th percentile: 1.1314321517944337
70th percentile: 1.2593981742858886
80th percentile: 1.4730186462402346
90th percentile: 1.7722935676574707
95th percentile: 1.9219310283660886
99th percentile: 2.0416409969329834
mean time: 1.1392396450042725
Pipeline stage StressChecker completed in 6.51s
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 5.86s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6142_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 0.12s
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-6142-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-6142-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-6142-v1-profiler ready after 210.4671881198883s
Pipeline stage MKMLProfilerDeployer completed in 210.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste07fb1c221cf6e7b8275b4b328c9ddbd7-deplo5ns49:/code/chaiverse_profiler_1726579170 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste07fb1c221cf6e7b8275b4b328c9ddbd7-deplo5ns49 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579170 && 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_1726579170/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste07fb1c221cf6e7b8275b4b328c9ddbd7-deplo5ns49:/code/chaiverse_profiler_1726579177 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste07fb1c221cf6e7b8275b4b328c9ddbd7-deplo5ns49 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579177 && 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_1726579177/summary.json'
kubectl exec -it sanchuanhehe-adjuste07fb1c221cf6e7b8275b4b328c9ddbd7-deplo5ns49 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579177/summary.json'
Pipeline stage MKMLProfilerRunner completed in 452.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-6142-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-6142-v1-profiler
Service sanchuanhehe-adjusted-co-6142-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6142_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_6142_v1 status is now torndown due to DeploymentManager action