sanchuanhehe-adjusted-co_8671

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_8671_v1

model_name: sanchuanhehe-adjusted-co_8671_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:07:10+00:00

num_battles: 11298

num_wins: 4637

celo_rating: 1112.89

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_8_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': 1.1239834948957463, 'latency_mean': 0.8896208989620209, 'latency_p50': 0.8888556957244873, 'latency_p90': 0.9894088268280029}, {'batch_size': 5, 'throughput': 3.724618622678409, 'latency_mean': 1.3335894656181335, 'latency_p50': 1.3226152658462524, 'latency_p90': 1.4673942565917968}, {'batch_size': 10, 'throughput': 5.419967933405336, 'latency_mean': 1.8201946187019349, 'latency_p50': 1.8174993991851807, 'latency_p90': 2.0341304063797}, {'batch_size': 15, 'throughput': 6.393549622943961, 'latency_mean': 2.316528789997101, 'latency_p50': 2.3379383087158203, 'latency_p90': 2.6132450342178344}, {'batch_size': 20, 'throughput': 7.001537647576571, 'latency_mean': 2.810603930950165, 'latency_p50': 2.8094706535339355, 'latency_p90': 3.2077725172042846}, {'batch_size': 25, 'throughput': 7.465017187116468, 'latency_mean': 3.2891856694221495, 'latency_p50': 3.2676784992218018, 'latency_p90': 3.8591442346572875}, {'batch_size': 30, 'throughput': 7.631091036202036, 'latency_mean': 3.8526293790340422, 'latency_p50': 3.8398678302764893, 'latency_p90': 4.423469996452331}, {'batch_size': 35, 'throughput': 7.813532551180401, 'latency_mean': 4.3796929001808165, 'latency_p50': 4.379169821739197, 'latency_p90': 5.155831813812256}, {'batch_size': 40, 'throughput': 7.831523537306644, 'latency_mean': 4.935796700716018, 'latency_p50': 4.89563262462616, 'latency_p90': 5.661588048934936}, {'batch_size': 45, 'throughput': 7.7349751413907315, 'latency_mean': 5.564568514823914, 'latency_p50': 5.552304744720459, 'latency_p90': 6.385279822349548}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_8671_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_8_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.74

us_pacific_date: 2024-09-17

win_ratio: 0.410426624181271

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-8671-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-8671-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: Downloaded to shared memory in 29.742s
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqu7qv_is, device:0
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: quantized model in 17.422s
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_8_le in 47.165s
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/config.json
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/tokenizer.model
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/tokenizer.json
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8671-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-8671-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.77it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 71.03it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 78.02it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 81.95it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 81.50it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 82.89it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 82.87it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 83.94it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 83.58it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 85.38it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:08, 22.55it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:06, 27.09it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:05, 34.06it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 43.32it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 54.90it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 60.32it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:02, 65.01it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 74.66it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 72.58it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 75.01it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 77.10it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:03, 23.65it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:02, 30.03it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 36.88it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 43.18it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 51.02it/s]
Loading 0:  86%|████████▌ | 250/291 [00:04<00:00, 57.45it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 64.17it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 67.96it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.31it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 75.11it/s]
                                                            
Job sanchuanhehe-adjusted-co-8671-v1-mkmlizer completed after 72.94s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-8671-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-8671-v1
Waiting for inference service sanchuanhehe-adjusted-co-8671-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
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-8671-v1 ready after 171.42771553993225s
Pipeline stage MKMLDeployer completed in 171.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2397239208221436s
Received healthy response to inference request in 0.8853240013122559s
Received healthy response to inference request in 0.7973971366882324s
Received healthy response to inference request in 1.184389591217041s
Received healthy response to inference request in 1.7817556858062744s
5 requests
0 failed requests
5th percentile: 0.8149825096130371
10th percentile: 0.8325678825378418
20th percentile: 0.8677386283874512
30th percentile: 0.9451371192932129
40th percentile: 1.064763355255127
50th percentile: 1.184389591217041
60th percentile: 1.206523323059082
70th percentile: 1.228657054901123
80th percentile: 1.3481302738189698
90th percentile: 1.5649429798126222
95th percentile: 1.6733493328094482
99th percentile: 1.7600744152069092
mean time: 1.1777180671691894
Pipeline stage StressChecker completed in 8.18s
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 6.06s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8671_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-8671-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-8671-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-8671-v1-profiler ready after 180.45953273773193s
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-adjustea3f7482b4026dd1a8f43700453041832-deplotvnhj:/code/chaiverse_profiler_1726578909 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustea3f7482b4026dd1a8f43700453041832-deplotvnhj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578909 && 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_1726578909/summary.json'
kubectl exec -it sanchuanhehe-adjustea3f7482b4026dd1a8f43700453041832-deplotvnhj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578909/summary.json'
Pipeline stage MKMLProfilerRunner completed in 462.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-8671-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-8671-v1-profiler
Service sanchuanhehe-adjusted-co-8671-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8671_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_8671_v1 status is now torndown due to DeploymentManager action