sanchuanhehe-adjusted-co_9723

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_9723_v1

model_name: sanchuanhehe-adjusted-co_9723_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:08:42+00:00

num_battles: 11136

num_wins: 4631

celo_rating: 1114.77

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_10_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': 1.125064234526692, 'latency_mean': 0.8887456715106964, 'latency_p50': 0.8914036750793457, 'latency_p90': 0.999433159828186}, {'batch_size': 5, 'throughput': 3.6977069486946847, 'latency_mean': 1.3489846193790436, 'latency_p50': 1.3411167860031128, 'latency_p90': 1.505934476852417}, {'batch_size': 10, 'throughput': 5.399130082198436, 'latency_mean': 1.8327374958992004, 'latency_p50': 1.8203034400939941, 'latency_p90': 2.0687309741973876}, {'batch_size': 15, 'throughput': 6.3917216593255075, 'latency_mean': 2.314779270887375, 'latency_p50': 2.3165172338485718, 'latency_p90': 2.655699849128723}, {'batch_size': 20, 'throughput': 6.917649805968956, 'latency_mean': 2.8482184982299805, 'latency_p50': 2.8300840854644775, 'latency_p90': 3.244044065475464}, {'batch_size': 25, 'throughput': 7.393829857248257, 'latency_mean': 3.3243810927867887, 'latency_p50': 3.317957282066345, 'latency_p90': 3.8331186056137083}, {'batch_size': 30, 'throughput': 7.503136791366208, 'latency_mean': 3.903978219032288, 'latency_p50': 3.921628713607788, 'latency_p90': 4.512692928314208}, {'batch_size': 35, 'throughput': 7.752568231010084, 'latency_mean': 4.3989180779457095, 'latency_p50': 4.374522924423218, 'latency_p90': 5.265259337425231}, {'batch_size': 40, 'throughput': 7.680517300466374, 'latency_mean': 5.032543649673462, 'latency_p50': 5.058542847633362, 'latency_p90': 6.011740016937256}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_9723_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_10_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.63

us_pacific_date: 2024-09-17

win_ratio: 0.41585847701149425

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-9723-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-9723-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: Downloaded to shared memory in 30.755s
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbhci2ysm, device:0
sanchuanhehe-adjusted-co-9723-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-9723-v1-mkmlizer: quantized model in 17.604s
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_10_l in 48.360s
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/config.json
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/tokenizer.model
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/tokenizer.json
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-9723-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-9723-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.29it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 71.02it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:03, 82.51it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 89.58it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 92.29it/s]
Loading 0:  21%|██        | 60/291 [00:00<00:02, 93.08it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 84.27it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 84.42it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 82.32it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 76.95it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:08, 21.22it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:06, 27.60it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 32.38it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 40.58it/s]
Loading 0:  48%|████▊     | 140/291 [00:02<00:02, 50.54it/s]
Loading 0:  52%|█████▏    | 150/291 [00:02<00:02, 60.11it/s]
Loading 0:  55%|█████▍    | 159/291 [00:02<00:02, 65.32it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 70.55it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 70.60it/s]
Loading 0:  64%|██████▍   | 187/291 [00:03<00:01, 68.92it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 72.69it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:04, 20.88it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:03, 25.22it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:02, 32.62it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 40.20it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:01, 49.93it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 55.46it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 62.02it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 62.50it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 63.60it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 64.36it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 17.11it/s]
                                                            
Job sanchuanhehe-adjusted-co-9723-v1-mkmlizer completed after 73.13s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-9723-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-9723-v1
Waiting for inference service sanchuanhehe-adjusted-co-9723-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
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', '')
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-9723-v1 ready after 171.45425605773926s
Pipeline stage MKMLDeployer completed in 172.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8537218570709229s
Received healthy response to inference request in 1.4978206157684326s
Received healthy response to inference request in 0.9007771015167236s
Received healthy response to inference request in 0.9215850830078125s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.458364486694336s
5 requests
0 failed requests
5th percentile: 0.9049386978149414
10th percentile: 0.9091002941131592
20th percentile: 0.9174234867095947
30th percentile: 1.0289409637451172
40th percentile: 1.2436527252197267
50th percentile: 1.458364486694336
60th percentile: 1.4741469383239747
70th percentile: 1.4899293899536132
80th percentile: 1.5690008640289308
90th percentile: 1.7113613605499267
95th percentile: 1.7825416088104247
99th percentile: 1.8394858074188232
mean time: 1.3264538288116454
Pipeline stage StressChecker completed in 7.52s
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 4.66s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9723_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-9723-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-9723-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-9723-v1-profiler ready after 180.4134120941162s
Pipeline stage MKMLProfilerDeployer completed in 180.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjusted25294a32531d269b6fce0cff0cb6d6d-deplog9zhz:/code/chaiverse_profiler_1726579001 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjusted25294a32531d269b6fce0cff0cb6d6d-deplog9zhz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579001 && 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_1726579001/summary.json'
kubectl exec -it sanchuanhehe-adjusted25294a32531d269b6fce0cff0cb6d6d-deplog9zhz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579001/summary.json'
Pipeline stage MKMLProfilerRunner completed in 440.94s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-9723-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-9723-v1-profiler
Service sanchuanhehe-adjusted-co-9723-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.09s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_9723_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_9723_v1 status is now torndown due to DeploymentManager action