sanchuanhehe-adjusted-co_2396

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_2396_v1

model_name: sanchuanhehe-adjusted-co_2396_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:06:03+00:00

num_battles: 11283

num_wins: 4702

celo_rating: 1116.55

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_5_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': 1.1125472145112751, 'latency_mean': 0.8987582242488861, 'latency_p50': 0.8984869718551636, 'latency_p90': 0.9880784749984741}, {'batch_size': 5, 'throughput': 3.6669682108308437, 'latency_mean': 1.3558521676063537, 'latency_p50': 1.3607985973358154, 'latency_p90': 1.5132735252380372}, {'batch_size': 10, 'throughput': 5.374096871376707, 'latency_mean': 1.8317912852764129, 'latency_p50': 1.8457355499267578, 'latency_p90': 2.0579522848129272}, {'batch_size': 15, 'throughput': 6.340010015703765, 'latency_mean': 2.3131996297836306, 'latency_p50': 2.3137078285217285, 'latency_p90': 2.6352435827255247}, {'batch_size': 20, 'throughput': 6.85956230954503, 'latency_mean': 2.859751365184784, 'latency_p50': 2.84369695186615, 'latency_p90': 3.2725730895996095}, {'batch_size': 25, 'throughput': 7.1900319095824905, 'latency_mean': 3.4011557590961456, 'latency_p50': 3.39235520362854, 'latency_p90': 3.9233580112457274}, {'batch_size': 30, 'throughput': 7.597629092028217, 'latency_mean': 3.864939147233963, 'latency_p50': 3.833865761756897, 'latency_p90': 4.483870959281921}, {'batch_size': 35, 'throughput': 7.739523140059734, 'latency_mean': 4.393675760030747, 'latency_p50': 4.385034441947937, 'latency_p90': 5.1915094375610344}, {'batch_size': 40, 'throughput': 7.677459301729675, 'latency_mean': 5.048382377624511, 'latency_p50': 5.114675164222717, 'latency_p90': 5.938054108619689}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_2396_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_5_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.63

us_pacific_date: 2024-09-17

win_ratio: 0.4167331383497297

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-2396-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-2396-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: Downloaded to shared memory in 30.465s
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpek2thj_o, device:0
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-2396-v1-mkmlizer: quantized model in 18.427s
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_5_le in 48.892s
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/config.json
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/tokenizer.model
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/tokenizer.json
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-2396-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-2396-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 41.79it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:05, 48.61it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 52.64it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:04, 55.36it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 58.93it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 61.81it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:03, 61.72it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 63.36it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 68.84it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:03, 66.82it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 65.19it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:09, 19.02it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 23.16it/s]
Loading 0:  42%|████▏     | 121/291 [00:03<00:05, 29.22it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 36.66it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 44.25it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.16it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 54.95it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:01, 64.26it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 65.80it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 66.39it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 72.00it/s]
Loading 0:  70%|███████   | 204/291 [00:05<00:03, 22.10it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 25.69it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 31.72it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 38.84it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 45.32it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 51.29it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 54.55it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 60.80it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 64.65it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 62.26it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.25it/s]
                                                            
Job sanchuanhehe-adjusted-co-2396-v1-mkmlizer completed after 85.12s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-2396-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.04s
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-2396-v1
Waiting for inference service sanchuanhehe-adjusted-co-2396-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
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-2396-v1 ready after 180.4717481136322s
Pipeline stage MKMLDeployer completed in 180.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8980541229248047s
Received healthy response to inference request in 1.1606454849243164s
Received healthy response to inference request in 0.9568624496459961s
Received healthy response to inference request in 0.7507598400115967s
Received healthy response to inference request in 1.3674547672271729s
5 requests
0 failed requests
5th percentile: 0.7919803619384765
10th percentile: 0.8332008838653564
20th percentile: 0.9156419277191162
30th percentile: 0.9976190567016602
40th percentile: 1.0791322708129882
50th percentile: 1.1606454849243164
60th percentile: 1.243369197845459
70th percentile: 1.3260929107666015
80th percentile: 1.4735746383666992
90th percentile: 1.685814380645752
95th percentile: 1.7919342517852783
99th percentile: 1.8768301486968995
mean time: 1.2267553329467773
Pipeline stage StressChecker completed in 8.70s
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 6.48s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2396_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 0.13s
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-2396-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-2396-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-2396-v1-profiler ready after 190.46596312522888s
Pipeline stage MKMLProfilerDeployer completed in 190.84s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste7ada8e53c6edf4de67fabecfdb7cc24a-deplok72qq:/code/chaiverse_profiler_1726578893 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste7ada8e53c6edf4de67fabecfdb7cc24a-deplok72qq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578893 && 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_1726578893/summary.json'
kubectl exec -it sanchuanhehe-adjuste7ada8e53c6edf4de67fabecfdb7cc24a-deplok72qq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578893/summary.json'
Pipeline stage MKMLProfilerRunner completed in 443.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-2396-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-2396-v1-profiler
Service sanchuanhehe-adjusted-co-2396-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_2396_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_2396_v1 status is now torndown due to DeploymentManager action