sanchuanhehe-adjusted-co_5817

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_5817_v1

model_name: sanchuanhehe-adjusted-co_5817_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:05:24+00:00

num_battles: 9934

num_wins: 4120

celo_rating: 1114.4

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_3_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': 1.1158422307165106, 'latency_mean': 0.8960913980007171, 'latency_p50': 0.8964142799377441, 'latency_p90': 0.9927923202514648}, {'batch_size': 5, 'throughput': 3.67933748654286, 'latency_mean': 1.3533528673648834, 'latency_p50': 1.356613039970398, 'latency_p90': 1.5049211978912354}, {'batch_size': 10, 'throughput': 5.4574571885772745, 'latency_mean': 1.8158668625354766, 'latency_p50': 1.813752293586731, 'latency_p90': 2.0785747528076173}, {'batch_size': 15, 'throughput': 6.380723033063905, 'latency_mean': 2.3166026854515076, 'latency_p50': 2.312294363975525, 'latency_p90': 2.655214953422546}, {'batch_size': 20, 'throughput': 6.851961937676072, 'latency_mean': 2.853168295621872, 'latency_p50': 2.8364890813827515, 'latency_p90': 3.311525845527649}, {'batch_size': 25, 'throughput': 7.3412348980442195, 'latency_mean': 3.3321629583835604, 'latency_p50': 3.338539242744446, 'latency_p90': 3.8134505510330197}, {'batch_size': 30, 'throughput': 7.627499905117796, 'latency_mean': 3.840067421197891, 'latency_p50': 3.818799614906311, 'latency_p90': 4.472873997688294}, {'batch_size': 35, 'throughput': 7.6514761152422155, 'latency_mean': 4.4577772223949435, 'latency_p50': 4.377682209014893, 'latency_p90': 5.447376394271851}, {'batch_size': 40, 'throughput': 7.510551524253903, 'latency_mean': 5.136673911809921, 'latency_p50': 5.141934871673584, 'latency_p90': 6.239179992675781}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_5817_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_3_le

model_size: 7B

ranking_group: single

throughput_3p7s: 7.74

us_pacific_date: 2024-09-17

win_ratio: 0.414737265955305

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-5817-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-5817-v1-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
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-5817-v1-mkmlizer: Downloaded to shared memory in 30.765s
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3xufswhk, device:0
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: quantized model in 18.974s
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_3_le in 49.739s
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/config.json
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/tokenizer.model
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/tokenizer.json
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5817-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-5817-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:06, 45.91it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 57.69it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 62.51it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:04, 61.09it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 58.67it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:04, 59.10it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:03, 59.06it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 58.45it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:03, 55.22it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 49.72it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:03, 53.73it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:03, 58.14it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:11, 16.83it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:08, 22.28it/s]
Loading 0:  42%|████▏     | 121/291 [00:03<00:06, 28.08it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 34.11it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 39.55it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 44.10it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 46.74it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 44.57it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 48.89it/s]
Loading 0:  61%|██████    | 178/291 [00:04<00:02, 50.73it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:01, 52.75it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:01, 55.10it/s]
Loading 0:  70%|███████   | 204/291 [00:05<00:04, 19.29it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:03, 22.81it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:02, 29.36it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 36.36it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 43.19it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 50.95it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 56.93it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 62.49it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 66.56it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 68.61it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 17.48it/s]
                                                            
Job sanchuanhehe-adjusted-co-5817-v1-mkmlizer completed after 74.9s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-5817-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.47s
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-5817-v1
Waiting for inference service sanchuanhehe-adjusted-co-5817-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_henub_2024-09-09: ('http://chaiml-elo-alignment-run-3-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51838->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sanchuanhehe-adjusted-co-5817-v1 ready after 171.20804071426392s
Pipeline stage MKMLDeployer completed in 171.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7908470630645752s
Received healthy response to inference request in 0.5601968765258789s
Received healthy response to inference request in 0.5616066455841064s
Received healthy response to inference request in 1.1610736846923828s
Received healthy response to inference request in 1.2994771003723145s
5 requests
0 failed requests
5th percentile: 0.5604788303375244
10th percentile: 0.56076078414917
20th percentile: 0.5613246917724609
30th percentile: 0.6815000534057617
40th percentile: 0.9212868690490723
50th percentile: 1.1610736846923828
60th percentile: 1.2164350509643556
70th percentile: 1.271796417236328
80th percentile: 1.3977510929107666
90th percentile: 1.594299077987671
95th percentile: 1.692573070526123
99th percentile: 1.7711922645568847
mean time: 1.0746402740478516
Pipeline stage StressChecker completed in 7.84s
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 4.97s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5817_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-5817-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-5817-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-5817-v1-profiler ready after 190.54772424697876s
Pipeline stage MKMLProfilerDeployer completed in 190.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste9363adb12eca292bc685d0066a62c525-deplo7ll7v:/code/chaiverse_profiler_1726578823 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste9363adb12eca292bc685d0066a62c525-deplo7ll7v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726578823 && 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_1726578823/summary.json'
kubectl exec -it sanchuanhehe-adjuste9363adb12eca292bc685d0066a62c525-deplo7ll7v --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726578823/summary.json'
Pipeline stage MKMLProfilerRunner completed in 442.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-5817-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-5817-v1-profiler
Service sanchuanhehe-adjusted-co-5817-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.33s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5817_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_5817_v1 status is now torndown due to DeploymentManager action