developer_uid: sanchuanhehe
submission_id: sanchuanhehe-end-try-end_v3
model_name: sanchuanhehe-end-try-end_v3
model_group: sanchuanhehe/end_try_end
status: torndown
timestamp: 2024-09-17T07:46:16+00:00
num_battles: 10924
num_wins: 4904
celo_rating: 1213.93
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/end_try_end
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.9668551220939613, 'latency_mean': 1.0342170584201813, 'latency_p50': 1.0326677560806274, 'latency_p90': 1.174563503265381}, {'batch_size': 4, 'throughput': 1.902395130783871, 'latency_mean': 2.0906076765060426, 'latency_p50': 2.091786503791809, 'latency_p90': 2.32113196849823}, {'batch_size': 5, 'throughput': 1.9581201848466867, 'latency_mean': 2.538780937194824, 'latency_p50': 2.5418702363967896, 'latency_p90': 2.8717950582504272}, {'batch_size': 8, 'throughput': 2.1048347520868544, 'latency_mean': 3.7756795620918275, 'latency_p50': 3.799124598503113, 'latency_p90': 4.324716806411743}, {'batch_size': 10, 'throughput': 2.1077312405678765, 'latency_mean': 4.702877541780472, 'latency_p50': 4.719001054763794, 'latency_p90': 5.448392343521118}, {'batch_size': 12, 'throughput': 2.1195051276835506, 'latency_mean': 5.579156889915466, 'latency_p50': 5.536510467529297, 'latency_p90': 6.529785919189453}, {'batch_size': 15, 'throughput': 2.092316677082429, 'latency_mean': 7.026904593706131, 'latency_p50': 7.089908957481384, 'latency_p90': 7.798037171363831}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-end-try-end_v3
is_internal_developer: False
language_model: sanchuanhehe/end_try_end
model_size: 7B
ranking_group: single
throughput_3p7s: 2.11
us_pacific_date: 2024-09-17
win_ratio: 0.4489198095935555
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': 16, '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-end-try-end-v3-mkmlizer
Waiting for job on sanchuanhehe-end-try-end-v3-mkmlizer to finish
sanchuanhehe-end-try-end-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-end-try-end-v3-mkmlizer: ║ _____ __ __ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ /___/ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ Version: 0.10.1 ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ https://mk1.ai ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ The license key for the current software has been verified as ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ belonging to: ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ Chai Research Corp. ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sanchuanhehe-end-try-end-v3-mkmlizer: ║ ║
sanchuanhehe-end-try-end-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-end-try-end-v3-mkmlizer: Downloaded to shared memory in 29.874s
sanchuanhehe-end-try-end-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzss4i5wo, device:0
sanchuanhehe-end-try-end-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-end-try-end-v3-mkmlizer: quantized model in 17.737s
sanchuanhehe-end-try-end-v3-mkmlizer: Processed model sanchuanhehe/end_try_end in 47.611s
sanchuanhehe-end-try-end-v3-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-end-try-end-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-end-try-end-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/config.json
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/special_tokens_map.json
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/tokenizer_config.json
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/tokenizer.model
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/tokenizer.json
sanchuanhehe-end-try-end-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-end-try-end-v3/flywheel_model.0.safetensors
sanchuanhehe-end-try-end-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 53.95it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 70.69it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 89.42it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 84.72it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 84.35it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 86.03it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 77.74it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 77.90it/s] Loading 0: 32%|███▏ | 94/291 [00:01<00:02, 86.66it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:08, 23.25it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:05, 30.68it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:04, 37.01it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 42.76it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 55.89it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 63.49it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:01, 65.22it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:01, 69.93it/s] Loading 0: 64%|██████▍ | 187/291 [00:03<00:01, 71.01it/s] Loading 0: 67%|██████▋ | 196/291 [00:03<00:01, 70.10it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:03, 23.97it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 27.78it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:02, 35.30it/s] Loading 0: 79%|███████▉ | 230/291 [00:04<00:01, 44.77it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:01, 50.53it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 57.45it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 63.82it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 68.17it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 71.99it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 76.06it/s]
Job sanchuanhehe-end-try-end-v3-mkmlizer completed after 73.01s with status: succeeded
Stopping job with name sanchuanhehe-end-try-end-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-end-try-end-v3
Waiting for inference service sanchuanhehe-end-try-end-v3 to be ready
Inference service sanchuanhehe-end-try-end-v3 ready after 172.85279202461243s
Pipeline stage MKMLDeployer completed in 173.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.138016700744629s
Received healthy response to inference request in 1.1359925270080566s
Received healthy response to inference request in 2.081655263900757s
Received healthy response to inference request in 1.922118902206421s
Received healthy response to inference request in 1.4372572898864746s
5 requests
0 failed requests
5th percentile: 1.1962454795837403
10th percentile: 1.256498432159424
20th percentile: 1.377004337310791
30th percentile: 1.534229612350464
40th percentile: 1.7281742572784424
50th percentile: 1.922118902206421
60th percentile: 1.9859334468841552
70th percentile: 2.0497479915618895
80th percentile: 2.0929275512695313
90th percentile: 2.11547212600708
95th percentile: 2.1267444133758544
99th percentile: 2.135762243270874
mean time: 1.7430081367492676
Pipeline stage StressChecker completed in 9.31s
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 9.13s
Shutdown handler de-registered
sanchuanhehe-end-try-end_v3 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-end-try-end-v3-profiler
Waiting for inference service sanchuanhehe-end-try-end-v3-profiler to be ready
Inference service sanchuanhehe-end-try-end-v3-profiler ready after 170.4994843006134s
Pipeline stage MKMLProfilerDeployer completed in 170.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-end-try-end-v3-profiler-predictor-00001-deplo9gn9p:/code/chaiverse_profiler_1726559665 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-end-try-end-v3-profiler-predictor-00001-deplo9gn9p --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726559665 && python profiles.py profile --best_of_n 16 --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_1726559665/summary.json'
kubectl exec -it sanchuanhehe-end-try-end-v3-profiler-predictor-00001-deplo9gn9p --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726559665/summary.json'
Pipeline stage MKMLProfilerRunner completed in 799.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-end-try-end-v3-profiler is running
Tearing down inference service sanchuanhehe-end-try-end-v3-profiler
Service sanchuanhehe-end-try-end-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.95s
Shutdown handler de-registered
sanchuanhehe-end-try-end_v3 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-end-try-end_v3 status is now torndown due to DeploymentManager action