sanchuanhehe-adjusted-co_5939

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_5939_v1

model_name: sanchuanhehe-adjusted-co_5939_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:09:12+00:00

num_battles: 11174

num_wins: 4624

celo_rating: 1115.29

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_11_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': 1.1324938861474172, 'latency_mean': 0.882947814464569, 'latency_p50': 0.8772894144058228, 'latency_p90': 0.9890750169754028}, {'batch_size': 5, 'throughput': 3.651701173488894, 'latency_mean': 1.359494012594223, 'latency_p50': 1.360946774482727, 'latency_p90': 1.519695806503296}, {'batch_size': 10, 'throughput': 5.377402892011261, 'latency_mean': 1.8295643532276153, 'latency_p50': 1.8244258165359497, 'latency_p90': 2.0628875732421874}, {'batch_size': 15, 'throughput': 6.276003631798023, 'latency_mean': 2.352746460437775, 'latency_p50': 2.3547970056533813, 'latency_p90': 2.685572075843811}, {'batch_size': 20, 'throughput': 6.922474605300863, 'latency_mean': 2.844750905036926, 'latency_p50': 2.826669692993164, 'latency_p90': 3.2648985147476193}, {'batch_size': 25, 'throughput': 7.297553288938868, 'latency_mean': 3.353040795326233, 'latency_p50': 3.321756601333618, 'latency_p90': 3.919150686264038}, {'batch_size': 30, 'throughput': 7.457378057147824, 'latency_mean': 3.924463988542557, 'latency_p50': 3.9374170303344727, 'latency_p90': 4.6348336935043335}, {'batch_size': 35, 'throughput': 7.637473898311875, 'latency_mean': 4.471341028213501, 'latency_p50': 4.426418304443359, 'latency_p90': 5.148914742469787}, {'batch_size': 40, 'throughput': 7.659099456351091, 'latency_mean': 5.076768682003022, 'latency_p50': 5.061015009880066, 'latency_p90': 5.964929413795471}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_5939_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_11_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.58

us_pacific_date: 2024-09-17

win_ratio: 0.413817791301235

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-5939-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-5939-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: Downloaded to shared memory in 30.769s
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7osisjwz, device:0
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: quantized model in 18.641s
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_11_l in 49.410s
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1/config.json
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1/tokenizer.model
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-5939-v1/tokenizer.json
sanchuanhehe-adjusted-co-5939-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.15it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 59.97it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:04, 58.88it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:04, 60.52it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 64.88it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 65.93it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 68.37it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:03, 67.51it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 67.22it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 69.06it/s]
Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 69.77it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:09, 19.19it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:07, 23.70it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:05, 29.48it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 35.03it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 39.50it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 43.83it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 46.56it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 48.92it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 51.90it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:01, 53.63it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:01, 56.12it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 57.79it/s]
Loading 0:  71%|███████▏  | 208/291 [00:05<00:04, 18.66it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:03, 21.40it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 27.34it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 32.53it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 38.24it/s]
Loading 0:  86%|████████▌ | 250/291 [00:06<00:00, 44.10it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 49.25it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 54.69it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 60.35it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 63.46it/s]
                                                            
Job sanchuanhehe-adjusted-co-5939-v1-mkmlizer completed after 75.98s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-5939-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-5939-v1
Waiting for inference service sanchuanhehe-adjusted-co-5939-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', '')
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-5939-v1 ready after 191.750501871109s
Pipeline stage MKMLDeployer completed in 192.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5430657863616943s
Received healthy response to inference request in 0.6975891590118408s
Received healthy response to inference request in 1.061640977859497s
Received healthy response to inference request in 1.4968640804290771s
Received healthy response to inference request in 0.8022627830505371s
5 requests
0 failed requests
5th percentile: 0.7185238838195801
10th percentile: 0.7394586086273194
20th percentile: 0.7813280582427978
30th percentile: 0.8541384220123291
40th percentile: 0.9578896999359131
50th percentile: 1.061640977859497
60th percentile: 1.2357302188873291
70th percentile: 1.409819459915161
80th percentile: 1.5061044216156005
90th percentile: 1.5245851039886475
95th percentile: 1.533825445175171
99th percentile: 1.5412177181243896
mean time: 1.1202845573425293
Pipeline stage StressChecker completed in 6.45s
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 4.61s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5939_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 0.17s
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-5939-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-5939-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-5939-v1-profiler ready after 190.4523274898529s
Pipeline stage MKMLProfilerDeployer completed in 190.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste03323c92766a60d2eb4fb52394eddd69-deplocplp5:/code/chaiverse_profiler_1726579061 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste03323c92766a60d2eb4fb52394eddd69-deplocplp5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579061 && 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_1726579061/summary.json'
kubectl exec -it sanchuanhehe-adjuste03323c92766a60d2eb4fb52394eddd69-deplocplp5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579061/summary.json'
Pipeline stage MKMLProfilerRunner completed in 440.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-5939-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-5939-v1-profiler
Service sanchuanhehe-adjusted-co-5939-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_5939_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_5939_v1 status is now torndown due to DeploymentManager action