stark2000s-ult-du-gpt-v1-7

developer_uid: stark2000s

submission_id: stark2000s-ult-du-gpt-v1-7_v2

model_name: stark2000s-ult-du-gpt-v1-7_v1

model_group: stark2000s/ult-du-gpt-v1

status: torndown

timestamp: 2024-09-09T08:58:21+00:00

num_battles: 11037

num_wins: 4484

celo_rating: 1175.77

family_friendly_score: 0.0

submission_type: basic

model_repo: stark2000s/ult-du-gpt-v1.7

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8969167579756123, 'latency_mean': 1.1148714315891266, 'latency_p50': 1.1036772727966309, 'latency_p90': 1.2605660915374757}, {'batch_size': 3, 'throughput': 1.6257407158517192, 'latency_mean': 1.8430435514450074, 'latency_p50': 1.854663372039795, 'latency_p90': 2.0522125482559206}, {'batch_size': 5, 'throughput': 1.8373197237146515, 'latency_mean': 2.710220755338669, 'latency_p50': 2.7252917289733887, 'latency_p90': 3.0285629272460937}, {'batch_size': 6, 'throughput': 1.8779814642739106, 'latency_mean': 3.1753862714767456, 'latency_p50': 3.1718125343322754, 'latency_p90': 3.599343514442444}, {'batch_size': 8, 'throughput': 1.9345481275119356, 'latency_mean': 4.106595264673233, 'latency_p50': 4.128857254981995, 'latency_p90': 4.554888772964477}, {'batch_size': 10, 'throughput': 1.9670148899058342, 'latency_mean': 5.032949815988541, 'latency_p50': 5.041834473609924, 'latency_p90': 5.854360508918762}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: stark2000s-ult-du-gpt-v1-7_v1

is_internal_developer: False

language_model: stark2000s/ult-du-gpt-v1.7

model_size: 8B

ranking_group: single

throughput_3p7s: 1.93

us_pacific_date: 2024-09-09

win_ratio: 0.4062698196973815

generation_params: {'temperature': 1.15, 'top_p': 0.95, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 stark2000s-ult-du-gpt-v1-7-v2-mkmlizer
Waiting for job on stark2000s-ult-du-gpt-v1-7-v2-mkmlizer to finish
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║     _____            __           __                                ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║       /___/                                                         ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║                                                                     ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║                                                                     ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  belonging to:                                                      ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║                                                                     ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ║                                                                     ║
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: Downloaded to shared memory in 20.783s
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjmr9gb_u, device:0
stark2000s-ult-du-gpt-v1-7-v2-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
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
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: quantized model in 25.843s
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: Processed model stark2000s/ult-du-gpt-v1.7 in 46.627s
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2/config.json
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2/special_tokens_map.json
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2/tokenizer_config.json
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2/tokenizer.json
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-ult-du-gpt-v1-7-v2/flywheel_model.0.safetensors
stark2000s-ult-du-gpt-v1-7-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 52.45it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 74.92it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 78.17it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 85.12it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 89.33it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 79.21it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 75.52it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 78.34it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 21.12it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 27.38it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 34.07it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 41.80it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.56it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:02, 58.06it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 68.79it/s]
Loading 0:  54%|█████▍    | 158/291 [00:02<00:01, 75.41it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:01, 79.57it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 75.22it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 22.62it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 28.62it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.52it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 41.22it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 48.69it/s]
Loading 0:  80%|████████  | 233/291 [00:04<00:01, 57.96it/s]
Loading 0:  83%|████████▎ | 242/291 [00:04<00:00, 62.33it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 66.49it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 75.90it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 78.67it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 80.55it/s]
                                                            
Job stark2000s-ult-du-gpt-v1-7-v2-mkmlizer completed after 125.32s with status: succeeded
Stopping job with name stark2000s-ult-du-gpt-v1-7-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-ult-du-gpt-v1-7-v2
Waiting for inference service stark2000s-ult-du-gpt-v1-7-v2 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
Inference service stark2000s-ult-du-gpt-v1-7-v2 ready after 151.1133053302765s
Pipeline stage MKMLDeployer completed in 152.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.341869354248047s
{"detail":"('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55196->127.0.0.1:8080: read: connection reset by peer\\n')"}
Received unhealthy response to inference request!
Received healthy response to inference request in 1.4040522575378418s
Received healthy response to inference request in 1.6933209896087646s
Received healthy response to inference request in 1.823747158050537s
5 requests
1 failed requests
5th percentile: 1.2607443809509278
10th percentile: 1.2965713500976563
20th percentile: 1.3682252883911132
30th percentile: 1.4619060039520264
40th percentile: 1.5776134967803954
50th percentile: 1.6933209896087646
60th percentile: 1.7454914569854736
70th percentile: 1.7976619243621825
80th percentile: 1.9273715972900392
90th percentile: 2.134620475769043
95th percentile: 2.238244915008545
99th percentile: 2.3211444664001464
mean time: 1.6975814342498778
%s, retrying in %s seconds...
Received healthy response to inference request in 1.965071201324463s
Received healthy response to inference request in 1.9456040859222412s
Received healthy response to inference request in 2.135727643966675s
Received healthy response to inference request in 1.464707374572754s
Received healthy response to inference request in 1.0595028400421143s
5 requests
0 failed requests
5th percentile: 1.1405437469482422
10th percentile: 1.2215846538543702
20th percentile: 1.383666467666626
30th percentile: 1.5608867168426515
40th percentile: 1.7532454013824463
50th percentile: 1.9456040859222412
60th percentile: 1.95339093208313
70th percentile: 1.9611777782440185
80th percentile: 1.9992024898529053
90th percentile: 2.06746506690979
95th percentile: 2.1015963554382324
99th percentile: 2.1289013862609862
mean time: 1.7141226291656495
Pipeline stage StressChecker completed in 18.69s
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 5.91s
Shutdown handler de-registered
stark2000s-ult-du-gpt-v1-7_v2 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 stark2000s-ult-du-gpt-v1-7-v2-profiler
Waiting for inference service stark2000s-ult-du-gpt-v1-7-v2-profiler to be ready
Inference service stark2000s-ult-du-gpt-v1-7-v2-profiler ready after 150.36947178840637s
Pipeline stage MKMLProfilerDeployer completed in 150.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/stark2000s-ult-du-gp6310d1e77a55b6e65d608eba601f7821-deploxvnhn:/code/chaiverse_profiler_1725872804 --namespace tenant-chaiml-guanaco
kubectl exec -it stark2000s-ult-du-gp6310d1e77a55b6e65d608eba601f7821-deploxvnhn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725872804 && 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_1725872804/summary.json'
kubectl exec -it stark2000s-ult-du-gp6310d1e77a55b6e65d608eba601f7821-deploxvnhn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725872804/summary.json'
Pipeline stage MKMLProfilerRunner completed in 771.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service stark2000s-ult-du-gpt-v1-7-v2-profiler is running
Tearing down inference service stark2000s-ult-du-gpt-v1-7-v2-profiler
Service stark2000s-ult-du-gpt-v1-7-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
stark2000s-ult-du-gpt-v1-7_v2 status is now inactive due to auto deactivation removed underperforming models
stark2000s-ult-du-gpt-v1-7_v2 status is now torndown due to DeploymentManager action