developer_uid: stark2000s
submission_id: stark2000s-ultrachat-v1-3_v1
model_name: stark2000s-ultrachat-v1-3_v1
model_group: stark2000s/ultrachat-v1.
status: torndown
timestamp: 2024-09-05T11:52:06+00:00
num_battles: 12215
num_wins: 5121
celo_rating: 1184.48
family_friendly_score: 0.0
submission_type: basic
model_repo: stark2000s/ultrachat-v1.3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.9138807508381571, 'latency_mean': 1.0941724348068238, 'latency_p50': 1.0959045886993408, 'latency_p90': 1.2330639362335205}, {'batch_size': 4, 'throughput': 1.8005760567185853, 'latency_mean': 2.2133977246284484, 'latency_p50': 2.190613627433777, 'latency_p90': 2.4755632162094114}, {'batch_size': 5, 'throughput': 1.8870339493878658, 'latency_mean': 2.6330902874469757, 'latency_p50': 2.625276803970337, 'latency_p90': 2.94414963722229}, {'batch_size': 8, 'throughput': 2.026720126450825, 'latency_mean': 3.93081840634346, 'latency_p50': 3.9558820724487305, 'latency_p90': 4.375384831428528}, {'batch_size': 10, 'throughput': 2.0381847669608635, 'latency_mean': 4.861768429279327, 'latency_p50': 4.798833250999451, 'latency_p90': 5.72421395778656}, {'batch_size': 12, 'throughput': 2.0292353397816667, 'latency_mean': 5.829045791625976, 'latency_p50': 5.865486741065979, 'latency_p90': 6.795967030525207}, {'batch_size': 15, 'throughput': 2.0282555413755867, 'latency_mean': 7.255859752893448, 'latency_p50': 7.338781952857971, 'latency_p90': 7.967689967155456}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: stark2000s-ultrachat-v1-3_v1
is_internal_developer: False
language_model: stark2000s/ultrachat-v1.3
model_size: 8B
ranking_group: single
throughput_3p7s: 2.02
us_pacific_date: 2024-09-05
win_ratio: 0.4192386410151453
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 stark2000s-ultrachat-v1-3-v1-mkmlizer
Waiting for job on stark2000s-ultrachat-v1-3-v1-mkmlizer to finish
stark2000s-ultrachat-v1-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║     _____            __           __                                ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║       /___/                                                         ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  belonging to:                                                      ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ║                                                                     ║
stark2000s-ultrachat-v1-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-ultrachat-v1-3-v1-mkmlizer: Downloaded to shared memory in 34.987s
stark2000s-ultrachat-v1-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfdm2iwml, device:0
stark2000s-ultrachat-v1-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-ultrachat-v1-3-v1-mkmlizer: quantized model in 25.878s
stark2000s-ultrachat-v1-3-v1-mkmlizer: Processed model stark2000s/ultrachat-v1.3 in 60.866s
stark2000s-ultrachat-v1-3-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-ultrachat-v1-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-ultrachat-v1-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v1
stark2000s-ultrachat-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v1/config.json
stark2000s-ultrachat-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v1/special_tokens_map.json
stark2000s-ultrachat-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v1/tokenizer_config.json
stark2000s-ultrachat-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-ultrachat-v1-3-v1/tokenizer.json
Job stark2000s-ultrachat-v1-3-v1-mkmlizer completed after 84.5s with status: succeeded
Stopping job with name stark2000s-ultrachat-v1-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service stark2000s-ultrachat-v1-3-v1
Waiting for inference service stark2000s-ultrachat-v1-3-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
Failed to get response for submission neversleep-noromaid-v0_8068_v150: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:37198->127.0.0.1:8080: read: connection reset by peer\n')
Inference service stark2000s-ultrachat-v1-3-v1 ready after 150.51602864265442s
Pipeline stage MKMLDeployer completed in 151.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2249436378479004s
Received healthy response to inference request in 1.78729248046875s
Received healthy response to inference request in 1.2211787700653076s
Received healthy response to inference request in 1.8576316833496094s
Received healthy response to inference request in 1.7246201038360596s
5 requests
0 failed requests
5th percentile: 1.321867036819458
10th percentile: 1.4225553035736085
20th percentile: 1.6239318370819091
30th percentile: 1.7371545791625977
40th percentile: 1.7622235298156739
50th percentile: 1.78729248046875
60th percentile: 1.8154281616210937
70th percentile: 1.8435638427734375
80th percentile: 1.9310940742492677
90th percentile: 2.078018856048584
95th percentile: 2.1514812469482423
99th percentile: 2.2102511596679686
mean time: 1.7631333351135254
Pipeline stage StressChecker completed in 9.47s
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 4.19s
Shutdown handler de-registered
stark2000s-ultrachat-v1-3_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service stark2000s-ultrachat-v1-3-v1-profiler
Waiting for inference service stark2000s-ultrachat-v1-3-v1-profiler to be ready
Inference service stark2000s-ultrachat-v1-3-v1-profiler ready after 140.34114718437195s
Pipeline stage MKMLProfilerDeployer completed in 140.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/stark2000s-ultrachat636e439fa9b0b8583a9e0d93577fa9b6-deplosf6sh:/code/chaiverse_profiler_1725537561 --namespace tenant-chaiml-guanaco
kubectl exec -it stark2000s-ultrachat636e439fa9b0b8583a9e0d93577fa9b6-deplosf6sh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725537561 && 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_1725537561/summary.json'
kubectl exec -it stark2000s-ultrachat636e439fa9b0b8583a9e0d93577fa9b6-deplosf6sh --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725537561/summary.json'
Pipeline stage MKMLProfilerRunner completed in 835.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service stark2000s-ultrachat-v1-3-v1-profiler is running
Tearing down inference service stark2000s-ultrachat-v1-3-v1-profiler
Service stark2000s-ultrachat-v1-3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.52s
Shutdown handler de-registered
stark2000s-ultrachat-v1-3_v1 status is now inactive due to auto deactivation removed underperforming models
stark2000s-ultrachat-v1-3_v1 status is now torndown due to DeploymentManager action