developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_3987_v1
model_name: sanchuanhehe-adjusted-co_3987_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:11:50+00:00
num_battles: 10847
num_wins: 4503
celo_rating: 1115.11
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_21_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': 1.1157860550501733, 'latency_mean': 0.8961277568340301, 'latency_p50': 0.9028682708740234, 'latency_p90': 1.0033515453338624}, {'batch_size': 5, 'throughput': 3.608482445564376, 'latency_mean': 1.3719536638259888, 'latency_p50': 1.3713923692703247, 'latency_p90': 1.539630627632141}, {'batch_size': 10, 'throughput': 5.277670270481256, 'latency_mean': 1.8727364611625672, 'latency_p50': 1.8660106658935547, 'latency_p90': 2.1284525871276854}, {'batch_size': 15, 'throughput': 6.210269749071687, 'latency_mean': 2.372339115142822, 'latency_p50': 2.3567720651626587, 'latency_p90': 2.746656084060669}, {'batch_size': 20, 'throughput': 6.775850818339949, 'latency_mean': 2.8960838222503664, 'latency_p50': 2.8780406713485718, 'latency_p90': 3.293748331069946}, {'batch_size': 25, 'throughput': 7.093303170884281, 'latency_mean': 3.440594880580902, 'latency_p50': 3.4773164987564087, 'latency_p90': 3.985186433792114}, {'batch_size': 30, 'throughput': 7.394869337598374, 'latency_mean': 3.968757781982422, 'latency_p50': 3.963421940803528, 'latency_p90': 4.66539409160614}, {'batch_size': 35, 'throughput': 7.483175360392526, 'latency_mean': 4.562410403490066, 'latency_p50': 4.486724376678467, 'latency_p90': 5.426478385925292}, {'batch_size': 40, 'throughput': 7.51927748602054, 'latency_mean': 5.159220370054245, 'latency_p50': 5.117734432220459, 'latency_p90': 6.247629332542418}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_3987_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_21_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.42
us_pacific_date: 2024-09-17
win_ratio: 0.41513782612703976
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-3987-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-3987-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: Downloaded to shared memory in 37.481s
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl601iqcz, device:0
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: quantized model in 18.524s
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_21_l in 56.006s
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/config.json
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/tokenizer.model
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/tokenizer.json
sanchuanhehe-adjusted-co-3987-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3987-v1/flywheel_model.0.safetensors
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', '')
Job sanchuanhehe-adjusted-co-3987-v1-mkmlizer completed after 83.65s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-3987-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.34s
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-3987-v1
Waiting for inference service sanchuanhehe-adjusted-co-3987-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', '')
Inference service sanchuanhehe-adjusted-co-3987-v1 ready after 191.29349660873413s
Pipeline stage MKMLDeployer completed in 191.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6610755920410156s
Received healthy response to inference request in 1.2858326435089111s
Received healthy response to inference request in 0.9042050838470459s
Received healthy response to inference request in 0.522367000579834s
Received healthy response to inference request in 1.268552541732788s
5 requests
0 failed requests
5th percentile: 0.5987346172332764
10th percentile: 0.6751022338867188
20th percentile: 0.8278374671936035
30th percentile: 0.9770745754241943
40th percentile: 1.1228135585784913
50th percentile: 1.268552541732788
60th percentile: 1.2754645824432373
70th percentile: 1.2823766231536866
80th percentile: 1.3608812332153322
90th percentile: 1.5109784126281738
95th percentile: 1.5860270023345946
99th percentile: 1.6460658740997314
mean time: 1.128406572341919
Pipeline stage StressChecker completed in 6.48s
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 4.29s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3987_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 0.11s
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-3987-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-3987-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-3987-v1-profiler ready after 180.40596961975098s
Pipeline stage MKMLProfilerDeployer completed in 180.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustefb460a60c3ed5a0178a6bf5482a23ed1-deplo68hl9:/code/chaiverse_profiler_1726579222 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustefb460a60c3ed5a0178a6bf5482a23ed1-deplo68hl9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579222 && 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_1726579222/summary.json'
kubectl exec -it sanchuanhehe-adjustefb460a60c3ed5a0178a6bf5482a23ed1-deplo68hl9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579222/summary.json'
Pipeline stage MKMLProfilerRunner completed in 449.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-3987-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-3987-v1-profiler
Service sanchuanhehe-adjusted-co-3987-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3987_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_3987_v1 status is now torndown due to DeploymentManager action