developer_uid: sanchuanhehe
submission_id: sanchuanhehe-adjusted-co_8106_v1
model_name: sanchuanhehe-adjusted-co_8106_v1
model_group: sanchuanhehe/adjusted_co
status: torndown
timestamp: 2024-09-17T13:10:04+00:00
num_battles: 9571
num_wins: 4017
celo_rating: 1115.8
family_friendly_score: 0.0
submission_type: basic
model_repo: sanchuanhehe/adjusted_config_14_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': 1.1134081386906343, 'latency_mean': 0.8980545008182526, 'latency_p50': 0.9057084321975708, 'latency_p90': 0.9955832004547119}, {'batch_size': 5, 'throughput': 3.6623070747906996, 'latency_mean': 1.3544789850711823, 'latency_p50': 1.3619868755340576, 'latency_p90': 1.509100580215454}, {'batch_size': 10, 'throughput': 5.40596296879587, 'latency_mean': 1.8295429754257202, 'latency_p50': 1.8460572957992554, 'latency_p90': 2.054676079750061}, {'batch_size': 15, 'throughput': 6.38402095219584, 'latency_mean': 2.3157673585414886, 'latency_p50': 2.3211792707443237, 'latency_p90': 2.6635978698730467}, {'batch_size': 20, 'throughput': 6.950492046824659, 'latency_mean': 2.832373138666153, 'latency_p50': 2.80575692653656, 'latency_p90': 3.2881997346878054}, {'batch_size': 25, 'throughput': 7.295987536837696, 'latency_mean': 3.3565800023078918, 'latency_p50': 3.311357617378235, 'latency_p90': 3.962792754173279}, {'batch_size': 30, 'throughput': 7.490857694887064, 'latency_mean': 3.9087402033805847, 'latency_p50': 3.913200616836548, 'latency_p90': 4.629199147224426}, {'batch_size': 35, 'throughput': 7.718387175318379, 'latency_mean': 4.414750400781632, 'latency_p50': 4.344720363616943, 'latency_p90': 5.195863175392151}, {'batch_size': 40, 'throughput': 7.582894176404114, 'latency_mean': 5.091791582107544, 'latency_p50': 5.068200469017029, 'latency_p90': 5.891938471794129}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sanchuanhehe-adjusted-co_8106_v1
is_internal_developer: False
language_model: sanchuanhehe/adjusted_config_14_l
model_size: 7B
ranking_group: single
throughput_3p7s: 7.6
us_pacific_date: 2024-09-17
win_ratio: 0.41970535994148994
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-8106-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-8106-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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', '')
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: Downloaded to shared memory in 32.805s
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplg0skwqy, device:0
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: quantized model in 17.518s
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_14_l in 50.323s
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/config.json
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/tokenizer.model
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/tokenizer.json
sanchuanhehe-adjusted-co-8106-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-8106-v1/flywheel_model.0.safetensors
Job sanchuanhehe-adjusted-co-8106-v1-mkmlizer completed after 74.38s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-8106-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-8106-v1
Waiting for inference service sanchuanhehe-adjusted-co-8106-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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sanchuanhehe-adjusted-co-8106-v1 ready after 181.4263792037964s
Pipeline stage MKMLDeployer completed in 181.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5899012088775635s
Received healthy response to inference request in 0.9689633846282959s
Received healthy response to inference request in 1.2435758113861084s
Received healthy response to inference request in 0.5761325359344482s
Received healthy response to inference request in 1.2042016983032227s
5 requests
0 failed requests
5th percentile: 0.6546987056732178
10th percentile: 0.7332648754119873
20th percentile: 0.8903972148895264
30th percentile: 1.0160110473632813
40th percentile: 1.1101063728332519
50th percentile: 1.2042016983032227
60th percentile: 1.219951343536377
70th percentile: 1.2357009887695312
80th percentile: 1.3128408908843996
90th percentile: 1.4513710498809815
95th percentile: 1.5206361293792723
99th percentile: 1.5760481929779053
mean time: 1.1165549278259277
Pipeline stage StressChecker completed in 6.89s
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 4.80s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8106_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-8106-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-8106-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-8106-v1-profiler ready after 190.45155811309814s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste41df77b25cbdeae0d79fc6138a83d5de-deplo2ltpg:/code/chaiverse_profiler_1726579103 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste41df77b25cbdeae0d79fc6138a83d5de-deplo2ltpg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579103 && 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_1726579103/summary.json'
kubectl exec -it sanchuanhehe-adjuste41df77b25cbdeae0d79fc6138a83d5de-deplo2ltpg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579103/summary.json'
Pipeline stage MKMLProfilerRunner completed in 443.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-8106-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-8106-v1-profiler
Service sanchuanhehe-adjusted-co-8106-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_8106_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_8106_v1 status is now torndown due to DeploymentManager action