sanchuanhehe-adjusted-co_3072

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_3072_v1

model_name: sanchuanhehe-adjusted-co_3072_v1

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T13:11:06+00:00

num_battles: 11059

num_wins: 4481

celo_rating: 1106.9

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_18_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': 1.1301589645895624, 'latency_mean': 0.8847708380222321, 'latency_p50': 0.882956862449646, 'latency_p90': 0.9794776439666748}, {'batch_size': 5, 'throughput': 3.68135306267999, 'latency_mean': 1.345117279291153, 'latency_p50': 1.3338255882263184, 'latency_p90': 1.5067287921905517}, {'batch_size': 10, 'throughput': 5.459950145963023, 'latency_mean': 1.814334181547165, 'latency_p50': 1.8022332191467285, 'latency_p90': 2.067904758453369}, {'batch_size': 15, 'throughput': 6.38243724401105, 'latency_mean': 2.30736661195755, 'latency_p50': 2.3009209632873535, 'latency_p90': 2.623387265205383}, {'batch_size': 20, 'throughput': 6.896018399492757, 'latency_mean': 2.84210169672966, 'latency_p50': 2.8356993198394775, 'latency_p90': 3.2566306352615353}, {'batch_size': 25, 'throughput': 7.3328343556117765, 'latency_mean': 3.325326923131943, 'latency_p50': 3.334073543548584, 'latency_p90': 3.893677234649658}, {'batch_size': 30, 'throughput': 7.6023500035371745, 'latency_mean': 3.858222601413727, 'latency_p50': 3.818552613258362, 'latency_p90': 4.4489784955978395}, {'batch_size': 35, 'throughput': 7.733748941503703, 'latency_mean': 4.3935893738269804, 'latency_p50': 4.316715836524963, 'latency_p90': 5.352930307388306}, {'batch_size': 40, 'throughput': 7.83509555877457, 'latency_mean': 4.970234518051147, 'latency_p50': 4.941752076148987, 'latency_p90': 5.701084089279175}, {'batch_size': 45, 'throughput': 7.671394730953197, 'latency_mean': 5.606036386489868, 'latency_p50': 5.561489105224609, 'latency_p90': 6.4165775060653685}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-adjusted-co_3072_v1

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_18_l

model_size: 7B

ranking_group: single

throughput_3p7s: 7.71

us_pacific_date: 2024-09-17

win_ratio: 0.4051903427072972

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-3072-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-3072-v1-mkmlizer to finish
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: Downloaded to shared memory in 31.496s
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaf9ft0k2, device:0
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-3072-v1-mkmlizer: quantized model in 17.820s
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_18_l in 49.317s
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/config.json
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/tokenizer.model
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/tokenizer.json
sanchuanhehe-adjusted-co-3072-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-3072-v1/flywheel_model.0.safetensors
Job sanchuanhehe-adjusted-co-3072-v1-mkmlizer completed after 73.75s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-3072-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sanchuanhehe-adjusted-co-3072-v1
Waiting for inference service sanchuanhehe-adjusted-co-3072-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', '')
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', '')
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-3072-v1 ready after 192.3638505935669s
Pipeline stage MKMLDeployer completed in 192.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4613702297210693s
Received healthy response to inference request in 1.1158936023712158s
Received healthy response to inference request in 0.659503698348999s
Received healthy response to inference request in 1.23740816116333s
Received healthy response to inference request in 0.9606978893280029s
5 requests
0 failed requests
5th percentile: 0.7197425365447998
10th percentile: 0.7799813747406006
20th percentile: 0.9004590511322021
30th percentile: 0.9917370319366455
40th percentile: 1.0538153171539306
50th percentile: 1.1158936023712158
60th percentile: 1.1644994258880614
70th percentile: 1.2131052494049073
80th percentile: 1.282200574874878
90th percentile: 1.3717854022979736
95th percentile: 1.4165778160095215
99th percentile: 1.4524117469787599
mean time: 1.0869747161865235
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 4.49s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3072_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-3072-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-3072-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-3072-v1-profiler ready after 180.43407440185547s
Pipeline stage MKMLProfilerDeployer completed in 180.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjuste3ee04ebb90fc588b221d5eaf07284d3f-deplo4trqb:/code/chaiverse_profiler_1726579163 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjuste3ee04ebb90fc588b221d5eaf07284d3f-deplo4trqb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726579163 && 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_1726579163/summary.json'
kubectl exec -it sanchuanhehe-adjuste3ee04ebb90fc588b221d5eaf07284d3f-deplo4trqb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726579163/summary.json'
Pipeline stage MKMLProfilerRunner completed in 466.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-3072-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-3072-v1-profiler
Service sanchuanhehe-adjusted-co-3072-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.12s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_3072_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_3072_v1 status is now torndown due to DeploymentManager action