chaiml-llama-8b-multihea_7810

developer_uid: chai_backend_admin
submission_id: chaiml-llama-8b-multihea_7810_v2
model_name: chaiml-llama-8b-multihea_7810_v2
model_group: ChaiML/llama_8b_multihea
status: inactive
timestamp: 2024-11-26T17:02:22+00:00
num_battles: 39207
num_wins: 20129
celo_rating: 1272.94
family_friendly_score: 0.5856
family_friendly_standard_error: 0.006966672663474293
submission_type: basic
model_repo: ChaiML/llama_8b_multihead_181m_preference
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-multihea_7810_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_multihead_181m_preference
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-26
win_ratio: 0.513403218812967
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': 256, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}
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 chaiml-llama-8b-multihea-7810-v2-mkmlizer
Waiting for job on chaiml-llama-8b-multihea-7810-v2-mkmlizer to finish
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-llama-8b-multihea-7810-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v2-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-llama-8b-multihea-7810-v2-mkmlizer: Downloaded to shared memory in 62.186s
chaiml-llama-8b-multihea-7810-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmps9hivgju, device:0
chaiml-llama-8b-multihea-7810-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
chaiml-llama-8b-multihea-7810-v2-mkmlizer: quantized model in 87.828s
chaiml-llama-8b-multihea-7810-v2-mkmlizer: Processed model ChaiML/llama_8b_multihead_181m_preference in 150.014s
chaiml-llama-8b-multihea-7810-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multihea-7810-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multihea-7810-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2
chaiml-llama-8b-multihea-7810-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2/config.json
chaiml-llama-8b-multihea-7810-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2/special_tokens_map.json
chaiml-llama-8b-multihea-7810-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2/tokenizer_config.json
chaiml-llama-8b-multihea-7810-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2/tokenizer.json
chaiml-llama-8b-multihea-7810-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v2/flywheel_model.0.safetensors
Job chaiml-llama-8b-multihea-7810-v2-mkmlizer completed after 175.61s with status: succeeded
Stopping job with name chaiml-llama-8b-multihea-7810-v2-mkmlizer
Pipeline stage MKMLizer completed in 176.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multihea-7810-v2
Waiting for inference service chaiml-llama-8b-multihea-7810-v2 to be ready
Inference service chaiml-llama-8b-multihea-7810-v2 ready after 131.11861991882324s
Pipeline stage MKMLDeployer completed in 131.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6078760623931885s
Received healthy response to inference request in 3.744285821914673s
Received healthy response to inference request in 3.439310073852539s
Received healthy response to inference request in 3.8374688625335693s
Received healthy response to inference request in 3.2975449562072754s
5 requests
0 failed requests
5th percentile: 3.325897979736328
10th percentile: 3.354251003265381
20th percentile: 3.4109570503234865
30th percentile: 3.473023271560669
40th percentile: 3.5404496669769285
50th percentile: 3.6078760623931885
60th percentile: 3.662439966201782
70th percentile: 3.717003870010376
80th percentile: 3.762922430038452
90th percentile: 3.800195646286011
95th percentile: 3.81883225440979
99th percentile: 3.8337415409088136
mean time: 3.585297155380249
%s, retrying in %s seconds...
Received healthy response to inference request in 2.50439453125s
Received healthy response to inference request in 3.0898334980010986s
Received healthy response to inference request in 3.0823540687561035s
Received healthy response to inference request in 3.866823434829712s
Received healthy response to inference request in 3.155337333679199s
5 requests
0 failed requests
5th percentile: 2.6199864387512206
10th percentile: 2.7355783462524412
20th percentile: 2.966762161254883
30th percentile: 3.0838499546051024
40th percentile: 3.0868417263031005
50th percentile: 3.0898334980010986
60th percentile: 3.1160350322723387
70th percentile: 3.142236566543579
80th percentile: 3.297634553909302
90th percentile: 3.582228994369507
95th percentile: 3.724526214599609
99th percentile: 3.8383639907836913
mean time: 3.1397485733032227
Pipeline stage StressChecker completed in 36.57s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.19s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.22s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7810_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 0.12s
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 chaiml-llama-8b-multihea-7810-v2-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v2-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v2-profiler ready after 130.33422589302063s
Pipeline stage MKMLProfilerDeployer completed in 130.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplov6rtc:/code/chaiverse_profiler_1732641053 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplov6rtc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732641053 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732641053/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplov6rtc:/code/chaiverse_profiler_1732643851 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplov6rtc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732643851 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732643851/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v2-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v2-profiler
Service chaiml-llama-8b-multihea-7810-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.39s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.47s
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 chaiml-llama-8b-multihea-7810-v2-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v2-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v2-profiler ready after 40.11071491241455s
Pipeline stage MKMLProfilerDeployer completed in 40.43s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplofpd2z:/code/chaiverse_profiler_1732644600 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplofpd2z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732644600 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732644600/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplofpd2z:/code/chaiverse_profiler_1732647377 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplofpd2z:/code/chaiverse_profiler_1732647378 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplofpd2z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732647378 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732647378/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v2-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v2-profiler
Service chaiml-llama-8b-multihea-7810-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.34s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.40s
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 chaiml-llama-8b-multihea-7810-v2-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v2-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v2-profiler ready after 60.15068507194519s
Pipeline stage MKMLProfilerDeployer completed in 60.45s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplovsdw4:/code/chaiverse_profiler_1732648249 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplovsdw4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732648249 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732648249/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplovsdw4:/code/chaiverse_profiler_1732651047 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplovsdw4:/code/chaiverse_profiler_1732651048 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-multa0edc542eea190189c7be7eb6c91a284-deplovsdw4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1732651048 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1732651048/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v2-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v2-profiler
Service chaiml-llama-8b-multihea-7810-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.49s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7810_v2 status is now inactive due to auto deactivation removed underperforming models