rirv938-llama-8b-multihe_7961

developer_uid: robert_irvine
submission_id: rirv938-llama-8b-multihe_7961_v1
model_name: rirv938-llama-8b-multihe_7961_v1
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2024-11-14T18:35:28+00:00
num_battles: 18375
num_wins: 8850
celo_rating: 1234.88
family_friendly_score: 0.5842
family_friendly_standard_error: 0.006970084074098389
submission_type: basic
model_repo: rirv938/llama_8b_multihead_204m_mcl
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: rirv938-llama-8b-multihe_7961_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_204m_mcl
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-14
win_ratio: 0.4816326530612245
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': 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 rirv938-llama-8b-multihe-7961-v1-mkmlizer
Waiting for job on rirv938-llama-8b-multihe-7961-v1-mkmlizer to finish
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-7961-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-multihe-7961-v1-mkmlizer: Downloaded to shared memory in 90.362s
rirv938-llama-8b-multihe-7961-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpavsly8fx, device:0
rirv938-llama-8b-multihe-7961-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-multihe-7961-v1-mkmlizer: quantized model in 86.880s
rirv938-llama-8b-multihe-7961-v1-mkmlizer: Processed model rirv938/llama_8b_multihead_204m_mcl in 177.242s
rirv938-llama-8b-multihe-7961-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multihe-7961-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multihe-7961-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1
rirv938-llama-8b-multihe-7961-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1/config.json
rirv938-llama-8b-multihe-7961-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1/special_tokens_map.json
rirv938-llama-8b-multihe-7961-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1/tokenizer_config.json
rirv938-llama-8b-multihe-7961-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1/tokenizer.json
rirv938-llama-8b-multihe-7961-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multihe-7961-v1/flywheel_model.0.safetensors
Job rirv938-llama-8b-multihe-7961-v1-mkmlizer completed after 207.15s with status: succeeded
Stopping job with name rirv938-llama-8b-multihe-7961-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-multihe-7961-v1
Waiting for inference service rirv938-llama-8b-multihe-7961-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-llama-8b-multihe-7961-v1 ready after 201.48637986183167s
Pipeline stage MKMLDeployer completed in 202.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.189104318618774s
Received healthy response to inference request in 1.816939353942871s
Received healthy response to inference request in 2.87457013130188s
Received healthy response to inference request in 1.9501261711120605s
Received healthy response to inference request in 3.2344088554382324s
5 requests
0 failed requests
5th percentile: 1.843576717376709
10th percentile: 1.870214080810547
20th percentile: 1.9234888076782226
30th percentile: 2.1350149631500246
40th percentile: 2.5047925472259522
50th percentile: 2.87457013130188
60th percentile: 3.0185056209564207
70th percentile: 3.162441110610962
80th percentile: 3.425347948074341
90th percentile: 3.807226133346558
95th percentile: 3.9981652259826657
99th percentile: 4.150916500091553
mean time: 2.8130297660827637
Pipeline stage StressChecker completed in 15.88s
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 2.53s
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 2.20s
Shutdown handler de-registered
rirv938-llama-8b-multihe_7961_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multihe-7961-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-7961-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-7961-v1-profiler ready after 200.59280681610107s
Pipeline stage MKMLProfilerDeployer completed in 200.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplobtrkz:/code/chaiverse_profiler_1731609992 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplobtrkz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731609992 && 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_1731609992/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplobtrkz:/code/chaiverse_profiler_1731612784 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplobtrkz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731612784 && 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_1731612784/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-7961-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-7961-v1-profiler
Service rirv938-llama-8b-multihe-7961-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.07s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-7961-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.23s
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 rirv938-llama-8b-multihe-7961-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-7961-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-7961-v1-profiler ready after 150.35749411582947s
Pipeline stage MKMLProfilerDeployer completed in 150.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deploklwdj:/code/chaiverse_profiler_1731613570 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deploklwdj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731613570 && 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_1731613570/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deploklwdj:/code/chaiverse_profiler_1731616338 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deploklwdj:/code/chaiverse_profiler_1731616339 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deploklwdj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731616339 && 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_1731616339/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-7961-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-7961-v1-profiler
Service rirv938-llama-8b-multihe-7961-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-7961-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multihe-7961-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-7961-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-7961-v1-profiler ready after 90.22451162338257s
Pipeline stage MKMLProfilerDeployer completed in 90.59s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplojssqz:/code/chaiverse_profiler_1731617145 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplojssqz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731617145 && 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_1731617145/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplojssqz:/code/chaiverse_profiler_1731619912 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplojssqz:/code/chaiverse_profiler_1731619913 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul2fca2431a9bed8672cda9c8d6f64c33f-deplojssqz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731619913 && 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_1731619913/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-7961-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-7961-v1-profiler
Service rirv938-llama-8b-multihe-7961-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.01s
Shutdown handler de-registered
rirv938-llama-8b-multihe_7961_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-multihe_7961_v1 status is now torndown due to DeploymentManager action