rirv938-llama-8b-multihe_3555

developer_uid: robert_irvine
submission_id: rirv938-llama-8b-multihe_3555_v1
model_name: rirv938-llama-8b-multihe_3555_v1
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2024-11-07T22:22:35+00:00
num_battles: 15560
num_wins: 6707
celo_rating: 1193.91
family_friendly_score: 0.6044
family_friendly_standard_error: 0.006915209902815677
submission_type: basic
model_repo: rirv938/llama_8b_multihead_57m_nsfw
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_3555_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_57m_nsfw
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-07
win_ratio: 0.43104113110539843
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-3555-v1-mkmlizer
Waiting for job on rirv938-llama-8b-multihe-3555-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  Version: 0.11.33                                                   ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-3555-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_gerot_2024-10-19: ('http://chaiml-llama-8b-pairwis-8189-v27-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41888->127.0.0.1:8080: read: connection reset by peer\n')
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
rirv938-llama-8b-multihe-3555-v1-mkmlizer: Downloaded to shared memory in 232.123s
rirv938-llama-8b-multihe-3555-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpa0xt4vsx, device:0
rirv938-llama-8b-multihe-3555-v1-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
rirv938-llama-8b-multihe-3555-v1-mkmlizer: quantized model in 89.152s
rirv938-llama-8b-multihe-3555-v1-mkmlizer: Processed model rirv938/llama_8b_multihead_57m_nsfw in 321.276s
rirv938-llama-8b-multihe-3555-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multihe-3555-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multihe-3555-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1
rirv938-llama-8b-multihe-3555-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1/config.json
rirv938-llama-8b-multihe-3555-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1/special_tokens_map.json
rirv938-llama-8b-multihe-3555-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1/tokenizer_config.json
rirv938-llama-8b-multihe-3555-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1/tokenizer.json
rirv938-llama-8b-multihe-3555-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multihe-3555-v1/flywheel_model.0.safetensors
Job rirv938-llama-8b-multihe-3555-v1-mkmlizer completed after 351.19s with status: succeeded
Stopping job with name rirv938-llama-8b-multihe-3555-v1-mkmlizer
Pipeline stage MKMLizer completed in 351.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-multihe-3555-v1
Waiting for inference service rirv938-llama-8b-multihe-3555-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
Inference service rirv938-llama-8b-multihe-3555-v1 ready after 170.58511018753052s
Pipeline stage MKMLDeployer completed in 171.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6417007446289062s
Received healthy response to inference request in 1.5358359813690186s
Received healthy response to inference request in 3.0106284618377686s
Received healthy response to inference request in 3.623760223388672s
Received healthy response to inference request in 2.7368645668029785s
5 requests
0 failed requests
5th percentile: 1.757008934020996
10th percentile: 1.9781818866729737
20th percentile: 2.420527791976929
30th percentile: 2.6607335090637205
40th percentile: 2.6987990379333495
50th percentile: 2.7368645668029785
60th percentile: 2.8463701248168944
70th percentile: 2.9558756828308104
80th percentile: 3.1332548141479495
90th percentile: 3.3785075187683105
95th percentile: 3.501133871078491
99th percentile: 3.599234952926636
mean time: 2.709757995605469
Pipeline stage StressChecker completed in 15.08s
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 2.72s
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 3.00s
Shutdown handler de-registered
rirv938-llama-8b-multihe_3555_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multihe-3555-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-3555-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-3555-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.82s
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-3555-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-3555-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-3555-v1-profiler ready after 120.2904109954834s
Pipeline stage MKMLProfilerDeployer completed in 120.63s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mulcfac0cc0091ce450dae4ff1e737996b8-deplohq4vb:/code/chaiverse_profiler_1731024760 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mulcfac0cc0091ce450dae4ff1e737996b8-deplohq4vb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731024760 && 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_1731024760/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mulcfac0cc0091ce450dae4ff1e737996b8-deplohq4vb:/code/chaiverse_profiler_1731026840 --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-mulcfac0cc0091ce450dae4ff1e737996b8-deplohq4vb:/code/chaiverse_profiler_1731026840 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mulcfac0cc0091ce450dae4ff1e737996b8-deplohq4vb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731026840 && 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_1731026840/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-3555-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-3555-v1-profiler
Service rirv938-llama-8b-multihe-3555-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.01s
Shutdown handler de-registered
rirv938-llama-8b-multihe_3555_v1 status is now inactive due to auto deactivation removed underperforming models
Deleting key rirv938-llama-8b-multihe-5639-v1/tokenizer.json from bucket guanaco-mkml-models
rirv938-llama-8b-multihe_3555_v1 status is now torndown due to DeploymentManager action