submission_id: nousresearch-meta-llama_4939_v50
developer_uid: end_to_end_test
best_of: 4
celo_rating: 1184.43
display_name: nousresearch-meta-llama_4939_v50
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, 'top_p': 0.99, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is only for e2e test
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3.1-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4939_v50
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 10768
num_wins: 4579
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-31T00:22:28+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.425241456166419
Download Preference Data
Resubmit model
Deleting key nousresearch-meta-llama-4939-v49/special_tokens_map.json from bucket guanaco-mkml-models
run pipeline %s
Deleting key nousresearch-meta-llama-4939-v49/tokenizer.json from bucket guanaco-mkml-models
run pipeline stage %s
Deleting key nousresearch-meta-llama-4939-v49/tokenizer_config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLizer
Pipeline stage MKMLModelDeleter completed in 8.52s
Starting job with name nousresearch-meta-llama-4939-v50-mkmlizer
nousresearch-meta-llama_4939_v49 status is now torndown due to DeploymentManager action
Waiting for job on nousresearch-meta-llama-4939-v50-mkmlizer to finish
nousresearch-meta-llama-4939-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v50-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ Version: 0.10.1 ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nousresearch-meta-llama-4939-v50-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v50-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v50-mkmlizer: Downloaded to shared memory in 35.880s
nousresearch-meta-llama-4939-v50-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp77f1b_wj, device:0
nousresearch-meta-llama-4939-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v50-mkmlizer: quantized model in 25.981s
nousresearch-meta-llama-4939-v50-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 61.861s
nousresearch-meta-llama-4939-v50-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v50
nousresearch-meta-llama-4939-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v50/special_tokens_map.json
nousresearch-meta-llama-4939-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v50/config.json
nousresearch-meta-llama-4939-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v50/tokenizer_config.json
nousresearch-meta-llama-4939-v50-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v50/tokenizer.json
Job nousresearch-meta-llama-4939-v50-mkmlizer completed after 87.73s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v50-mkmlizer
Pipeline stage MKMLizer completed in 89.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v50
Waiting for inference service nousresearch-meta-llama-4939-v50 to be ready
Inference service nousresearch-meta-llama-4939-v50 ready after 191.93627071380615s
Pipeline stage MKMLDeployer completed in 192.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0392119884490967s
Received healthy response to inference request in 1.5300579071044922s
Received healthy response to inference request in 1.6831412315368652s
Received healthy response to inference request in 2.1177520751953125s
Received healthy response to inference request in 1.3855531215667725s
5 requests
0 failed requests
5th percentile: 1.4144540786743165
10th percentile: 1.4433550357818603
20th percentile: 1.5011569499969482
30th percentile: 1.5606745719909667
40th percentile: 1.621907901763916
50th percentile: 1.6831412315368652
60th percentile: 1.8255695343017577
70th percentile: 1.9679978370666502
80th percentile: 2.0549200057983397
90th percentile: 2.086336040496826
95th percentile: 2.1020440578460695
99th percentile: 2.114610471725464
mean time: 1.7511432647705079
Pipeline stage StressChecker completed in 10.84s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.10s
nousresearch-meta-llama_4939_v50 status is now deployed due to DeploymentManager action
run pipeline %s
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 nousresearch-meta-llama-4939-v50-profiler
Waiting for inference service nousresearch-meta-llama-4939-v50-profiler to be ready
Inference service nousresearch-meta-llama-4939-v50-profiler ready after 180.416277885437s
Pipeline stage MKMLProfilerDeployer completed in 180.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.35s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service nousresearch-meta-llama-4939-v50-profiler is running
Tearing down inference service nousresearch-meta-llama-4939-v50-profiler
Service nousresearch-meta-llama-4939-v50-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.83s
nousresearch-meta-llama_4939_v50 status is now inactive due to auto deactivation removed underperforming models
nousresearch-meta-llama_4939_v50 status is now torndown due to DeploymentManager action