developer_uid: bogoconic1
submission_id: meta-llama-llama-3-1-8b_7331_v11
model_name: meta-llama-llama-3-1-8b_7331_v11
model_group: meta-llama/Llama-3.1-8B-
status: torndown
timestamp: 2025-04-29T12:10:53+00:00
num_battles: 8137
num_wins: 3591
celo_rating: 1242.12
family_friendly_score: 0.6528
family_friendly_standard_error: 0.006732787832688626
submission_type: basic
model_repo: meta-llama/Llama-3.1-8B-Instruct
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8535921374956918, 'latency_mean': 1.1714542520046234, 'latency_p50': 1.1794224977493286, 'latency_p90': 1.294944953918457}, {'batch_size': 4, 'throughput': 1.8164796818877347, 'latency_mean': 2.1901740515232087, 'latency_p50': 2.1953357458114624, 'latency_p90': 2.478584408760071}, {'batch_size': 5, 'throughput': 1.9471762636677579, 'latency_mean': 2.5623744893074036, 'latency_p50': 2.5716651678085327, 'latency_p90': 2.8583330392837523}, {'batch_size': 8, 'throughput': 2.13149501537054, 'latency_mean': 3.7235474717617034, 'latency_p50': 3.754328489303589, 'latency_p90': 4.152997994422913}, {'batch_size': 10, 'throughput': 2.200701168443812, 'latency_mean': 4.497839430570602, 'latency_p50': 4.539891958236694, 'latency_p90': 5.047207641601562}, {'batch_size': 12, 'throughput': 2.237462758167264, 'latency_mean': 5.316116899251938, 'latency_p50': 5.3736371994018555, 'latency_p90': 5.877039098739624}, {'batch_size': 15, 'throughput': 2.2457470045451022, 'latency_mean': 6.579268972873688, 'latency_p50': 6.59273362159729, 'latency_p90': 7.41103675365448}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: meta-llama-llama-3-1-8b_7331_v11
is_internal_developer: True
language_model: meta-llama/Llama-3.1-8B-Instruct
model_size: 8B
ranking_group: single
throughput_3p7s: 2.15
us_pacific_date: 2025-04-29
win_ratio: 0.44131743885953056
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 meta-llama-llama-3-1-8b-7331-v11-mkmlizer
Waiting for job on meta-llama-llama-3-1-8b-7331-v11-mkmlizer to finish
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║     _____            __           __                                ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║       /___/                                                         ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  Version: 0.12.8                                                    ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  belonging to:                                                      ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: Downloaded to shared memory in 41.684s
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbx1zgxg3, device:0
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: quantized model in 27.729s
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: Processed model meta-llama/Llama-3.1-8B-Instruct in 69.413s
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v11
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v11/config.json
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v11/special_tokens_map.json
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v11/tokenizer_config.json
meta-llama-llama-3-1-8b-7331-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v11/tokenizer.json
Job meta-llama-llama-3-1-8b-7331-v11-mkmlizer completed after 109.34s with status: succeeded
Stopping job with name meta-llama-llama-3-1-8b-7331-v11-mkmlizer
Pipeline stage MKMLizer completed in 110.03s
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 meta-llama-llama-3-1-8b-7331-v11
Waiting for inference service meta-llama-llama-3-1-8b-7331-v11 to be ready
Inference service meta-llama-llama-3-1-8b-7331-v11 ready after 140.63203930854797s
Pipeline stage MKMLDeployer completed in 141.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3629310131073s
Received healthy response to inference request in 1.5726535320281982s
Received healthy response to inference request in 1.5906643867492676s
Received healthy response to inference request in 1.492253065109253s
Received healthy response to inference request in 1.4584224224090576s
5 requests
0 failed requests
5th percentile: 1.4651885509490967
10th percentile: 1.4719546794891358
20th percentile: 1.4854869365692138
30th percentile: 1.508333158493042
40th percentile: 1.5404933452606202
50th percentile: 1.5726535320281982
60th percentile: 1.579857873916626
70th percentile: 1.5870622158050538
80th percentile: 1.745117712020874
90th percentile: 2.054024362564087
95th percentile: 2.208477687835693
99th percentile: 2.3320403480529786
mean time: 1.6953848838806151
Pipeline stage StressChecker completed in 9.83s
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 0.75s
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 0.71s
Shutdown handler de-registered
meta-llama-llama-3-1-8b_7331_v11 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 0.13s
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 meta-llama-llama-3-1-8b-7331-v11-profiler
Waiting for inference service meta-llama-llama-3-1-8b-7331-v11-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2549.01s
Shutdown handler de-registered
meta-llama-llama-3-1-8b_7331_v11 status is now inactive due to auto deactivation removed underperforming models
meta-llama-llama-3-1-8b_7331_v11 status is now torndown due to DeploymentManager action