developer_uid: bogoconic1
submission_id: meta-llama-llama-3-1-8b-_7331_v9
model_name: meta-llama-llama-3-1-8b-_7331_v9
model_group: meta-llama/Llama-3.1-8B-
status: torndown
timestamp: 2025-04-26T10:20:53+00:00
num_battles: 6859
num_wins: 2793
celo_rating: 1215.24
family_friendly_score: 0.652
family_friendly_standard_error: 0.006736408538679939
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': 0.8456478742807676, 'latency_mean': 1.1824661922454833, 'latency_p50': 1.1773123741149902, 'latency_p90': 1.3086817502975463}, {'batch_size': 4, 'throughput': 1.7680598544618722, 'latency_mean': 2.2497014784812928, 'latency_p50': 2.2521073818206787, 'latency_p90': 2.493956780433655}, {'batch_size': 5, 'throughput': 1.8933495579011783, 'latency_mean': 2.6256649541854857, 'latency_p50': 2.6315133571624756, 'latency_p90': 2.9030093431472777}, {'batch_size': 8, 'throughput': 2.1048764704089153, 'latency_mean': 3.7647667646408083, 'latency_p50': 3.767786383628845, 'latency_p90': 4.218079543113708}, {'batch_size': 10, 'throughput': 2.136627066410601, 'latency_mean': 4.643876881599426, 'latency_p50': 4.695489525794983, 'latency_p90': 5.120759224891662}, {'batch_size': 12, 'throughput': 2.165052920118729, 'latency_mean': 5.496908690929413, 'latency_p50': 5.533096551895142, 'latency_p90': 6.19813494682312}, {'batch_size': 15, 'throughput': 2.1866808532380615, 'latency_mean': 6.773029870986939, 'latency_p50': 6.763006925582886, 'latency_p90': 7.589442467689514}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: meta-llama-llama-3-1-8b-_7331_v9
is_internal_developer: True
language_model: meta-llama/Llama-3.1-8B-Instruct
model_size: 8B
ranking_group: single
throughput_3p7s: 2.12
us_pacific_date: 2025-04-26
win_ratio: 0.407202216066482
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': "{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}
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-v9-mkmlizer
Waiting for job on meta-llama-llama-3-1-8b-7331-v9-mkmlizer to finish
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║     _____            __           __                                ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║       /___/                                                         ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  Version: 0.12.8                                                    ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  belonging to:                                                      ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ║                                                                     ║
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: Downloaded to shared memory in 37.443s
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpasdnv2cq, device:0
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: quantized model in 27.222s
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: Processed model meta-llama/Llama-3.1-8B-Instruct in 64.665s
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9/config.json
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9/special_tokens_map.json
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9/tokenizer_config.json
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9/tokenizer.json
meta-llama-llama-3-1-8b-7331-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-llama-3-1-8b-7331-v9/flywheel_model.0.safetensors
Job meta-llama-llama-3-1-8b-7331-v9-mkmlizer completed after 109.54s with status: succeeded
Stopping job with name meta-llama-llama-3-1-8b-7331-v9-mkmlizer
Pipeline stage MKMLizer completed in 110.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-llama-3-1-8b-7331-v9
Waiting for inference service meta-llama-llama-3-1-8b-7331-v9 to be ready
Inference service meta-llama-llama-3-1-8b-7331-v9 ready after 140.66366696357727s
Pipeline stage MKMLDeployer completed in 141.22s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.199122190475464s
Received healthy response to inference request in 1.1480426788330078s
Received healthy response to inference request in 1.397089958190918s
Received healthy response to inference request in 1.3978767395019531s
5 requests
1 failed requests
5th percentile: 1.1978521347045898
10th percentile: 1.2476615905761719
20th percentile: 1.347280502319336
30th percentile: 1.397247314453125
40th percentile: 1.397562026977539
50th percentile: 1.3978767395019531
60th percentile: 1.7183749198913574
70th percentile: 2.0388731002807616
80th percentile: 5.786371707916263
90th percentile: 12.960870742797853
95th percentile: 16.548120260238644
99th percentile: 19.417919874191284
mean time: 5.255500268936157
%s, retrying in %s seconds...
Received healthy response to inference request in 1.1298003196716309s
Received healthy response to inference request in 1.0620100498199463s
Received healthy response to inference request in 1.45570707321167s
Received healthy response to inference request in 1.2131397724151611s
Received healthy response to inference request in 1.2354655265808105s
5 requests
0 failed requests
5th percentile: 1.0755681037902831
10th percentile: 1.0891261577606202
20th percentile: 1.116242265701294
30th percentile: 1.146468210220337
40th percentile: 1.179803991317749
50th percentile: 1.2131397724151611
60th percentile: 1.222070074081421
70th percentile: 1.2310003757476806
80th percentile: 1.2795138359069824
90th percentile: 1.3676104545593262
95th percentile: 1.411658763885498
99th percentile: 1.4468974113464355
mean time: 1.2192245483398438
Pipeline stage StressChecker completed in 34.95s
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 0.81s
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 0.67s
Shutdown handler de-registered
meta-llama-llama-3-1-8b-_7331_v9 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service meta-llama-llama-3-1-8b-7331-v9-profiler
Waiting for inference service meta-llama-llama-3-1-8b-7331-v9-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4073.67s
Shutdown handler de-registered
meta-llama-llama-3-1-8b-_7331_v9 status is now inactive due to auto deactivation removed underperforming models
meta-llama-llama-3-1-8b-_7331_v9 status is now torndown due to DeploymentManager action