developer_uid: jiayi1
submission_id: meta-llama-meta-llama-3-8b_v17
model_name: test_01
model_group: meta-llama/Meta-Llama-3-
status: torndown
timestamp: 2025-01-07T10:21:09+00:00
num_battles: 9634
num_wins: 3914
celo_rating: 1196.25
family_friendly_score: 0.593
family_friendly_standard_error: 0.00694767587039004
submission_type: basic
model_repo: meta-llama/Meta-Llama-3-8B
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8718667808535356, 'latency_mean': 1.1468763852119446, 'latency_p50': 1.1455415487289429, 'latency_p90': 1.267365288734436}, {'batch_size': 4, 'throughput': 1.8676625529237345, 'latency_mean': 2.132639756202698, 'latency_p50': 2.129624366760254, 'latency_p90': 2.322745752334595}, {'batch_size': 5, 'throughput': 1.9985768343442267, 'latency_mean': 2.4810811460018156, 'latency_p50': 2.4816750288009644, 'latency_p90': 2.7291014194488525}, {'batch_size': 8, 'throughput': 2.2292061011297943, 'latency_mean': 3.560294053554535, 'latency_p50': 3.594799280166626, 'latency_p90': 4.008766674995422}, {'batch_size': 10, 'throughput': 2.283253154849226, 'latency_mean': 4.346350429058075, 'latency_p50': 4.391378283500671, 'latency_p90': 4.887363529205322}, {'batch_size': 12, 'throughput': 2.3185925363464657, 'latency_mean': 5.121398162841797, 'latency_p50': 5.151126027107239, 'latency_p90': 5.754642200469971}, {'batch_size': 15, 'throughput': 2.344767397680361, 'latency_mean': 6.3116320192813875, 'latency_p50': 6.344835877418518, 'latency_p90': 7.015512323379516}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: test_01
is_internal_developer: False
language_model: meta-llama/Meta-Llama-3-8B
model_size: 8B
ranking_group: single
throughput_3p7s: 2.26
us_pacific_date: 2025-01-07
win_ratio: 0.40626946232094663
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-meta-llama-3-8b-v17-mkmlizer
Waiting for job on meta-llama-meta-llama-3-8b-v17-mkmlizer to finish
meta-llama-meta-llama-3-8b-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ Version: 0.11.12 ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ║ ║
meta-llama-meta-llama-3-8b-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-8b-v17-mkmlizer: Downloaded to shared memory in 48.927s
meta-llama-meta-llama-3-8b-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1538mlp, device:0
meta-llama-meta-llama-3-8b-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-8b-v17-mkmlizer: quantized model in 26.752s
meta-llama-meta-llama-3-8b-v17-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B in 75.679s
meta-llama-meta-llama-3-8b-v17-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-8b-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-8b-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17
meta-llama-meta-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17/config.json
meta-llama-meta-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17/special_tokens_map.json
meta-llama-meta-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17/tokenizer_config.json
meta-llama-meta-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17/tokenizer.json
meta-llama-meta-llama-3-8b-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v17/flywheel_model.0.safetensors
Job meta-llama-meta-llama-3-8b-v17-mkmlizer completed after 104.28s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-8b-v17-mkmlizer
Pipeline stage MKMLizer completed in 104.76s
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-meta-llama-3-8b-v17
Waiting for inference service meta-llama-meta-llama-3-8b-v17 to be ready
Inference service meta-llama-meta-llama-3-8b-v17 ready after 352.40234184265137s
Pipeline stage MKMLDeployer completed in 352.85s
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 2.0184454917907715s
Received healthy response to inference request in 1.4157764911651611s
Received healthy response to inference request in 1.2511441707611084s
Received healthy response to inference request in 6.167036771774292s
5 requests
1 failed requests
5th percentile: 1.2840706348419189
10th percentile: 1.3169970989227295
20th percentile: 1.3828500270843507
30th percentile: 1.5363102912902833
40th percentile: 1.7773778915405274
50th percentile: 2.0184454917907715
60th percentile: 3.6778820037841795
70th percentile: 5.3373185157775875
80th percentile: 8.96121430397034
90th percentile: 14.549569368362427
95th percentile: 17.343746900558468
99th percentile: 19.579088926315308
mean time: 6.19806547164917
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2979423999786377s
Received healthy response to inference request in 1.2984976768493652s
Received healthy response to inference request in 1.3612034320831299s
Received healthy response to inference request in 1.2719016075134277s
Received healthy response to inference request in 1.3407323360443115s
5 requests
0 failed requests
5th percentile: 1.2771097660064696
10th percentile: 1.2823179244995118
20th percentile: 1.2927342414855958
30th percentile: 1.2980534553527832
40th percentile: 1.2982755661010743
50th percentile: 1.2984976768493652
60th percentile: 1.3153915405273438
70th percentile: 1.3322854042053223
80th percentile: 1.3448265552520753
90th percentile: 1.3530149936676026
95th percentile: 1.3571092128753661
99th percentile: 1.360384588241577
mean time: 1.3140554904937745
Pipeline stage StressChecker completed in 40.14s
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 0.71s
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 0.81s
Shutdown handler de-registered
meta-llama-meta-llama-3-8b_v17 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service meta-llama-meta-llama-3-8b-v17-profiler
Waiting for inference service meta-llama-meta-llama-3-8b-v17-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 2300.26s
Shutdown handler de-registered
meta-llama-meta-llama-3-8b_v17 status is now inactive due to auto deactivation removed underperforming models
meta-llama-meta-llama-3-8b_v17 status is now torndown due to DeploymentManager action