meta-llama-meta-llama-_53865

developer_uid: rica40325

submission_id: meta-llama-meta-llama-_53865_v12

model_name: meta-llama-meta-llama-_53865_v12

model_group: meta-llama/Meta-Llama-3-

status: torndown

timestamp: 2025-03-11T12:32:49+00:00

num_battles: 13235

num_wins: 5356

celo_rating: 1211.14

family_friendly_score: 0.6502

family_friendly_standard_error: 0.006744478630702302

submission_type: basic

model_repo: meta-llama/Meta-Llama-3-8B-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': 0.8348622232076359, 'latency_mean': 1.197732502222061, 'latency_p50': 1.2003403902053833, 'latency_p90': 1.3201200246810914}, {'batch_size': 4, 'throughput': 1.7486500094393782, 'latency_mean': 2.2739748513698577, 'latency_p50': 2.2724605798721313, 'latency_p90': 2.5440354108810426}, {'batch_size': 5, 'throughput': 1.886395182098319, 'latency_mean': 2.64024080991745, 'latency_p50': 2.633581280708313, 'latency_p90': 2.930198836326599}, {'batch_size': 8, 'throughput': 2.0684557701313286, 'latency_mean': 3.843261125087738, 'latency_p50': 3.8412346839904785, 'latency_p90': 4.3846375942230225}, {'batch_size': 10, 'throughput': 2.1200192269886444, 'latency_mean': 4.687804243564606, 'latency_p50': 4.706663250923157, 'latency_p90': 5.238546133041382}, {'batch_size': 12, 'throughput': 2.1476905025530306, 'latency_mean': 5.525243538618088, 'latency_p50': 5.508439064025879, 'latency_p90': 6.306067419052124}, {'batch_size': 15, 'throughput': 2.1590337725929674, 'latency_mean': 6.849507834911346, 'latency_p50': 6.87001633644104, 'latency_p90': 7.683525085449219}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: meta-llama-meta-llama-_53865_v12

is_internal_developer: False

language_model: meta-llama/Meta-Llama-3-8B-Instruct

model_size: 8B

ranking_group: single

throughput_3p7s: 2.07

us_pacific_date: 2025-03-11

win_ratio: 0.4046845485455232

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-53865-v12-mkmlizer
Waiting for job on meta-llama-meta-llama-53865-v12-mkmlizer to finish
meta-llama-meta-llama-53865-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-53865-v12-mkmlizer: ║     _____            __           __                                ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║       /___/                                                         ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  Version: 0.12.8                                                    ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  belonging to:                                                      ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
meta-llama-meta-llama-53865-v12-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-53865-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-53865-v12-mkmlizer: Downloaded to shared memory in 37.024s
meta-llama-meta-llama-53865-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2w7_ll7o, device:0
meta-llama-meta-llama-53865-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-53865-v12-mkmlizer: quantized model in 25.570s
meta-llama-meta-llama-53865-v12-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B-Instruct in 62.595s
meta-llama-meta-llama-53865-v12-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-53865-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-53865-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12
meta-llama-meta-llama-53865-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12/config.json
meta-llama-meta-llama-53865-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12/special_tokens_map.json
meta-llama-meta-llama-53865-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12/tokenizer_config.json
meta-llama-meta-llama-53865-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12/tokenizer.json
meta-llama-meta-llama-53865-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-53865-v12/flywheel_model.0.safetensors
meta-llama-meta-llama-53865-v12-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.72it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 47.35it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 51.20it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 53.14it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 53.89it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 53.96it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:03, 59.87it/s]
Loading 0:  22%|██▏       | 65/291 [00:01<00:03, 57.37it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:03, 56.15it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:04, 49.13it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 39.01it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 39.72it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 40.67it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:03, 48.78it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 47.88it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 49.68it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 46.35it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 53.65it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 51.09it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 52.10it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:02, 49.52it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:02, 51.47it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 55.02it/s]
Loading 0:  59%|█████▉    | 171/291 [00:03<00:02, 51.41it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 49.77it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 50.43it/s]
Loading 0:  65%|██████▍   | 189/291 [00:03<00:03, 33.82it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 36.30it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 44.82it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 44.65it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 47.19it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 49.77it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 48.41it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 49.77it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:01, 51.87it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 50.27it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 51.58it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 53.18it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 50.81it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 52.10it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 48.60it/s]
Loading 0:  97%|█████████▋| 282/291 [00:05<00:00, 47.32it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.55it/s]
                                                            
Job meta-llama-meta-llama-53865-v12-mkmlizer completed after 83.77s with status: succeeded
Stopping job with name meta-llama-meta-llama-53865-v12-mkmlizer
Pipeline stage MKMLizer completed in 84.34s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-meta-llama-53865-v12
Waiting for inference service meta-llama-meta-llama-53865-v12 to be ready
Inference service meta-llama-meta-llama-53865-v12 ready after 90.31497049331665s
Pipeline stage MKMLDeployer completed in 90.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.802170753479004s
Received healthy response to inference request in 1.1558420658111572s
Received healthy response to inference request in 1.3311593532562256s
Received healthy response to inference request in 1.32216215133667s
Received healthy response to inference request in 1.3738808631896973s
5 requests
0 failed requests
5th percentile: 1.1891060829162599
10th percentile: 1.2223701000213623
20th percentile: 1.2888981342315673
30th percentile: 1.3239615917205811
40th percentile: 1.3275604724884034
50th percentile: 1.3311593532562256
60th percentile: 1.3482479572296142
70th percentile: 1.3653365612030028
80th percentile: 1.4595388412475587
90th percentile: 1.6308547973632812
95th percentile: 1.7165127754211424
99th percentile: 1.7850391578674316
mean time: 1.3970430374145508
Pipeline stage StressChecker completed in 8.42s
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 0.62s
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-meta-llama-_53865_v12 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 0.10s
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-meta-llama-53865-v12-profiler
Waiting for inference service meta-llama-meta-llama-53865-v12-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 3673.70s
Shutdown handler de-registered
meta-llama-meta-llama-_53865_v12 status is now inactive due to auto deactivation removed underperforming models
meta-llama-meta-llama-_53865_v12 status is now torndown due to DeploymentManager action