nvidia-llama-3-1-nemotr_90076

developer_uid: NischayDnk

submission_id: nvidia-llama-3-1-nemotr_90076_v1

model_name: nvidia-llama-3-1-nemotr_90076_v1

model_group: nvidia/Llama-3.1-Nemotro

status: torndown

timestamp: 2025-04-09T22:31:28+00:00

num_battles: 6671

num_wins: 1695

celo_rating: 1091.32

family_friendly_score: 0.7612

family_friendly_standard_error: 0.006029503462143463

submission_type: basic

model_repo: nvidia/Llama-3.1-Nemotron-Nano-8B-v1

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.8522492574356436, 'latency_mean': 1.1733026087284089, 'latency_p50': 1.172040581703186, 'latency_p90': 1.3041963577270508}, {'batch_size': 4, 'throughput': 1.7916223382803793, 'latency_mean': 2.2264898335933685, 'latency_p50': 2.2181206941604614, 'latency_p90': 2.4689576387405396}, {'batch_size': 5, 'throughput': 1.9200985201917866, 'latency_mean': 2.5921551418304443, 'latency_p50': 2.590139865875244, 'latency_p90': 2.87287859916687}, {'batch_size': 8, 'throughput': 2.1432964491884765, 'latency_mean': 3.70583602309227, 'latency_p50': 3.7391101121902466, 'latency_p90': 4.144318222999573}, {'batch_size': 10, 'throughput': 2.1881069621599623, 'latency_mean': 4.530903775691986, 'latency_p50': 4.550515174865723, 'latency_p90': 5.130789947509766}, {'batch_size': 12, 'throughput': 2.223266232328614, 'latency_mean': 5.342088930606842, 'latency_p50': 5.356830835342407, 'latency_p90': 6.069124817848206}, {'batch_size': 15, 'throughput': 2.2304448685929525, 'latency_mean': 6.628514684438706, 'latency_p50': 6.61847984790802, 'latency_p90': 7.413778638839721}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nvidia-llama-3-1-nemotr_90076_v1

is_internal_developer: False

language_model: nvidia/Llama-3.1-Nemotron-Nano-8B-v1

model_size: 8B

ranking_group: single

throughput_3p7s: 2.16

us_pacific_date: 2025-04-09

win_ratio: 0.2540848448508469

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.02, '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 nvidia-llama-3-1-nemotr-90076-v1-mkmlizer
Waiting for job on nvidia-llama-3-1-nemotr-90076-v1-mkmlizer to finish
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║     _____            __           __                                ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║       /___/                                                         ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║                                                                     ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  https://mk1.ai                                                     ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║                                                                     ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  belonging to:                                                      ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║                                                                     ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ║                                                                     ║
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: Downloaded to shared memory in 31.890s
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxi1yki4v, device:0
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: quantized model in 25.956s
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: Processed model nvidia/Llama-3.1-Nemotron-Nano-8B-v1 in 57.847s
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: creating bucket guanaco-mkml-models
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1/config.json
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1/special_tokens_map.json
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1/tokenizer_config.json
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1/tokenizer.json
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nvidia-llama-3-1-nemotr-90076-v1/flywheel_model.0.safetensors
nvidia-llama-3-1-nemotr-90076-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.63it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 43.64it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 49.45it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 51.40it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 53.56it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 54.88it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 55.35it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 60.34it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 58.48it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:03, 57.23it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:06, 33.99it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:04, 41.89it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 43.12it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 46.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 48.57it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 47.74it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 49.53it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.01it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 47.01it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:03, 44.48it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.84it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 47.45it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.39it/s]
Loading 0:  56%|█████▋    | 164/291 [00:03<00:02, 44.94it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 42.83it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 47.16it/s]
Loading 0:  62%|██████▏   | 180/291 [00:03<00:02, 43.48it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 44.00it/s]
Loading 0:  65%|██████▌   | 190/291 [00:04<00:03, 27.40it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 28.67it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 37.64it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 39.29it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 41.35it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 47.43it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 46.24it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 46.09it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 52.23it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 50.17it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 48.66it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.13it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 46.85it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 46.00it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 50.86it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 48.38it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 47.85it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.27it/s]
                                                            
Job nvidia-llama-3-1-nemotr-90076-v1-mkmlizer completed after 84.21s with status: succeeded
Stopping job with name nvidia-llama-3-1-nemotr-90076-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nvidia-llama-3-1-nemotr-90076-v1
Waiting for inference service nvidia-llama-3-1-nemotr-90076-v1 to be ready
Inference service nvidia-llama-3-1-nemotr-90076-v1 ready after 110.54020142555237s
Pipeline stage MKMLDeployer completed in 111.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8007917404174805s
Received healthy response to inference request in 1.249009609222412s
Received healthy response to inference request in 1.4448649883270264s
Received healthy response to inference request in 1.220520257949829s
Received healthy response to inference request in 1.3136870861053467s
5 requests
0 failed requests
5th percentile: 1.2262181282043456
10th percentile: 1.2319159984588623
20th percentile: 1.2433117389678956
30th percentile: 1.2619451045989991
40th percentile: 1.287816095352173
50th percentile: 1.3136870861053467
60th percentile: 1.3661582469940186
70th percentile: 1.4186294078826904
80th percentile: 1.5160503387451172
90th percentile: 1.6584210395812988
95th percentile: 1.7296063899993896
99th percentile: 1.7865546703338624
mean time: 1.4057747364044189
Pipeline stage StressChecker completed in 8.20s
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 0.66s
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 0.65s
Shutdown handler de-registered
nvidia-llama-3-1-nemotr_90076_v1 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 0.09s
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 nvidia-llama-3-1-nemotr-90076-v1-profiler
Waiting for inference service nvidia-llama-3-1-nemotr-90076-v1-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 2405.38s
Shutdown handler de-registered
nvidia-llama-3-1-nemotr_90076_v1 status is now inactive due to auto deactivation removed underperforming models
nvidia-llama-3-1-nemotr_90076_v1 status is now torndown due to DeploymentManager action