developer_uid: NischayDnk
submission_id: nousresearch-meta-lla_49417_v100
model_name: nousresearch-meta-lla_49417_v100
model_group: NousResearch/Meta-Llama-
status: torndown
timestamp: 2025-04-09T22:34:08+00:00
num_battles: 6312
num_wins: 2756
celo_rating: 1227.77
family_friendly_score: 0.6437999999999999
family_friendly_standard_error: 0.006772319543553744
submission_type: basic
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
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': 0.8446194661977039, 'latency_mean': 1.1839004266262054, 'latency_p50': 1.194342017173767, 'latency_p90': 1.3033437490463258}, {'batch_size': 4, 'throughput': 1.7693950697435152, 'latency_mean': 2.251284453868866, 'latency_p50': 2.2602903842926025, 'latency_p90': 2.5462408304214477}, {'batch_size': 5, 'throughput': 1.9112104369296612, 'latency_mean': 2.5975968647003174, 'latency_p50': 2.596548080444336, 'latency_p90': 2.897284483909607}, {'batch_size': 8, 'throughput': 2.1414338376954145, 'latency_mean': 3.7165813350677492, 'latency_p50': 3.7274194955825806, 'latency_p90': 4.16852445602417}, {'batch_size': 10, 'throughput': 2.1677794970682456, 'latency_mean': 4.573817018270493, 'latency_p50': 4.603637456893921, 'latency_p90': 5.159499835968018}, {'batch_size': 12, 'throughput': 2.2075233263211653, 'latency_mean': 5.385495047569275, 'latency_p50': 5.435672760009766, 'latency_p90': 5.974556398391724}, {'batch_size': 15, 'throughput': 2.213111845984996, 'latency_mean': 6.686356360912323, 'latency_p50': 6.732022285461426, 'latency_p90': 7.4154431343078615}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: nousresearch-meta-lla_49417_v100
is_internal_developer: False
language_model: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
ranking_group: single
throughput_3p7s: 2.15
us_pacific_date: 2025-04-09
win_ratio: 0.43662864385297845
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 nousresearch-meta-lla-49417-v100-mkmlizer
Waiting for job on nousresearch-meta-lla-49417-v100-mkmlizer to finish
nousresearch-meta-lla-49417-v100-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-lla-49417-v100-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║                                                                     ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  Version: 0.12.8                                                    ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║                                                                     ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║                                                                     ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nousresearch-meta-lla-49417-v100-mkmlizer: ║                                                                     ║
nousresearch-meta-lla-49417-v100-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-lla-49417-v100-mkmlizer: Downloaded to shared memory in 25.091s
nousresearch-meta-lla-49417-v100-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5mcr4utn, device:0
nousresearch-meta-lla-49417-v100-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-lla-49417-v100-mkmlizer: quantized model in 25.776s
nousresearch-meta-lla-49417-v100-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 50.868s
nousresearch-meta-lla-49417-v100-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-lla-49417-v100-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-lla-49417-v100-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-lla-49417-v100
nousresearch-meta-lla-49417-v100-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-lla-49417-v100/tokenizer_config.json
nousresearch-meta-lla-49417-v100-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-lla-49417-v100/tokenizer.json
nousresearch-meta-lla-49417-v100-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-lla-49417-v100/flywheel_model.0.safetensors
nousresearch-meta-lla-49417-v100-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.04it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 47.04it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.21it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 52.46it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 53.61it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 54.66it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 53.45it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 57.82it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 53.17it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 53.79it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 38.22it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:05, 38.84it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:04, 40.99it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 46.44it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 45.93it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 46.17it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 51.15it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 45.50it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 45.00it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 51.22it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 48.36it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 49.26it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 50.48it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 47.07it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 45.60it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 53.71it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 44.95it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 34.54it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 35.82it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 36.70it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 39.54it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 42.08it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 39.70it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 46.27it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 46.54it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 42.02it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.59it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 47.86it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 47.58it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 52.51it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 50.23it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 51.36it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 51.30it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 49.41it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 46.24it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  3.40it/s]
                                                            

Job nousresearch-meta-lla-49417-v100-mkmlizer completed after 73.61s with status: succeeded
Stopping job with name nousresearch-meta-lla-49417-v100-mkmlizer
Pipeline stage MKMLizer completed in 74.06s
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 nousresearch-meta-lla-49417-v100
Waiting for inference service nousresearch-meta-lla-49417-v100 to be ready
Inference service nousresearch-meta-lla-49417-v100 ready after 110.4670262336731s
Pipeline stage MKMLDeployer completed in 110.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.24833083152771s
Received healthy response to inference request in 1.4082281589508057s
Received healthy response to inference request in 1.5666770935058594s
Received healthy response to inference request in 1.3328111171722412s
Received healthy response to inference request in 1.168226718902588s
5 requests
0 failed requests
5th percentile: 1.2011435985565186
10th percentile: 1.2340604782104492
20th percentile: 1.2998942375183105
30th percentile: 1.3478945255279542
40th percentile: 1.37806134223938
50th percentile: 1.4082281589508057
60th percentile: 1.4716077327728272
70th percentile: 1.5349873065948485
80th percentile: 1.7030078411102296
90th percentile: 1.97566933631897
95th percentile: 2.1120000839233395
99th percentile: 2.221064682006836
mean time: 1.5448547840118407
Pipeline stage StressChecker completed in 8.89s
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 0.68s
Shutdown handler de-registered
nousresearch-meta-lla_49417_v100 status is now deployed due to DeploymentManager action
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 2421.99s
Shutdown handler de-registered
nousresearch-meta-lla_49417_v100 status is now inactive due to auto deactivation removed underperforming models
nousresearch-meta-lla_49417_v100 status is now torndown due to DeploymentManager action