submission_id: nousresearch-meta-llama_4939_v10
developer_uid: end_to_end_test
best_of: 4
display_name: nousresearch-meta-llama_4939_v10
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, 'top_p': 0.99, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is only for e2e test
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3.1-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4939_v10
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 974
num_wins: 417
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-29T04:44:18+00:00
us_pacific_date: 2024-08-28
win_ratio: 0.42813141683778233
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v10-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v10-mkmlizer to finish
nousresearch-meta-llama-4939-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v10-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v10-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v10-mkmlizer: Downloaded to shared memory in 59.822s
nousresearch-meta-llama-4939-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpckp06ni6, device:0
nousresearch-meta-llama-4939-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v10-mkmlizer: quantized model in 25.818s
nousresearch-meta-llama-4939-v10-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 85.640s
nousresearch-meta-llama-4939-v10-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10
nousresearch-meta-llama-4939-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10/config.json
nousresearch-meta-llama-4939-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10/special_tokens_map.json
nousresearch-meta-llama-4939-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10/tokenizer_config.json
nousresearch-meta-llama-4939-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10/tokenizer.json
nousresearch-meta-llama-4939-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v10/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v10-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.28it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 50.39it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 54.39it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 53.05it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 54.35it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 58.78it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 54.71it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:04, 55.77it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 49.28it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 54.54it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 51.51it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 37.78it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:05, 38.85it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 42.65it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:03, 47.55it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:03, 49.44it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.50it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.55it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 48.87it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:03, 49.09it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 46.84it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 50.77it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 52.62it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 45.53it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 53.57it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 47.03it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:02, 37.51it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:02, 38.94it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 40.75it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 41.49it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.58it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.37it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 46.01it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 50.22it/s]
Loading 0:  81%|████████  | 235/291 [00:04<00:01, 47.35it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 45.31it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 48.75it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 46.82it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 47.61it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 44.96it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 44.47it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 49.78it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 47.84it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 45.84it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  3.35it/s]
                                                            

Job nousresearch-meta-llama-4939-v10-mkmlizer completed after 108.97s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v10-mkmlizer
Pipeline stage MKMLizer completed in 110.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.25s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4939-v10
Waiting for inference service nousresearch-meta-llama-4939-v10 to be ready
Inference service nousresearch-meta-llama-4939-v10 ready after 172.4092710018158s
Pipeline stage ISVCDeployer completed in 173.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 8.596512079238892s
Received healthy response to inference request in 1.5250658988952637s
Received healthy response to inference request in 2.075890064239502s
Received healthy response to inference request in 1.8671066761016846s
Received healthy response to inference request in 1.9189958572387695s
5 requests
0 failed requests
5th percentile: 1.5934740543365478
10th percentile: 1.661882209777832
20th percentile: 1.7986985206604005
30th percentile: 1.8774845123291015
40th percentile: 1.8982401847839356
50th percentile: 1.9189958572387695
60th percentile: 1.9817535400390625
70th percentile: 2.0445112228393554
80th percentile: 3.380014467239381
90th percentile: 5.988263273239136
95th percentile: 7.292387676239013
99th percentile: 8.335687198638915
mean time: 3.1967141151428224
Pipeline stage StressChecker completed in 18.63s
nousresearch-meta-llama_4939_v10 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v10 status is now inactive due to admin request
admin requested tearing down of nousresearch-meta-llama_4939_v10
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4939-v10 is running
Tearing down inference service nousresearch-meta-llama-4939-v10
Service nousresearch-meta-llama-4939-v10 has been torndown
Pipeline stage ISVCDeleter completed in 3.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4939-v10/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLizer
Deleting key nousresearch-meta-llama-4939-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Starting job with name nousresearch-meta-llama-4939-v11-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v11-mkmlizer to finish
Deleting key nousresearch-meta-llama-4939-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v10/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 15.72s
nousresearch-meta-llama_4939_v10 status is now torndown due to DeploymentManager action