nousresearch-meta-llama_4939

submission_id: nousresearch-meta-llama_4939_v21

developer_uid: end_to_end_test

best_of: 4

display_name: nousresearch-meta-llama_4939_v21

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_v21

model_num_parameters: 8030261248.0

model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct

model_size: 8B

num_battles: 28

num_wins: 11

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-29T06:56:57+00:00

us_pacific_date: 2024-08-28

win_ratio: 0.39285714285714285

Download Preference Data

Resubmit model

Deleting key nousresearch-meta-llama-4939-v20/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLizer
Deleting key nousresearch-meta-llama-4939-v20/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Starting job with name nousresearch-meta-llama-4939-v21-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v21-mkmlizer to finish
Deleting key nousresearch-meta-llama-4939-v20/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v20/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v20/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 8.62s
nousresearch-meta-llama_4939_v20 status is now torndown due to DeploymentManager action
nousresearch-meta-llama-4939-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v21-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v21-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v21-mkmlizer: Downloaded to shared memory in 34.031s
nousresearch-meta-llama-4939-v21-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpngytj_x4, device:0
nousresearch-meta-llama-4939-v21-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v21-mkmlizer: quantized model in 25.503s
nousresearch-meta-llama-4939-v21-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 59.535s
nousresearch-meta-llama-4939-v21-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21
nousresearch-meta-llama-4939-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21/config.json
nousresearch-meta-llama-4939-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21/tokenizer_config.json
nousresearch-meta-llama-4939-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21/special_tokens_map.json
nousresearch-meta-llama-4939-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21/tokenizer.json
nousresearch-meta-llama-4939-v21-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v21/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v21-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.44it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 47.80it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.04it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 52.31it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 54.30it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 55.38it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 55.96it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 55.72it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 60.83it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:04, 42.59it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:04, 42.66it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 41.07it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 45.04it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 51.41it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 50.05it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.04it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.03it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 49.37it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 50.89it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:02, 47.36it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 54.23it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 51.96it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 51.01it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 55.69it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 46.87it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:02, 37.16it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:02, 37.65it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 40.15it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:01, 44.21it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 43.55it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 51.33it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 50.18it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 50.97it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:01, 52.86it/s]
Loading 0:  84%|████████▍ | 244/291 [00:04<00:00, 51.22it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 52.28it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 48.89it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 55.76it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 49.07it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 49.54it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 44.75it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.44it/s]
                                                            
Job nousresearch-meta-llama-4939-v21-mkmlizer completed after 87.66s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v21-mkmlizer
Pipeline stage MKMLizer completed in 88.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.24s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4939-v21
Waiting for inference service nousresearch-meta-llama-4939-v21 to be ready
Inference service nousresearch-meta-llama-4939-v21 ready after 457.940349817276s
Pipeline stage ISVCDeployer completed in 458.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 8.718723058700562s
Received healthy response to inference request in 1.5619630813598633s
Received healthy response to inference request in 2.5837008953094482s
Received healthy response to inference request in 1.5048141479492188s
Received healthy response to inference request in 2.822391986846924s
5 requests
0 failed requests
5th percentile: 1.5162439346313477
10th percentile: 1.5276737213134766
20th percentile: 1.5505332946777344
30th percentile: 1.7663106441497802
40th percentile: 2.1750057697296143
50th percentile: 2.5837008953094482
60th percentile: 2.6791773319244383
70th percentile: 2.774653768539429
80th percentile: 4.001658201217652
90th percentile: 6.3601906299591064
95th percentile: 7.539456844329833
99th percentile: 8.482869815826415
mean time: 3.438318634033203
Pipeline stage StressChecker completed in 19.67s
nousresearch-meta-llama_4939_v21 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v21 status is now inactive due to admin request
admin requested tearing down of nousresearch-meta-llama_4939_v21
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4939-v21 is running
Tearing down inference service nousresearch-meta-llama-4939-v21
Service nousresearch-meta-llama-4939-v21 has been torndown
Pipeline stage ISVCDeleter completed in 12.26s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4939-v21/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v21/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v22-mkmlizer
Deleting key nousresearch-meta-llama-4939-v21/special_tokens_map.json from bucket guanaco-mkml-models
Waiting for job on nousresearch-meta-llama-4939-v22-mkmlizer to finish
Deleting key nousresearch-meta-llama-4939-v21/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4939-v21/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 7.71s
nousresearch-meta-llama_4939_v21 status is now torndown due to DeploymentManager action