nousresearch-meta-llama_4939

submission_id: nousresearch-meta-llama_4939_v80

developer_uid: end_to_end_test

best_of: 4

display_name: nousresearch-meta-llama_4939_v80

family_friendly_score: 0.76

family_friendly_standard_error: 0.08717797887081347

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_v80

model_num_parameters: 8030261248.0

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

model_size: 8B

num_battles: 25

num_wins: 11

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-10-21T13:55:22+00:00

us_pacific_date: 2024-10-21

win_ratio: 0.44

Download Preference Data

Resubmit model

Pipeline stage MKMLModelDeleter completed in 13.19s
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler de-registered
nousresearch-meta-llama_4939_v79 status is now torndown due to DeploymentManager action
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v80-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v80-mkmlizer to finish
nousresearch-meta-llama-4939-v80-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v80-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  Version: 0.11.12                                                   ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v80-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v80-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v80-mkmlizer: Downloaded to shared memory in 35.499s
nousresearch-meta-llama-4939-v80-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6_f4g5tv, device:0
nousresearch-meta-llama-4939-v80-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v80-mkmlizer: quantized model in 26.090s
nousresearch-meta-llama-4939-v80-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 61.590s
nousresearch-meta-llama-4939-v80-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v80-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v80-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80
nousresearch-meta-llama-4939-v80-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80/config.json
nousresearch-meta-llama-4939-v80-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80/special_tokens_map.json
nousresearch-meta-llama-4939-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80/tokenizer_config.json
nousresearch-meta-llama-4939-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80/tokenizer.json
nousresearch-meta-llama-4939-v80-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v80/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v80-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.76it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 56.41it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:04, 56.38it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:04, 56.97it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 49.18it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 51.60it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:04, 55.69it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:04, 52.56it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 45.62it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 48.06it/s]
Loading 0:  25%|██▍       | 72/291 [00:01<00:04, 50.31it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.44it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 35.03it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:05, 34.76it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 41.73it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 42.31it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 43.54it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 49.93it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 47.72it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 44.96it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.13it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.95it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 45.99it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:02, 49.46it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:02, 49.67it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 42.01it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 45.62it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 45.42it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 45.96it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 45.92it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 34.58it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.77it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 34.56it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 42.24it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:01, 43.84it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:02, 38.37it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 47.64it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 46.09it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 45.71it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.94it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 47.76it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 46.39it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 51.74it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 48.31it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 47.76it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 53.42it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 51.46it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 44.92it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  3.41it/s]
                                                            
Job nousresearch-meta-llama-4939-v80-mkmlizer completed after 88.76s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v80-mkmlizer
Pipeline stage MKMLizer completed in 90.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v80
Waiting for inference service nousresearch-meta-llama-4939-v80 to be ready
Inference service nousresearch-meta-llama-4939-v80 ready after 151.8779900074005s
Pipeline stage MKMLDeployer completed in 153.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.55094575881958s
Received healthy response to inference request in 1.276526689529419s
Received healthy response to inference request in 1.4990930557250977s
Received healthy response to inference request in 1.5206468105316162s
Received healthy response to inference request in 1.4845383167266846s
5 requests
0 failed requests
5th percentile: 1.318129014968872
10th percentile: 1.359731340408325
20th percentile: 1.4429359912872315
30th percentile: 1.4874492645263673
40th percentile: 1.4932711601257325
50th percentile: 1.4990930557250977
60th percentile: 1.5077145576477051
70th percentile: 1.5163360595703126
80th percentile: 1.726706600189209
90th percentile: 2.138826179504395
95th percentile: 2.344885969161987
99th percentile: 2.5097338008880614
mean time: 1.6663501262664795
Pipeline stage StressChecker completed in 11.69s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 3.46s
Shutdown handler de-registered
nousresearch-meta-llama_4939_v80 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 jobs
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s jobs
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s jobs
clean up pipeline due to error=DeploymentChecksError("('http://nousresearch-meta-llama-4939-v80-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
nousresearch-meta-llama_4939_v80 status is now inactive due to admin request
nousresearch-meta-llama_4939_v80 status is now torndown due to DeploymentManager action