nousresearch-meta-llama_4939

submission_id: nousresearch-meta-llama_4939_v35

developer_uid: end_to_end_test

best_of: 4

display_name: nousresearch-meta-llama_4939_v35

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_v35

model_num_parameters: 8030261248.0

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

model_size: 8B

num_battles: 16

num_wins: 5

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-08-30T18:05:02+00:00

us_pacific_date: 2024-08-30

win_ratio: 0.3125

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v35-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v35-mkmlizer to finish
nousresearch-meta-llama-4939-v35-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v35-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v35-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v35-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v35-mkmlizer: Downloaded to shared memory in 33.697s
nousresearch-meta-llama-4939-v35-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxjvz7mwl, device:0
nousresearch-meta-llama-4939-v35-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v35-mkmlizer: quantized model in 26.079s
nousresearch-meta-llama-4939-v35-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 59.777s
nousresearch-meta-llama-4939-v35-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v35-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v35-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35
nousresearch-meta-llama-4939-v35-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35/special_tokens_map.json
nousresearch-meta-llama-4939-v35-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35/config.json
nousresearch-meta-llama-4939-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35/tokenizer_config.json
nousresearch-meta-llama-4939-v35-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35/tokenizer.json
nousresearch-meta-llama-4939-v35-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v35/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v35-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, 42.97it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:05, 52.93it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:05, 46.42it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 45.71it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 46.67it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 49.32it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 50.83it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 57.16it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 50.87it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 50.06it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 36.32it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:05, 36.42it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:05, 37.55it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 43.71it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 44.74it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:04, 40.22it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 48.89it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 44.45it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 41.95it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 47.44it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 47.67it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:02, 47.02it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 52.64it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 50.30it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 48.97it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 54.27it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 45.31it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:02, 35.14it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 36.15it/s]
Loading 0:  68%|██████▊   | 197/291 [00:04<00:02, 38.61it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 38.81it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.60it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.25it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 45.45it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 51.47it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 50.88it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 51.67it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 51.06it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 48.82it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 51.20it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 53.31it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 50.27it/s]
Loading 0:  95%|█████████▌| 277/291 [00:06<00:00, 45.92it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 41.39it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.20it/s]
                                                            
Job nousresearch-meta-llama-4939-v35-mkmlizer completed after 87.3s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v35-mkmlizer
Pipeline stage MKMLizer completed in 88.28s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v35
Waiting for inference service nousresearch-meta-llama-4939-v35 to be ready
Inference service nousresearch-meta-llama-4939-v35 ready after 181.68693709373474s
Pipeline stage MKMLDeployer completed in 182.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9795780181884766s
Received healthy response to inference request in 1.3179471492767334s
Received healthy response to inference request in 1.2954111099243164s
Received healthy response to inference request in 1.0550451278686523s
Received healthy response to inference request in 1.2604811191558838s
5 requests
0 failed requests
5th percentile: 1.0961323261260987
10th percentile: 1.137219524383545
20th percentile: 1.2193939208984375
30th percentile: 1.2674671173095704
40th percentile: 1.2814391136169434
50th percentile: 1.2954111099243164
60th percentile: 1.3044255256652832
70th percentile: 1.31343994140625
80th percentile: 1.450273323059082
90th percentile: 1.7149256706237794
95th percentile: 1.8472518444061279
99th percentile: 1.9531127834320068
mean time: 1.3816925048828126
Pipeline stage StressChecker completed in 8.93s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
triggered trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.89s
nousresearch-meta-llama_4939_v35 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v35 status is now inactive due to admin request
nousresearch-meta-llama_4939_v35 status is now torndown due to DeploymentManager action