nousresearch-meta-llama_4939

submission_id: nousresearch-meta-llama_4939_v57

developer_uid: end_to_end_test

best_of: 4

display_name: nousresearch-meta-llama_4939_v57

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_v57

model_num_parameters: 8030261248.0

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

model_size: 8B

num_battles: 148

num_wins: 58

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-09-01T05:05:20+00:00

us_pacific_date: 2024-08-31

win_ratio: 0.3918918918918919

Download Preference Data

Resubmit model

run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v57-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v57-mkmlizer to finish
nousresearch-meta-llama-4939-v57-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v57-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v57-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v57-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v57-mkmlizer: Downloaded to shared memory in 35.613s
nousresearch-meta-llama-4939-v57-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnqwdw_yc, device:0
nousresearch-meta-llama-4939-v57-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v57-mkmlizer: quantized model in 25.828s
nousresearch-meta-llama-4939-v57-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 61.440s
nousresearch-meta-llama-4939-v57-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v57-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v57-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57
nousresearch-meta-llama-4939-v57-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57/config.json
nousresearch-meta-llama-4939-v57-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57/special_tokens_map.json
nousresearch-meta-llama-4939-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57/tokenizer_config.json
nousresearch-meta-llama-4939-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57/tokenizer.json
nousresearch-meta-llama-4939-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v57/flywheel_model.0.safetensors
nousresearch-meta-llama-4939-v57-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.60it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 47.94it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.85it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 51.49it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 51.72it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 53.46it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:03, 59.50it/s]
Loading 0:  22%|██▏       | 65/291 [00:01<00:03, 57.40it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:03, 55.85it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:04, 49.58it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 38.74it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 39.43it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:04, 40.04it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:04, 43.95it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 51.41it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 49.93it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 49.48it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 46.23it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 53.13it/s]
Loading 0:  50%|████▉     | 145/291 [00:02<00:02, 49.18it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:02, 50.67it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 52.67it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 49.23it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 50.78it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 52.64it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 51.88it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:02, 34.42it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 36.68it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 44.82it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 44.89it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 47.06it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 49.88it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 47.12it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 46.69it/s]
Loading 0:  81%|████████▏ | 237/291 [00:04<00:01, 49.43it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:00, 51.17it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.69it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 49.67it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 48.26it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 46.42it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 51.15it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 46.18it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 46.26it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.25it/s]
                                                            
Job nousresearch-meta-llama-4939-v57-mkmlizer completed after 88.63s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v57-mkmlizer
Pipeline stage MKMLizer completed in 89.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v57
Waiting for inference service nousresearch-meta-llama-4939-v57 to be ready
Inference service nousresearch-meta-llama-4939-v57 ready after 182.50630974769592s
Pipeline stage MKMLDeployer completed in 183.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0518798828125s
Received healthy response to inference request in 2.124678134918213s
Received healthy response to inference request in 1.7271323204040527s
Received healthy response to inference request in 1.522547960281372s
Received healthy response to inference request in 1.9009768962860107s
5 requests
0 failed requests
5th percentile: 1.5634648323059082
10th percentile: 1.6043817043304442
20th percentile: 1.6862154483795166
30th percentile: 1.7619012355804444
40th percentile: 1.8314390659332276
50th percentile: 1.9009768962860107
60th percentile: 1.9613380908966065
70th percentile: 2.0216992855072022
80th percentile: 2.0664395332336425
90th percentile: 2.095558834075928
95th percentile: 2.1101184844970704
99th percentile: 2.1217662048339845
mean time: 1.8654430389404297
Pipeline stage StressChecker completed in 11.63s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 237.22s
nousresearch-meta-llama_4939_v57 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v57 status is now inactive due to admin request
Starting job with name nousresearch-meta-llama-4939-v58-mkmlizer
nousresearch-meta-llama_4939_v57 status is now torndown due to DeploymentManager action