meta-llama-meta-llama-3-8b

developer_uid: azuruce

submission_id: meta-llama-meta-llama-3-8b_v18

model_name: meta-llama-meta-llama-3-8b_v18

model_group: meta-llama/Meta-Llama-3-

status: torndown

timestamp: 2025-01-19T05:59:40+00:00

num_battles: 9072

num_wins: 3347

celo_rating: 1177.64

family_friendly_score: 0.5900000000000001

family_friendly_standard_error: 0.0069555733049116815

submission_type: basic

model_repo: meta-llama/Meta-Llama-3-8B

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: meta-llama-meta-llama-3-8b_v18

ineligible_reason: num_battles<10000

is_internal_developer: False

language_model: meta-llama/Meta-Llama-3-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-18

win_ratio: 0.3689373897707231

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'You:', 'User:', 'Me', '<|eot_id|>', 'Bot:', '\n', '####', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name meta-llama-meta-llama-3-8b-v18-mkmlizer
Waiting for job on meta-llama-meta-llama-3-8b-v18-mkmlizer to finish
meta-llama-meta-llama-3-8b-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║     _____            __           __                                ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║       /___/                                                         ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  Version: 0.11.12                                                   ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  belonging to:                                                      ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-8b-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-8b-v18-mkmlizer: Downloaded to shared memory in 44.826s
meta-llama-meta-llama-3-8b-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd2zwqboo, device:0
meta-llama-meta-llama-3-8b-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-8b-v18-mkmlizer: quantized model in 25.706s
meta-llama-meta-llama-3-8b-v18-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B in 70.532s
meta-llama-meta-llama-3-8b-v18-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-8b-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-8b-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18
meta-llama-meta-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18/config.json
meta-llama-meta-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18/special_tokens_map.json
meta-llama-meta-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18/tokenizer_config.json
meta-llama-meta-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18/tokenizer.json
meta-llama-meta-llama-3-8b-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-8b-v18/flywheel_model.0.safetensors
meta-llama-meta-llama-3-8b-v18-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.13it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 48.06it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 52.97it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 55.19it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 56.04it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 56.32it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 56.21it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:03, 56.34it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 61.33it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:04, 42.99it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:04, 43.43it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:04, 41.43it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:03, 48.84it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 47.58it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 49.60it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 47.00it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.89it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 50.49it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 51.23it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:02, 47.91it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 53.56it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 49.85it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 50.62it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 54.89it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 47.51it/s]
Loading 0:  65%|██████▍   | 188/291 [00:03<00:02, 37.41it/s]
Loading 0:  66%|██████▋   | 193/291 [00:03<00:02, 38.24it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 40.41it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 39.88it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.07it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.90it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 46.21it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 47.62it/s]
Loading 0:  82%|████████▏ | 239/291 [00:04<00:01, 50.78it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 55.73it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 52.29it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 52.15it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 49.65it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 55.21it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 50.03it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 46.54it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  3.62it/s]
                                                            
Job meta-llama-meta-llama-3-8b-v18-mkmlizer completed after 95.21s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-8b-v18-mkmlizer
Pipeline stage MKMLizer completed in 95.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-meta-llama-3-8b-v18
Waiting for inference service meta-llama-meta-llama-3-8b-v18 to be ready
Inference service meta-llama-meta-llama-3-8b-v18 ready after 120.41927480697632s
Pipeline stage MKMLDeployer completed in 120.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3103055953979492s
Received healthy response to inference request in 0.9068276882171631s
Received healthy response to inference request in 0.7564020156860352s
Received healthy response to inference request in 0.8018903732299805s
Received healthy response to inference request in 1.275604009628296s
5 requests
0 failed requests
5th percentile: 0.7654996871948242
10th percentile: 0.7745973587036132
20th percentile: 0.7927927017211914
30th percentile: 0.822877836227417
40th percentile: 0.86485276222229
50th percentile: 0.9068276882171631
60th percentile: 1.0543382167816162
70th percentile: 1.2018487453460693
80th percentile: 1.2825443267822265
90th percentile: 1.296424961090088
95th percentile: 1.3033652782440186
99th percentile: 1.308917531967163
mean time: 1.0102059364318847
Pipeline stage StressChecker completed in 6.33s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.63s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.65s
Shutdown handler de-registered
meta-llama-meta-llama-3-8b_v18 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 threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2130.22s
Shutdown handler de-registered
meta-llama-meta-llama-3-8b_v18 status is now inactive due to auto deactivation removed underperforming models
meta-llama-meta-llama-3-8b_v18 status is now torndown due to DeploymentManager action