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

developer_uid: valentin87
submission_id: meta-llama-llama-guard-3-8b_v5
model_name: meta-llama-llama-guard-3-8b_v4
model_group: meta-llama/Llama-Guard-3
status: inactive
timestamp: 2024-10-25T13:19:59+00:00
num_battles: 3320671
num_wins: 1136470
celo_rating: 1130.1
family_friendly_score: 0.5860000000000001
family_friendly_standard_error: 0.006965687331484238
submission_type: basic
model_repo: meta-llama/Llama-Guard-3-8B
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 2048
max_output_tokens: 64
display_name: meta-llama-llama-guard-3-8b_v4
is_internal_developer: True
language_model: meta-llama/Llama-Guard-3-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-10-25
win_ratio: 0.3422410711570041
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 64}
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}
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-llama-guard-3-8b-v5-mkmlizer
Waiting for job on meta-llama-llama-guard-3-8b-v5-mkmlizer to finish
meta-llama-llama-guard-3-8b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║     _____            __           __                                ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║       /___/                                                         ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║                                                                     ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║                                                                     ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  belonging to:                                                      ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║                                                                     ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ║                                                                     ║
meta-llama-llama-guard-3-8b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
meta-llama-llama-guard-3-8b-v5-mkmlizer: Downloaded to shared memory in 46.718s
meta-llama-llama-guard-3-8b-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp80acc_3g, device:0
meta-llama-llama-guard-3-8b-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-llama-guard-3-8b-v5-mkmlizer: quantized model in 25.849s
meta-llama-llama-guard-3-8b-v5-mkmlizer: Processed model meta-llama/Llama-Guard-3-8B in 72.567s
meta-llama-llama-guard-3-8b-v5-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
meta-llama-llama-guard-3-8b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-llama-guard-3-8b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5
meta-llama-llama-guard-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5/config.json
meta-llama-llama-guard-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5/special_tokens_map.json
meta-llama-llama-guard-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5/tokenizer_config.json
meta-llama-llama-guard-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5/tokenizer.json
meta-llama-llama-guard-3-8b-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-llama-guard-3-8b-v5/flywheel_model.0.safetensors
meta-llama-llama-guard-3-8b-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 35.10it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 57.42it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:05, 53.15it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:05, 52.96it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 43.79it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 52.58it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:05, 48.32it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:04, 50.28it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 52.06it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 47.89it/s]
Loading 0:  24%|██▎       | 69/291 [00:01<00:04, 47.56it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 52.42it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 49.32it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 34.94it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 39.24it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.56it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 41.39it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.39it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 45.13it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.51it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.09it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.54it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 44.63it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:02, 48.17it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:02, 48.00it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 47.84it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 44.98it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 44.80it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 51.26it/s]
Loading 0:  62%|██████▏   | 181/291 [00:03<00:02, 44.17it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:02, 36.40it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 37.62it/s]
Loading 0:  68%|██████▊   | 197/291 [00:04<00:02, 40.23it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.96it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 41.95it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 43.14it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 48.29it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 44.50it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 44.05it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.40it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 46.40it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.48it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.04it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 45.53it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 44.85it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 48.31it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 48.51it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 42.01it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.13it/s]
                                                            
Job meta-llama-llama-guard-3-8b-v5-mkmlizer completed after 94.7s with status: succeeded
Stopping job with name meta-llama-llama-guard-3-8b-v5-mkmlizer
Pipeline stage MKMLizer completed in 95.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-llama-guard-3-8b-v5
Waiting for inference service meta-llama-llama-guard-3-8b-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service meta-llama-llama-guard-3-8b-v5 ready after 130.48954463005066s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.861304521560669s
Received healthy response to inference request in 0.34589314460754395s
Received healthy response to inference request in 1.0687551498413086s
Received healthy response to inference request in 0.4467124938964844s
Received healthy response to inference request in 0.7337870597839355s
5 requests
0 failed requests
5th percentile: 0.366057014465332
10th percentile: 0.38622088432312013
20th percentile: 0.4265486240386963
30th percentile: 0.5041274070739746
40th percentile: 0.6189572334289551
50th percentile: 0.7337870597839355
60th percentile: 0.7847940444946289
70th percentile: 0.8358010292053223
80th percentile: 0.9027946472167969
90th percentile: 0.9857748985290528
95th percentile: 1.0272650241851806
99th percentile: 1.060457124710083
mean time: 0.6912904739379883
Pipeline stage StressChecker completed in 5.16s
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 5.99s
Shutdown handler de-registered
meta-llama-llama-guard-3-8b_v5 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2014.68s
Shutdown handler de-registered