developer_uid: fengjiayi
submission_id: felfri-llama-guard-2-8b-_1569_v1
model_name: felfri-llama-guard-2-8b-_1569_v1
model_group: felfri/Llama-Guard-2-8B-
status: torndown
timestamp: 2025-01-23T05:26:53+00:00
num_battles: 5697
num_wins: 2403
celo_rating: 1167.02
family_friendly_score: 0.6024
family_friendly_standard_error: 0.006921188337272726
submission_type: basic
model_repo: felfri/Llama-Guard-2-8B-German-v0.2
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: felfri-llama-guard-2-8b-_1569_v1
is_internal_developer: False
language_model: felfri/Llama-Guard-2-8B-German-v0.2
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-22
win_ratio: 0.4218009478672986
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': 1024, 'best_of': 8, '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 felfri-llama-guard-2-8b-1569-v1-mkmlizer
Waiting for job on felfri-llama-guard-2-8b-1569-v1-mkmlizer to finish
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ _____ __ __ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ /___/ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ Version: 0.11.12 ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ https://mk1.ai ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ The license key for the current software has been verified as ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ belonging to: ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ Chai Research Corp. ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ║ ║
felfri-llama-guard-2-8b-1569-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
felfri-llama-guard-2-8b-1569-v1-mkmlizer: Downloaded to shared memory in 35.584s
felfri-llama-guard-2-8b-1569-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgk6iaooo, device:0
felfri-llama-guard-2-8b-1569-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
felfri-llama-guard-2-8b-1569-v1-mkmlizer: quantized model in 26.867s
felfri-llama-guard-2-8b-1569-v1-mkmlizer: Processed model felfri/Llama-Guard-2-8B-German-v0.2 in 62.451s
felfri-llama-guard-2-8b-1569-v1-mkmlizer: creating bucket guanaco-mkml-models
felfri-llama-guard-2-8b-1569-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
felfri-llama-guard-2-8b-1569-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1
felfri-llama-guard-2-8b-1569-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1/config.json
felfri-llama-guard-2-8b-1569-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1/special_tokens_map.json
felfri-llama-guard-2-8b-1569-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1/tokenizer_config.json
felfri-llama-guard-2-8b-1569-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1/tokenizer.json
felfri-llama-guard-2-8b-1569-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/felfri-llama-guard-2-8b-1569-v1/flywheel_model.0.safetensors
felfri-llama-guard-2-8b-1569-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 35.53it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:05, 52.26it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:05, 51.26it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 40.18it/s] Loading 0: 10%|█ | 30/291 [00:00<00:05, 45.51it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 45.13it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 45.33it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:05, 46.24it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 37.49it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:05, 45.96it/s] Loading 0: 22%|██▏ | 63/291 [00:01<00:04, 45.77it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:06, 36.91it/s] Loading 0: 26%|██▌ | 75/291 [00:01<00:04, 43.55it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:04, 43.10it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:07, 29.13it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 32.92it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:06, 30.55it/s] Loading 0: 35%|███▌ | 102/291 [00:02<00:04, 38.36it/s] Loading 0: 37%|███▋ | 107/291 [00:02<00:04, 40.11it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 42.14it/s] Loading 0: 41%|████ | 118/291 [00:02<00:04, 41.45it/s] Loading 0: 42%|████▏ | 123/291 [00:03<00:04, 41.73it/s] Loading 0: 44%|████▍ | 129/291 [00:03<00:03, 45.81it/s] Loading 0: 46%|████▌ | 134/291 [00:03<00:03, 45.28it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 45.04it/s] Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 42.40it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 41.67it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 46.03it/s] Loading 0: 55%|█████▌ | 161/291 [00:03<00:02, 43.54it/s] Loading 0: 57%|█████▋ | 166/291 [00:04<00:02, 42.49it/s] Loading 0: 59%|█████▉ | 171/291 [00:04<00:02, 44.19it/s] Loading 0: 60%|██████ | 176/291 [00:04<00:02, 44.97it/s] Loading 0: 62%|██████▏ | 181/291 [00:04<00:02, 37.29it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 27.99it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:03, 30.88it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 32.47it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:02, 37.33it/s] Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 37.83it/s] Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 39.18it/s] Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 43.59it/s] Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 44.85it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 45.15it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 42.89it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 42.38it/s] Loading 0: 85%|████████▍ | 246/291 [00:06<00:00, 46.18it/s] Loading 0: 86%|████████▋ | 251/291 [00:06<00:00, 46.64it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 46.91it/s] Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 43.87it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 42.80it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 46.49it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 46.25it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 39.57it/s] Loading 0: 99%|█████████▉| 288/291 [00:12<00:01, 2.97it/s]
Job felfri-llama-guard-2-8b-1569-v1-mkmlizer completed after 83.55s with status: succeeded
Stopping job with name felfri-llama-guard-2-8b-1569-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service felfri-llama-guard-2-8b-1569-v1
Waiting for inference service felfri-llama-guard-2-8b-1569-v1 to be ready
Inference service felfri-llama-guard-2-8b-1569-v1 ready after 140.51652598381042s
Pipeline stage MKMLDeployer completed in 141.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8041203022003174s
Received healthy response to inference request in 1.5188415050506592s
Received healthy response to inference request in 1.281477928161621s
Received healthy response to inference request in 1.2072868347167969s
Received healthy response to inference request in 1.469858169555664s
5 requests
0 failed requests
5th percentile: 1.2221250534057617
10th percentile: 1.2369632720947266
20th percentile: 1.2666397094726562
30th percentile: 1.3191539764404296
40th percentile: 1.394506072998047
50th percentile: 1.469858169555664
60th percentile: 1.4894515037536622
70th percentile: 1.5090448379516601
80th percentile: 1.5758972644805909
90th percentile: 1.690008783340454
95th percentile: 1.7470645427703857
99th percentile: 1.792709150314331
mean time: 1.4563169479370117
Pipeline stage StressChecker completed in 8.65s
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 0.68s
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 0.64s
Shutdown handler de-registered
felfri-llama-guard-2-8b-_1569_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service felfri-llama-guard-2-8b-1569-v1-profiler
Waiting for inference service felfri-llama-guard-2-8b-1569-v1-profiler to be ready
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 2113.15s
Shutdown handler de-registered
felfri-llama-guard-2-8b-_1569_v1 status is now inactive due to auto deactivation removed underperforming models
felfri-llama-guard-2-8b-_1569_v1 status is now torndown due to DeploymentManager action