developer_uid: rirv938
submission_id: rirv938-llama-8b-multih_77470_v5
model_name: rirv938-llama-8b-multih_77470_v5
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2025-01-27T17:44:35+00:00
num_battles: 8750
num_wins: 4801
celo_rating: 1299.78
family_friendly_score: 0.5546
family_friendly_standard_error: 0.007028781402206217
submission_type: basic
model_repo: rirv938/llama_8b_multihead_22m_256_tokens_step_15036_safety_oversampled
model_architecture: MultiHeadLlamaClassifier
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: rirv938-llama-8b-multih_77470_v5
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_22m_256_tokens_step_15036_safety_oversampled
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-27
win_ratio: 0.5486857142857143
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': 256, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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 rirv938-llama-8b-multih-77470-v5-mkmlizer
Waiting for job on rirv938-llama-8b-multih-77470-v5-mkmlizer to finish
rirv938-llama-8b-multih-77470-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ /___/ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ Version: 0.11.37 ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ║ ║
rirv938-llama-8b-multih-77470-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-multih-77470-v5-mkmlizer: Downloaded to shared memory in 21.936s
rirv938-llama-8b-multih-77470-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1dcd9eca, device:0
rirv938-llama-8b-multih-77470-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-multih-77470-v5-mkmlizer: quantized model in 15.731s
rirv938-llama-8b-multih-77470-v5-mkmlizer: Processed model rirv938/llama_8b_multihead_22m_256_tokens_step_15036_safety_oversampled in 37.667s
rirv938-llama-8b-multih-77470-v5-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multih-77470-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multih-77470-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5
rirv938-llama-8b-multih-77470-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5/config.json
rirv938-llama-8b-multih-77470-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5/special_tokens_map.json
rirv938-llama-8b-multih-77470-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5/tokenizer_config.json
rirv938-llama-8b-multih-77470-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5/tokenizer.json
rirv938-llama-8b-multih-77470-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multih-77470-v5/flywheel_model.0.safetensors
rirv938-llama-8b-multih-77470-v5-mkmlizer: Loading 0: 0%| | 0/297 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/297 [00:00<00:08, 33.87it/s] Loading 0: 4%|▍ | 13/297 [00:00<00:05, 53.18it/s] Loading 0: 6%|▋ | 19/297 [00:00<00:05, 49.66it/s] Loading 0: 8%|▊ | 25/297 [00:00<00:05, 50.65it/s] Loading 0: 11%|█ | 32/297 [00:00<00:05, 46.66it/s] Loading 0: 13%|█▎ | 40/297 [00:00<00:04, 54.29it/s] Loading 0: 15%|█▌ | 46/297 [00:00<00:04, 51.15it/s] Loading 0: 18%|█▊ | 52/297 [00:01<00:04, 52.53it/s] Loading 0: 20%|█▉ | 59/297 [00:01<00:04, 48.71it/s] Loading 0: 23%|██▎ | 67/297 [00:01<00:04, 55.24it/s] Loading 0: 25%|██▍ | 73/297 [00:01<00:04, 52.14it/s] Loading 0: 27%|██▋ | 79/297 [00:01<00:04, 53.04it/s] Loading 0: 29%|██▊ | 85/297 [00:01<00:05, 37.13it/s] Loading 0: 30%|███ | 90/297 [00:01<00:05, 39.40it/s] Loading 0: 32%|███▏ | 95/297 [00:02<00:05, 36.20it/s] Loading 0: 35%|███▍ | 103/297 [00:02<00:04, 44.68it/s] Loading 0: 37%|███▋ | 109/297 [00:02<00:04, 44.87it/s] Loading 0: 38%|███▊ | 114/297 [00:02<00:04, 45.49it/s] Loading 0: 41%|████ | 121/297 [00:02<00:03, 50.33it/s] Loading 0: 43%|████▎ | 127/297 [00:02<00:03, 48.55it/s] Loading 0: 45%|████▍ | 133/297 [00:02<00:03, 50.58it/s] Loading 0: 47%|████▋ | 139/297 [00:02<00:03, 52.40it/s] Loading 0: 49%|████▉ | 145/297 [00:03<00:03, 49.97it/s] Loading 0: 51%|█████ | 151/297 [00:03<00:02, 50.78it/s] Loading 0: 53%|█████▎ | 157/297 [00:03<00:02, 52.74it/s] Loading 0: 55%|█████▍ | 163/297 [00:03<00:02, 50.76it/s] Loading 0: 57%|█████▋ | 169/297 [00:03<00:02, 52.59it/s] Loading 0: 60%|█████▉ | 177/297 [00:03<00:02, 54.39it/s] Loading 0: 62%|██████▏ | 183/297 [00:03<00:02, 53.85it/s] Loading 0: 64%|██████▎ | 189/297 [00:04<00:03, 31.31it/s] Loading 0: 65%|██████▌ | 194/297 [00:04<00:03, 33.71it/s] Loading 0: 68%|██████▊ | 202/297 [00:04<00:02, 41.81it/s] Loading 0: 70%|███████ | 208/297 [00:04<00:02, 41.37it/s] Loading 0: 72%|███████▏ | 213/297 [00:04<00:02, 40.23it/s] Loading 0: 74%|███████▍ | 220/297 [00:04<00:01, 45.05it/s] Loading 0: 76%|███████▌ | 226/297 [00:04<00:01, 44.36it/s] Loading 0: 78%|███████▊ | 231/297 [00:04<00:01, 45.59it/s] Loading 0: 80%|████████ | 238/297 [00:05<00:01, 51.48it/s] Loading 0: 82%|████████▏ | 244/297 [00:05<00:01, 49.26it/s] Loading 0: 84%|████████▍ | 250/297 [00:05<00:00, 50.10it/s] Loading 0: 87%|████████▋ | 257/297 [00:05<00:00, 46.46it/s] Loading 0: 89%|████████▉ | 265/297 [00:05<00:00, 53.39it/s] Loading 0: 91%|█████████ | 271/297 [00:05<00:00, 49.27it/s] Loading 0: 93%|█████████▎| 277/297 [00:05<00:00, 50.78it/s] Loading 0: 95%|█████████▌| 283/297 [00:06<00:00, 46.28it/s] Loading 0: 97%|█████████▋| 288/297 [00:06<00:00, 31.86it/s]
Job rirv938-llama-8b-multih-77470-v5-mkmlizer completed after 65.76s with status: succeeded
Stopping job with name rirv938-llama-8b-multih-77470-v5-mkmlizer
Pipeline stage MKMLizer completed in 66.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.31s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-multih-77470-v5
Waiting for inference service rirv938-llama-8b-multih-77470-v5 to be ready
Inference service rirv938-llama-8b-multih-77470-v5 ready after 232.0172929763794s
Pipeline stage MKMLDeployer completed in 233.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.8833863735198975s
Received healthy response to inference request in 4.06858229637146s
Received healthy response to inference request in 4.319745063781738s
Received healthy response to inference request in 3.251652717590332s
Received healthy response to inference request in 4.0743186473846436s
5 requests
0 failed requests
5th percentile: 3.377999448776245
10th percentile: 3.504346179962158
20th percentile: 3.7570396423339845
30th percentile: 3.92042555809021
40th percentile: 3.994503927230835
50th percentile: 4.06858229637146
60th percentile: 4.070876836776733
70th percentile: 4.073171377182007
80th percentile: 4.123403930664063
90th percentile: 4.221574497222901
95th percentile: 4.270659780502319
99th percentile: 4.309928007125855
mean time: 3.9195370197296144
Pipeline stage StressChecker completed in 21.96s
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 1.42s
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 1.23s
Shutdown handler de-registered
rirv938-llama-8b-multih_77470_v5 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multih-77470-v5-profiler
Waiting for inference service rirv938-llama-8b-multih-77470-v5-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6029.26s
Shutdown handler de-registered
rirv938-llama-8b-multih_77470_v5 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-multih_77470_v5 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1