thedrummer-llama-3some-8b-v2

developer_uid: fengjiayi
submission_id: thedrummer-llama-3some-8b-v2_v4
model_name: thedrummer-llama-3some-8b-v2_v4
model_group: TheDrummer/Llama-3SOME-8
status: torndown
timestamp: 2025-01-23T07:43:40+00:00
num_battles: 5626
num_wins: 2608
celo_rating: 1240.14
family_friendly_score: 0.5868
family_friendly_standard_error: 0.006963702463488802
submission_type: basic
model_repo: TheDrummer/Llama-3SOME-8B-v2
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: thedrummer-llama-3some-8b-v2_v4
is_internal_developer: False
language_model: TheDrummer/Llama-3SOME-8B-v2
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-22
win_ratio: 0.46356203341628155
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 thedrummer-llama-3some-8b-v2-v4-mkmlizer
Waiting for job on thedrummer-llama-3some-8b-v2-v4-mkmlizer to finish
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║     _____            __           __                                ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║       /___/                                                         ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║                                                                     ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  https://mk1.ai                                                     ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║                                                                     ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  belonging to:                                                      ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║                                                                     ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  Chai Research Corp.                                                ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ║                                                                     ║
thedrummer-llama-3some-8b-v2-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thedrummer-llama-3some-8b-v2-v4-mkmlizer: Downloaded to shared memory in 21.398s
thedrummer-llama-3some-8b-v2-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp44oq8x12, device:0
thedrummer-llama-3some-8b-v2-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thedrummer-llama-3some-8b-v2-v4-mkmlizer: quantized model in 27.408s
thedrummer-llama-3some-8b-v2-v4-mkmlizer: Processed model TheDrummer/Llama-3SOME-8B-v2 in 48.806s
thedrummer-llama-3some-8b-v2-v4-mkmlizer: creating bucket guanaco-mkml-models
thedrummer-llama-3some-8b-v2-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thedrummer-llama-3some-8b-v2-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4
thedrummer-llama-3some-8b-v2-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4/special_tokens_map.json
thedrummer-llama-3some-8b-v2-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4/config.json
thedrummer-llama-3some-8b-v2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4/tokenizer_config.json
thedrummer-llama-3some-8b-v2-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4/tokenizer.json
thedrummer-llama-3some-8b-v2-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thedrummer-llama-3some-8b-v2-v4/flywheel_model.0.safetensors
thedrummer-llama-3some-8b-v2-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:51,  2.46s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:09,  1.50it/s]
Loading 0:   4%|▍         | 11/291 [00:05<01:23,  3.35it/s]
Loading 0:   5%|▌         | 15/291 [00:05<00:52,  5.21it/s]
Loading 0:   8%|▊         | 23/291 [00:05<00:26, 10.29it/s]
Loading 0:  10%|▉         | 29/291 [00:05<00:18, 14.02it/s]
Loading 0:  12%|█▏        | 34/291 [00:05<00:14, 17.71it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:10, 24.38it/s]
Loading 0:  16%|█▌        | 47/291 [00:05<00:08, 27.15it/s]
Loading 0:  18%|█▊        | 52/291 [00:06<00:07, 30.16it/s]
Loading 0:  20%|██        | 59/291 [00:06<00:06, 37.25it/s]
Loading 0:  22%|██▏       | 65/291 [00:06<00:08, 25.56it/s]
Loading 0:  24%|██▍       | 70/291 [00:06<00:07, 28.34it/s]
Loading 0:  26%|██▌       | 76/291 [00:06<00:06, 32.92it/s]
Loading 0:  28%|██▊       | 81/291 [00:06<00:06, 34.29it/s]
Loading 0:  30%|██▉       | 86/291 [00:07<00:05, 36.38it/s]
Loading 0:  31%|███▏      | 91/291 [00:07<00:05, 39.00it/s]
Loading 0:  33%|███▎      | 96/291 [00:07<00:05, 33.24it/s]
Loading 0:  35%|███▌      | 103/291 [00:07<00:04, 40.48it/s]
Loading 0:  37%|███▋      | 108/291 [00:07<00:04, 40.83it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:04, 40.02it/s]
Loading 0:  41%|████      | 118/291 [00:07<00:04, 40.98it/s]
Loading 0:  42%|████▏     | 123/291 [00:08<00:04, 34.45it/s]
Loading 0:  45%|████▍     | 130/291 [00:08<00:03, 40.98it/s]
Loading 0:  46%|████▋     | 135/291 [00:08<00:03, 40.65it/s]
Loading 0:  48%|████▊     | 140/291 [00:08<00:03, 40.97it/s]
Loading 0:  50%|████▉     | 145/291 [00:08<00:03, 42.27it/s]
Loading 0:  52%|█████▏    | 150/291 [00:08<00:04, 34.22it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:03, 41.41it/s]
Loading 0:  56%|█████▌    | 162/291 [00:08<00:03, 41.50it/s]
Loading 0:  57%|█████▋    | 167/291 [00:09<00:04, 27.66it/s]
Loading 0:  59%|█████▉    | 171/291 [00:09<00:04, 29.47it/s]
Loading 0:  60%|██████    | 175/291 [00:09<00:03, 31.32it/s]
Loading 0:  62%|██████▏   | 179/291 [00:09<00:03, 32.23it/s]
Loading 0:  63%|██████▎   | 184/291 [00:09<00:02, 35.77it/s]
Loading 0:  65%|██████▍   | 188/291 [00:09<00:02, 35.52it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:02, 38.68it/s]
Loading 0:  68%|██████▊   | 198/291 [00:10<00:02, 38.52it/s]
Loading 0:  70%|██████▉   | 203/291 [00:10<00:02, 38.93it/s]
Loading 0:  71%|███████   | 207/291 [00:10<00:02, 38.63it/s]
Loading 0:  73%|███████▎  | 211/291 [00:10<00:02, 38.74it/s]
Loading 0:  74%|███████▍  | 215/291 [00:10<00:02, 37.90it/s]
Loading 0:  76%|███████▌  | 221/291 [00:10<00:01, 42.13it/s]
Loading 0:  78%|███████▊  | 226/291 [00:10<00:01, 43.87it/s]
Loading 0:  79%|███████▉  | 231/291 [00:10<00:01, 38.09it/s]
Loading 0:  82%|████████▏ | 239/291 [00:11<00:01, 47.42it/s]
Loading 0:  84%|████████▍ | 245/291 [00:11<00:01, 43.90it/s]
Loading 0:  86%|████████▌ | 250/291 [00:11<00:00, 43.66it/s]
Loading 0:  88%|████████▊ | 257/291 [00:11<00:00, 49.22it/s]
Loading 0:  90%|█████████ | 263/291 [00:11<00:00, 43.36it/s]
Loading 0:  92%|█████████▏| 268/291 [00:11<00:00, 27.65it/s]
Loading 0:  95%|█████████▍| 275/291 [00:12<00:00, 34.01it/s]
Loading 0:  96%|█████████▌| 280/291 [00:12<00:00, 36.81it/s]
Loading 0:  98%|█████████▊| 285/291 [00:12<00:00, 33.11it/s]
                                                            
Job thedrummer-llama-3some-8b-v2-v4-mkmlizer completed after 83.81s with status: succeeded
Stopping job with name thedrummer-llama-3some-8b-v2-v4-mkmlizer
Pipeline stage MKMLizer completed in 84.28s
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 thedrummer-llama-3some-8b-v2-v4
Waiting for inference service thedrummer-llama-3some-8b-v2-v4 to be ready
Inference service thedrummer-llama-3some-8b-v2-v4 ready after 140.46428680419922s
Pipeline stage MKMLDeployer completed in 140.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.777400255203247s
Received healthy response to inference request in 1.4157814979553223s
Received healthy response to inference request in 1.3862049579620361s
Received healthy response to inference request in 1.7381410598754883s
Received healthy response to inference request in 1.1967194080352783s
5 requests
0 failed requests
5th percentile: 1.2346165180206299
10th percentile: 1.2725136280059814
20th percentile: 1.3483078479766846
30th percentile: 1.3921202659606933
40th percentile: 1.4039508819580078
50th percentile: 1.4157814979553223
60th percentile: 1.5447253227233886
70th percentile: 1.6736691474914551
80th percentile: 1.74599289894104
90th percentile: 1.7616965770721436
95th percentile: 1.7695484161376953
99th percentile: 1.7758298873901368
mean time: 1.5028494358062745
Pipeline stage StressChecker completed in 8.72s
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 0.62s
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
thedrummer-llama-3some-8b-v2_v4 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service thedrummer-llama-3some-8b-v2-v4-profiler
Waiting for inference service thedrummer-llama-3some-8b-v2-v4-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 2148.95s
Shutdown handler de-registered
thedrummer-llama-3some-8b-v2_v4 status is now inactive due to auto deactivation removed underperforming models
thedrummer-llama-3some-8b-v2_v4 status is now torndown due to DeploymentManager action