developer_uid: azuruce
submission_id: nbeerbower-gemma2-guten_20103_v1
model_name: repro-w-memory-prompt
model_group: nbeerbower/gemma2-gutenb
status: torndown
timestamp: 2025-02-03T19:30:31+00:00
num_battles: 8745
num_wins: 3825
celo_rating: 1228.66
family_friendly_score: 0.5882000000000001
family_friendly_standard_error: 0.006960183330918806
submission_type: basic
model_repo: nbeerbower/gemma2-gutenberg-27B
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: repro-w-memory-prompt
is_internal_developer: True
language_model: nbeerbower/gemma2-gutenberg-27B
model_size: 29B
ranking_group: single
us_pacific_date: 2025-02-03
win_ratio: 0.43739279588336194
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 nbeerbower-gemma2-guten-20103-v1-mkmlizer
Waiting for job on nbeerbower-gemma2-guten-20103-v1-mkmlizer to finish
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║     _____            __           __                                ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║       /___/                                                         ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║                                                                     ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  https://mk1.ai                                                     ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║                                                                     ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  belonging to:                                                      ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║                                                                     ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ║                                                                     ║
nbeerbower-gemma2-guten-20103-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nbeerbower-gemma2-guten-20103-v1-mkmlizer: Downloaded to shared memory in 85.785s
nbeerbower-gemma2-guten-20103-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpixe4ll99, device:0
nbeerbower-gemma2-guten-20103-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nbeerbower-gemma2-guten-20103-v1-mkmlizer: quantized model in 65.886s
nbeerbower-gemma2-guten-20103-v1-mkmlizer: Processed model nbeerbower/gemma2-gutenberg-27B in 151.670s
nbeerbower-gemma2-guten-20103-v1-mkmlizer: creating bucket guanaco-mkml-models
nbeerbower-gemma2-guten-20103-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nbeerbower-gemma2-guten-20103-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/config.json
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/special_tokens_map.json
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/tokenizer_config.json
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/tokenizer.model
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/flywheel_model.2.safetensors
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/flywheel_model.0.safetensors
nbeerbower-gemma2-guten-20103-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/nbeerbower-gemma2-guten-20103-v1/flywheel_model.1.safetensors
nbeerbower-gemma2-guten-20103-v1-mkmlizer: 
Loading 0:   0%|          | 0/508 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/508 [00:00<00:12, 39.78it/s]
Loading 0:   2%|▏         | 12/508 [00:00<00:10, 46.99it/s]
Loading 0:   3%|▎         | 17/508 [00:00<00:14, 34.85it/s]
Loading 0:   5%|▌         | 27/508 [00:00<00:09, 49.84it/s]
Loading 0:   6%|▋         | 33/508 [00:00<00:15, 30.69it/s]
Loading 0:   7%|▋         | 38/508 [00:01<00:14, 31.55it/s]
Loading 0:   9%|▉         | 47/508 [00:01<00:11, 39.84it/s]
Loading 0:  10%|█         | 52/508 [00:01<00:10, 41.65it/s]
Loading 0:  11%|█▏        | 58/508 [00:01<00:10, 42.39it/s]
Loading 0:  12%|█▏        | 63/508 [00:01<00:10, 44.13it/s]
Loading 0:  13%|█▎        | 68/508 [00:01<00:10, 42.20it/s]
Loading 0:  14%|█▍        | 73/508 [00:01<00:14, 30.05it/s]
Loading 0:  15%|█▌        | 78/508 [00:02<00:13, 32.01it/s]
Loading 0:  16%|█▌        | 82/508 [00:02<00:13, 31.91it/s]
Loading 0:  17%|█▋        | 88/508 [00:02<00:12, 34.38it/s]
Loading 0:  19%|█▉        | 97/508 [00:02<00:09, 42.46it/s]
Loading 0:  20%|██        | 102/508 [00:02<00:09, 43.86it/s]
Loading 0:  21%|██▏       | 108/508 [00:02<00:09, 43.43it/s]
Loading 0:  22%|██▏       | 113/508 [00:02<00:08, 44.62it/s]
Loading 0:  23%|██▎       | 118/508 [00:03<00:11, 33.13it/s]
Loading 0:  24%|██▍       | 124/508 [00:03<00:09, 38.56it/s]
Loading 0:  25%|██▌       | 129/508 [00:03<00:09, 40.95it/s]
Loading 0:  27%|██▋       | 135/508 [00:03<00:09, 41.09it/s]
Loading 0:  28%|██▊       | 142/508 [00:03<00:07, 47.55it/s]
Loading 0:  29%|██▉       | 148/508 [00:03<00:09, 38.67it/s]
Loading 0:  31%|███       | 157/508 [00:03<00:07, 45.53it/s]
Loading 0:  32%|███▏      | 164/508 [00:04<00:06, 50.63it/s]
Loading 0:  33%|███▎      | 170/508 [00:04<00:07, 47.19it/s]
Loading 0:  35%|███▍      | 176/508 [00:04<00:11, 29.88it/s]
Loading 0:  36%|███▌      | 181/508 [00:04<00:10, 30.86it/s]
Loading 0:  37%|███▋      | 190/508 [00:04<00:08, 37.71it/s]
Loading 0:  38%|███▊      | 195/508 [00:18<03:28,  1.50it/s]
Loading 0:  39%|███▉      | 199/508 [00:18<02:43,  1.88it/s]
Loading 0:  40%|████      | 204/508 [00:19<02:03,  2.47it/s]
Loading 0:  42%|████▏     | 211/508 [00:19<01:19,  3.72it/s]
Loading 0:  43%|████▎     | 216/508 [00:19<01:01,  4.77it/s]
Loading 0:  43%|████▎     | 220/508 [00:19<00:48,  5.99it/s]
Loading 0:  44%|████▍     | 225/508 [00:19<00:35,  7.92it/s]
Loading 0:  46%|████▌     | 234/508 [00:19<00:21, 12.62it/s]
Loading 0:  47%|████▋     | 241/508 [00:19<00:15, 17.14it/s]
Loading 0:  48%|████▊     | 246/508 [00:20<00:13, 18.98it/s]
Loading 0:  50%|█████     | 254/508 [00:20<00:09, 25.75it/s]
Loading 0:  51%|█████     | 260/508 [00:20<00:09, 27.11it/s]
Loading 0:  52%|█████▏    | 265/508 [00:20<00:09, 24.53it/s]
Loading 0:  53%|█████▎    | 269/508 [00:20<00:09, 25.07it/s]
Loading 0:  55%|█████▍    | 278/508 [00:20<00:06, 33.43it/s]
Loading 0:  56%|█████▌    | 285/508 [00:21<00:05, 39.84it/s]
Loading 0:  57%|█████▋    | 291/508 [00:21<00:06, 33.92it/s]
Loading 0:  59%|█████▉    | 300/508 [00:21<00:05, 40.06it/s]
Loading 0:  60%|██████    | 305/508 [00:21<00:04, 41.72it/s]
Loading 0:  61%|██████    | 311/508 [00:21<00:04, 44.97it/s]
Loading 0:  62%|██████▏   | 317/508 [00:22<00:06, 27.80it/s]
Loading 0:  64%|██████▍   | 324/508 [00:22<00:05, 32.53it/s]
Loading 0:  66%|██████▌   | 333/508 [00:22<00:04, 38.30it/s]
Loading 0:  67%|██████▋   | 340/508 [00:22<00:03, 43.92it/s]
Loading 0:  68%|██████▊   | 346/508 [00:22<00:04, 36.52it/s]
Loading 0:  70%|██████▉   | 354/508 [00:22<00:03, 40.83it/s]
Loading 0:  71%|███████   | 359/508 [00:23<00:04, 31.70it/s]
Loading 0:  71%|███████▏  | 363/508 [00:23<00:04, 32.54it/s]
Loading 0:  72%|███████▏  | 368/508 [00:23<00:04, 33.21it/s]
Loading 0:  74%|███████▍  | 377/508 [00:23<00:03, 39.42it/s]
Loading 0:  76%|███████▌  | 384/508 [00:23<00:02, 45.33it/s]
Loading 0:  77%|███████▋  | 389/508 [00:23<00:03, 38.52it/s]
Loading 0:  78%|███████▊  | 397/508 [00:24<00:02, 44.78it/s]
Loading 0:  79%|███████▉  | 402/508 [00:24<00:02, 41.77it/s]
Loading 0:  80%|████████  | 407/508 [00:24<00:03, 29.33it/s]
Loading 0:  81%|████████  | 411/508 [00:24<00:03, 31.21it/s]
Loading 0:  82%|████████▏ | 419/508 [00:24<00:02, 38.65it/s]
Loading 0:  83%|████████▎ | 424/508 [00:24<00:02, 35.36it/s]
Loading 0:  85%|████████▌ | 432/508 [00:25<00:01, 40.91it/s]
Loading 0:  86%|████████▌ | 437/508 [00:25<00:01, 42.64it/s]
Loading 0:  87%|████████▋ | 443/508 [00:25<00:01, 42.37it/s]
Loading 0:  88%|████████▊ | 448/508 [00:25<00:01, 43.78it/s]
Loading 0:  89%|████████▉ | 453/508 [00:38<00:41,  1.32it/s]
Loading 0:  90%|████████▉ | 457/508 [00:39<00:30,  1.69it/s]
Loading 0:  91%|█████████ | 461/508 [00:39<00:21,  2.21it/s]
Loading 0:  92%|█████████▏| 466/508 [00:39<00:13,  3.15it/s]
Loading 0:  93%|█████████▎| 474/508 [00:39<00:06,  5.20it/s]
Loading 0:  94%|█████████▍| 479/508 [00:39<00:04,  6.70it/s]
Loading 0:  96%|█████████▌| 487/508 [00:39<00:02, 10.08it/s]
Loading 0:  97%|█████████▋| 492/508 [00:40<00:01, 12.60it/s]
Loading 0:  98%|█████████▊| 497/508 [00:40<00:00, 15.17it/s]
Loading 0:  99%|█████████▉| 502/508 [00:40<00:00, 16.03it/s]
Loading 0: 100%|█████████▉| 506/508 [00:40<00:00, 18.59it/s]
                                                            

Job nbeerbower-gemma2-guten-20103-v1-mkmlizer completed after 186.1s with status: succeeded
Stopping job with name nbeerbower-gemma2-guten-20103-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.62s
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 nbeerbower-gemma2-guten-20103-v1
Waiting for inference service nbeerbower-gemma2-guten-20103-v1 to be ready
Inference service nbeerbower-gemma2-guten-20103-v1 ready after 160.58986806869507s
Pipeline stage MKMLDeployer completed in 161.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.137282133102417s
Received healthy response to inference request in 3.34060001373291s
Received healthy response to inference request in 3.542830467224121s
Received healthy response to inference request in 3.333256244659424s
Received healthy response to inference request in 3.4108614921569824s
5 requests
0 failed requests
5th percentile: 3.334724998474121
10th percentile: 3.3361937522888185
20th percentile: 3.339131259918213
30th percentile: 3.3546523094177245
40th percentile: 3.3827569007873537
50th percentile: 3.4108614921569824
60th percentile: 3.4636490821838377
70th percentile: 3.5164366722106934
80th percentile: 3.6617208003997805
90th percentile: 3.8995014667510985
95th percentile: 4.018391799926758
99th percentile: 4.113504066467285
mean time: 3.552966070175171
Pipeline stage StressChecker completed in 19.03s
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 0.72s
Shutdown handler de-registered
nbeerbower-gemma2-guten_20103_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nbeerbower-gemma2-guten-20103-v1-profiler
Waiting for inference service nbeerbower-gemma2-guten-20103-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4634.42s
Shutdown handler de-registered
nbeerbower-gemma2-guten_20103_v1 status is now inactive due to auto deactivation removed underperforming models
nbeerbower-gemma2-guten_20103_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1