developer_uid: NischayDnk
submission_id: google-gemma-2-27b-it_v14
model_name: google-gemma-2-27b-it_v14
model_group: google/gemma-2-27b-it
status: torndown
timestamp: 2025-03-30T02:07:10+00:00
num_battles: 8931
num_wins: 4092
celo_rating: 1253.17
family_friendly_score: 0.6762
family_friendly_standard_error: 0.006617455099961011
submission_type: basic
model_repo: google/gemma-2-27b-it
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.27829149758530536, 'latency_mean': 3.593267312049866, 'latency_p50': 3.5696576833724976, 'latency_p90': 3.998752570152283}, {'batch_size': 2, 'throughput': 0.4226914035219555, 'latency_mean': 4.712723867893219, 'latency_p50': 4.7018009424209595, 'latency_p90': 5.214720463752746}, {'batch_size': 3, 'throughput': 0.5288424960221356, 'latency_mean': 5.643985108137131, 'latency_p50': 5.6601362228393555, 'latency_p90': 6.159605503082275}, {'batch_size': 5, 'throughput': 0.6745893957650901, 'latency_mean': 7.351925208568573, 'latency_p50': 7.334542632102966, 'latency_p90': 8.18201789855957}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: google-gemma-2-27b-it_v14
is_internal_developer: False
language_model: google/gemma-2-27b-it
model_size: 29B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-03-29
win_ratio: 0.4581793752099429
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': '<bos><start_of_turn>system\n{memory}<end_of_turn>\n', 'prompt_template': '', 'bot_template': '<start_of_turn>{bot_name}\n{message}<end_of_turn>\n', 'user_template': '<start_of_turn>{user_name}\n{message}<end_of_turn>\n', 'response_template': '<start_of_turn>{bot_name}\n', '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 google-gemma-2-27b-it-v14-mkmlizer
Waiting for job on google-gemma-2-27b-it-v14-mkmlizer to finish
google-gemma-2-27b-it-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
google-gemma-2-27b-it-v14-mkmlizer: ║ _____ __ __ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
google-gemma-2-27b-it-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
google-gemma-2-27b-it-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ /___/ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ Version: 0.12.8 ║
google-gemma-2-27b-it-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
google-gemma-2-27b-it-v14-mkmlizer: ║ https://mk1.ai ║
google-gemma-2-27b-it-v14-mkmlizer: ║ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ The license key for the current software has been verified as ║
google-gemma-2-27b-it-v14-mkmlizer: ║ belonging to: ║
google-gemma-2-27b-it-v14-mkmlizer: ║ ║
google-gemma-2-27b-it-v14-mkmlizer: ║ Chai Research Corp. ║
google-gemma-2-27b-it-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
google-gemma-2-27b-it-v14-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
google-gemma-2-27b-it-v14-mkmlizer: ║ ║
google-gemma-2-27b-it-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
google-gemma-2-27b-it-v14-mkmlizer: Downloaded to shared memory in 59.467s
google-gemma-2-27b-it-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4br0lfgn, device:0
google-gemma-2-27b-it-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
google-gemma-2-27b-it-v14-mkmlizer: quantized model in 69.270s
google-gemma-2-27b-it-v14-mkmlizer: Processed model google/gemma-2-27b-it in 128.738s
google-gemma-2-27b-it-v14-mkmlizer: creating bucket guanaco-mkml-models
google-gemma-2-27b-it-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
google-gemma-2-27b-it-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/google-gemma-2-27b-it-v14
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/config.json
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/special_tokens_map.json
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/tokenizer_config.json
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/tokenizer.model
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/tokenizer.json
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/flywheel_model.0.safetensors
google-gemma-2-27b-it-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/google-gemma-2-27b-it-v14/flywheel_model.1.safetensors
google-gemma-2-27b-it-v14-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 37.24it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 44.74it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 33.44it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 45.97it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 29.68it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:14, 33.31it/s] Loading 0: 9%|▉ | 45/508 [00:01<00:11, 39.19it/s] Loading 0: 10%|▉ | 50/508 [00:01<00:12, 36.02it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:10, 42.10it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 43.09it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 39.19it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 28.97it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:13, 30.75it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 30.40it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 34.18it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:10, 40.01it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:11, 35.98it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 40.27it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 41.98it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:11, 32.78it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 37.72it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 39.72it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 38.99it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:08, 40.90it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 41.21it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 42.60it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 42.51it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:07, 43.65it/s] Loading 0: 33%|███▎ | 167/508 [00:04<00:07, 45.18it/s] Loading 0: 34%|███▍ | 172/508 [00:04<00:11, 29.37it/s] Loading 0: 35%|███▍ | 176/508 [00:04<00:10, 31.13it/s] Loading 0: 35%|███▌ | 180/508 [00:04<00:09, 32.82it/s] Loading 0: 37%|███▋ | 188/508 [00:05<00:07, 40.30it/s] Loading 0: 38%|███▊ | 193/508 [00:19<04:20, 1.21it/s] Loading 0: 39%|███▉ | 199/508 [00:19<02:55, 1.76it/s] Loading 0: 40%|████ | 204/508 [00:20<02:11, 2.32it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:24, 3.50it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:04, 4.50it/s] Loading 0: 43%|████▎ | 220/508 [00:20<00:50, 5.65it/s] Loading 0: 44%|████▍ | 224/508 [00:20<00:39, 7.19it/s] Loading 0: 46%|████▌ | 232/508 [00:20<00:24, 11.25it/s] Loading 0: 47%|████▋ | 237/508 [00:21<00:20, 13.37it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 18.51it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 21.89it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.71it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.86it/s] Loading 0: 52%|█████▏ | 264/508 [00:21<00:10, 23.94it/s] Loading 0: 53%|█████▎ | 268/508 [00:21<00:09, 26.49it/s] Loading 0: 54%|█████▍ | 276/508 [00:22<00:06, 34.44it/s] Loading 0: 55%|█████▌ | 281/508 [00:22<00:06, 32.52it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 38.07it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 39.46it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 38.79it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:04, 40.72it/s] Loading 0: 61%|██████▏ | 312/508 [00:22<00:04, 47.19it/s] Loading 0: 63%|██████▎ | 318/508 [00:23<00:06, 29.29it/s] Loading 0: 64%|██████▎ | 323/508 [00:23<00:05, 32.67it/s] Loading 0: 65%|██████▌ | 331/508 [00:23<00:04, 38.25it/s] Loading 0: 66%|██████▌ | 336/508 [00:23<00:04, 35.13it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:04, 40.20it/s] Loading 0: 69%|██████▊ | 349/508 [00:24<00:03, 41.66it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:03, 39.31it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 31.81it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 33.03it/s] Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 34.36it/s] Loading 0: 74%|███████▍ | 375/508 [00:24<00:03, 41.45it/s] Loading 0: 75%|███████▍ | 380/508 [00:24<00:03, 36.19it/s] Loading 0: 76%|███████▋ | 388/508 [00:25<00:02, 40.26it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 41.80it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 39.42it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 38.56it/s] Loading 0: 80%|████████ | 407/508 [00:25<00:03, 30.50it/s] Loading 0: 81%|████████ | 411/508 [00:25<00:03, 32.24it/s] Loading 0: 82%|████████▏ | 419/508 [00:25<00:02, 39.13it/s] Loading 0: 83%|████████▎ | 424/508 [00:26<00:02, 35.08it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 40.11it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 41.59it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 40.78it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 42.02it/s] Loading 0: 89%|████████▉ | 451/508 [00:41<00:01, 42.02it/s] Loading 0: 89%|████████▉ | 452/508 [00:41<00:49, 1.14it/s] Loading 0: 90%|████████▉ | 456/508 [00:41<00:34, 1.50it/s] Loading 0: 91%|█████████ | 460/508 [00:41<00:24, 1.95it/s] Loading 0: 92%|█████████▏| 466/508 [00:41<00:14, 2.99it/s] Loading 0: 93%|█████████▎| 474/508 [00:42<00:06, 4.86it/s] Loading 0: 94%|█████████▍| 479/508 [00:42<00:04, 6.21it/s] Loading 0: 96%|█████████▌| 487/508 [00:42<00:02, 9.36it/s] Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.73it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 13.99it/s] Loading 0: 99%|█████████▉| 502/508 [00:43<00:00, 14.75it/s] Loading 0: 100%|█████████▉| 506/508 [00:43<00:00, 17.20it/s]
Job google-gemma-2-27b-it-v14-mkmlizer completed after 165.97s with status: succeeded
Stopping job with name google-gemma-2-27b-it-v14-mkmlizer
Pipeline stage MKMLizer completed in 166.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service google-gemma-2-27b-it-v14
Waiting for inference service google-gemma-2-27b-it-v14 to be ready
Inference service google-gemma-2-27b-it-v14 ready after 110.57119297981262s
Pipeline stage MKMLDeployer completed in 111.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.715073585510254s
Received healthy response to inference request in 3.1202216148376465s
Received healthy response to inference request in 2.994913101196289s
Received healthy response to inference request in 3.1228983402252197s
Received healthy response to inference request in 3.128767251968384s
5 requests
0 failed requests
5th percentile: 3.0199748039245606
10th percentile: 3.045036506652832
20th percentile: 3.095159912109375
30th percentile: 3.120756959915161
40th percentile: 3.1218276500701903
50th percentile: 3.1228983402252197
60th percentile: 3.1252459049224854
70th percentile: 3.127593469619751
80th percentile: 3.246028518676758
90th percentile: 3.4805510520935057
95th percentile: 3.59781231880188
99th percentile: 3.691621332168579
mean time: 3.2163747787475585
Pipeline stage StressChecker completed in 17.30s
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 0.68s
Shutdown handler de-registered
google-gemma-2-27b-it_v14 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 5933.88s
Shutdown handler de-registered
google-gemma-2-27b-it_v14 status is now inactive due to auto deactivation removed underperforming models
google-gemma-2-27b-it_v14 status is now torndown due to DeploymentManager action