submission_id: flammenai-mahou-1-5-mist_3961_v1
developer_uid: cloudyu
best_of: 8
celo_rating: 1235.51
display_name: flammenai-mahou-1-5-mist_3961_v1
family_friendly_score: 0.5836
family_friendly_standard_error: 0.0069715283833604235
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: flammenai/Mahou-1.5-mistral-nemo-12B
latencies: [{'batch_size': 1, 'throughput': 0.623994900239433, 'latency_mean': 1.6025107645988463, 'latency_p50': 1.5923594236373901, 'latency_p90': 1.7770482063293456}, {'batch_size': 3, 'throughput': 1.1569918377176653, 'latency_mean': 2.5826380431652067, 'latency_p50': 2.5761804580688477, 'latency_p90': 2.8602519989013673}, {'batch_size': 5, 'throughput': 1.4036834173263517, 'latency_mean': 3.5483146393299103, 'latency_p50': 3.5465667247772217, 'latency_p90': 4.009358906745911}, {'batch_size': 6, 'throughput': 1.4741583854144815, 'latency_mean': 4.039160680770874, 'latency_p50': 4.042127370834351, 'latency_p90': 4.575933456420898}, {'batch_size': 8, 'throughput': 1.5541771029345302, 'latency_mean': 5.118795312643051, 'latency_p50': 5.09264063835144, 'latency_p90': 5.813714241981506}, {'batch_size': 10, 'throughput': 1.593658795032706, 'latency_mean': 6.218390600681305, 'latency_p50': 6.274651765823364, 'latency_p90': 6.997619009017944}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: flammenai/Mahou-1.5-mist
model_name: flammenai-mahou-1-5-mist_3961_v1
model_num_parameters: 12772070400.0
model_repo: flammenai/Mahou-1.5-mistral-nemo-12B
model_size: 13B
num_battles: 22642
num_wins: 10575
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.43
timestamp: 2024-11-23T23:07:18+00:00
us_pacific_date: 2024-11-23
win_ratio: 0.46705238053175513
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 flammenai-mahou-1-5-mist-3961-v1-mkmlizer
Waiting for job on flammenai-mahou-1-5-mist-3961-v1-mkmlizer to finish
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ _____ __ __ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ /___/ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ Version: 0.11.12 ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ https://mk1.ai ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ The license key for the current software has been verified as ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ belonging to: ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ Chai Research Corp. ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ║ ║
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: Downloaded to shared memory in 53.314s
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnmmdagy8, device:0
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: quantized model in 36.610s
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: Processed model flammenai/Mahou-1.5-mistral-nemo-12B in 89.925s
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: creating bucket guanaco-mkml-models
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1/config.json
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1/special_tokens_map.json
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1/tokenizer_config.json
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1/tokenizer.json
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/flammenai-mahou-1-5-mist-3961-v1/flywheel_model.0.safetensors
flammenai-mahou-1-5-mist-3961-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 29.85it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.52it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.70it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.65it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.59it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.00it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.60it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 47.97it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 48.24it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 46.81it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:10, 29.37it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:08, 35.87it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 37.80it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 38.85it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.45it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.02it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.41it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 51.65it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 46.49it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 44.79it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.04it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 44.83it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 43.81it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.94it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.89it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.64it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.79it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 41.57it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 43.25it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 42.21it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 41.85it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:03, 46.31it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:03, 45.62it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.07it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 43.66it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 35.32it/s] Loading 0: 58%|█████▊ | 210/363 [00:04<00:03, 42.68it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 42.83it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 44.09it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:05, 26.35it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 29.44it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.36it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 36.85it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 37.75it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 40.54it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 35.23it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.68it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.63it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 43.06it/s] Loading 0: 77%|███████▋ | 279/363 [00:06<00:01, 42.93it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 35.73it/s] Loading 0: 80%|███████▉ | 289/363 [00:07<00:01, 38.71it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 36.93it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 38.10it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:25, 2.33it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:19, 2.85it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:12, 4.10it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.87it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.30it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.80it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 16.56it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.34it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 22.97it/s] Loading 0: 98%|█████████▊| 355/363 [00:15<00:00, 28.21it/s] Loading 0: 99%|█████████▉| 360/363 [00:15<00:00, 30.53it/s]
Job flammenai-mahou-1-5-mist-3961-v1-mkmlizer completed after 114.15s with status: succeeded
Stopping job with name flammenai-mahou-1-5-mist-3961-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.47s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service flammenai-mahou-1-5-mist-3961-v1
Waiting for inference service flammenai-mahou-1-5-mist-3961-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service flammenai-mahou-1-5-mist-3961-v1 ready after 120.51038646697998s
Pipeline stage MKMLDeployer completed in 121.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4714114665985107s
Received healthy response to inference request in 2.0230414867401123s
Received healthy response to inference request in 1.3532817363739014s
Received healthy response to inference request in 1.6552743911743164s
Received healthy response to inference request in 1.7622792720794678s
5 requests
0 failed requests
5th percentile: 1.4136802673339843
10th percentile: 1.4740787982940673
20th percentile: 1.5948758602142334
30th percentile: 1.6766753673553467
40th percentile: 1.7194773197174071
50th percentile: 1.7622792720794678
60th percentile: 1.8665841579437257
70th percentile: 1.9708890438079834
80th percentile: 2.112715482711792
90th percentile: 2.2920634746551514
95th percentile: 2.381737470626831
99th percentile: 2.453476667404175
mean time: 1.8530576705932618
Pipeline stage StressChecker completed in 10.54s
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 2.10s
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 2.03s
Shutdown handler de-registered
flammenai-mahou-1-5-mist_3961_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service flammenai-mahou-1-5-mist-3961-v1-profiler
Waiting for inference service flammenai-mahou-1-5-mist-3961-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 2629.79s
Shutdown handler de-registered
flammenai-mahou-1-5-mist_3961_v1 status is now inactive due to auto deactivation removed underperforming models