submission_id: locutusque-apollo-2-0-ll_3599_v6
developer_uid: Locutusque
best_of: 6
celo_rating: 1224.71
display_name: locutusque-apollo-2-0-ll_3599_v6
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.2, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.05, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 6, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Locutusque/Apollo-2.0-Llama-3.1-8B
latencies: [{'batch_size': 1, 'throughput': 0.88107257563792, 'latency_mean': 1.1349208056926727, 'latency_p50': 1.142648696899414, 'latency_p90': 1.2553473949432372}, {'batch_size': 4, 'throughput': 1.9487932085288193, 'latency_mean': 2.0437524831295013, 'latency_p50': 2.0607783794403076, 'latency_p90': 2.302227282524109}, {'batch_size': 5, 'throughput': 2.136229789857718, 'latency_mean': 2.3287510442733765, 'latency_p50': 2.335047483444214, 'latency_p90': 2.587317419052124}, {'batch_size': 8, 'throughput': 2.395361027972405, 'latency_mean': 3.307644000053406, 'latency_p50': 3.3298054933547974, 'latency_p90': 3.7095855951309202}, {'batch_size': 10, 'throughput': 2.4739535286236323, 'latency_mean': 4.013040326833725, 'latency_p50': 4.052019119262695, 'latency_p90': 4.562651753425598}, {'batch_size': 12, 'throughput': 2.4903990097480446, 'latency_mean': 4.7632996165752415, 'latency_p50': 4.805569410324097, 'latency_p90': 5.3300707817077635}, {'batch_size': 15, 'throughput': 2.5220805785365794, 'latency_mean': 5.881174513101578, 'latency_p50': 5.908824801445007, 'latency_p90': 6.578080487251282}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Locutusque/Apollo-2.0-Ll
model_name: locutusque-apollo-2-0-ll_3599_v6
model_num_parameters: 8030261248.0
model_repo: Locutusque/Apollo-2.0-Llama-3.1-8B
model_size: 8B
num_battles: 10303
num_wins: 4864
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.46
timestamp: 2024-09-12T02:49:07+00:00
us_pacific_date: 2024-09-11
win_ratio: 0.4720955061632534
Download Preference Data
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 locutusque-apollo-2-0-ll-3599-v6-mkmlizer
Waiting for job on locutusque-apollo-2-0-ll-3599-v6-mkmlizer to finish
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ _____ __ __ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ /___/ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ Version: 0.10.1 ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ https://mk1.ai ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ The license key for the current software has been verified as ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ belonging to: ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ Chai Research Corp. ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ║ ║
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: Downloaded to shared memory in 59.722s
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn3erkrmn, device:0
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: quantized model in 26.511s
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: Processed model Locutusque/Apollo-2.0-Llama-3.1-8B in 86.234s
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6/special_tokens_map.json
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6/config.json
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6/tokenizer_config.json
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6/tokenizer.json
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/locutusque-apollo-2-0-ll-3599-v6/flywheel_model.0.safetensors
locutusque-apollo-2-0-ll-3599-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 31.99it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:05, 46.58it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 44.89it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 44.69it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:06, 43.11it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:05, 43.09it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 48.23it/s] Loading 0: 16%|█▌ | 47/291 [00:01<00:07, 34.73it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 40.26it/s] Loading 0: 21%|██ | 61/291 [00:01<00:05, 43.23it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:05, 43.96it/s] Loading 0: 24%|██▍ | 71/291 [00:01<00:05, 43.27it/s] Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 40.53it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:05, 41.41it/s] Loading 0: 30%|███ | 88/291 [00:02<00:04, 45.40it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:04, 44.80it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:04, 45.36it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 45.62it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:05, 30.55it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:05, 32.50it/s] Loading 0: 41%|████ | 120/291 [00:02<00:04, 39.53it/s] Loading 0: 43%|████▎ | 125/291 [00:03<00:04, 41.41it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 42.59it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 40.61it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 41.24it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 48.34it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:03, 43.30it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 43.53it/s] Loading 0: 56%|█████▋ | 164/291 [00:03<00:03, 37.82it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 38.35it/s] Loading 0: 60%|██████ | 175/291 [00:04<00:02, 42.46it/s] Loading 0: 62%|██████▏ | 180/291 [00:04<00:02, 43.44it/s] Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 36.23it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:02, 45.14it/s] Loading 0: 68%|██████▊ | 199/291 [00:04<00:02, 44.12it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:01, 43.85it/s] Loading 0: 72%|███████▏ | 210/291 [00:05<00:01, 46.28it/s] Loading 0: 74%|███████▍ | 215/291 [00:05<00:01, 45.62it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 41.56it/s] Loading 0: 77%|███████▋ | 225/291 [00:05<00:01, 34.19it/s] Loading 0: 79%|███████▉ | 230/291 [00:05<00:01, 36.32it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 45.45it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 41.91it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:01, 41.57it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 47.05it/s] Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 45.98it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 45.53it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 50.93it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 45.06it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 45.94it/s] Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 3.30it/s]
Job locutusque-apollo-2-0-ll-3599-v6-mkmlizer completed after 105.35s with status: succeeded
Stopping job with name locutusque-apollo-2-0-ll-3599-v6-mkmlizer
Pipeline stage MKMLizer completed in 107.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service locutusque-apollo-2-0-ll-3599-v6
Waiting for inference service locutusque-apollo-2-0-ll-3599-v6 to be ready
Inference service locutusque-apollo-2-0-ll-3599-v6 ready after 150.7997829914093s
Pipeline stage MKMLDeployer completed in 151.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9064486026763916s
Received healthy response to inference request in 7.66996431350708s
Received healthy response to inference request in 1.2877678871154785s
Received healthy response to inference request in 1.3934848308563232s
Received healthy response to inference request in 8.054815769195557s
5 requests
0 failed requests
5th percentile: 1.3089112758636474
10th percentile: 1.3300546646118163
20th percentile: 1.3723414421081543
30th percentile: 1.496077585220337
40th percentile: 1.7012630939483644
50th percentile: 1.9064486026763916
60th percentile: 4.211854887008666
70th percentile: 6.517261171340941
80th percentile: 7.746934604644776
90th percentile: 7.900875186920166
95th percentile: 7.977845478057861
99th percentile: 8.039421710968018
mean time: 4.062496280670166
%s, retrying in %s seconds...
Received healthy response to inference request in 6.1523237228393555s
Received healthy response to inference request in 1.649895429611206s
Received healthy response to inference request in 1.3210034370422363s
Received healthy response to inference request in 4.720201730728149s
Received healthy response to inference request in 1.517533302307129s
5 requests
0 failed requests
5th percentile: 1.3603094100952149
10th percentile: 1.3996153831481934
20th percentile: 1.4782273292541503
30th percentile: 1.5440057277679444
40th percentile: 1.5969505786895752
50th percentile: 1.649895429611206
60th percentile: 2.878017950057983
70th percentile: 4.10614047050476
80th percentile: 5.006626129150391
90th percentile: 5.579474925994873
95th percentile: 5.865899324417114
99th percentile: 6.095038843154907
mean time: 3.072191524505615
Pipeline stage StressChecker completed in 37.54s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.91s
Shutdown handler de-registered
locutusque-apollo-2-0-ll_3599_v6 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service locutusque-apollo-2-0-ll-3599-v6-profiler
Waiting for inference service locutusque-apollo-2-0-ll-3599-v6-profiler to be ready
Inference service locutusque-apollo-2-0-ll-3599-v6-profiler ready after 170.53359985351562s
Pipeline stage MKMLProfilerDeployer completed in 170.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/locutusque-apollo-2-044ea2eabfdff1ea9b4957c4d0079fe1-deplo6sk2h:/code/chaiverse_profiler_1726109870 --namespace tenant-chaiml-guanaco
kubectl exec -it locutusque-apollo-2-044ea2eabfdff1ea9b4957c4d0079fe1-deplo6sk2h --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726109870 && python profiles.py profile --best_of_n 6 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726109870/summary.json'
kubectl exec -it locutusque-apollo-2-044ea2eabfdff1ea9b4957c4d0079fe1-deplo6sk2h --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726109870/summary.json'
Pipeline stage MKMLProfilerRunner completed in 752.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service locutusque-apollo-2-0-ll-3599-v6-profiler is running
Tearing down inference service locutusque-apollo-2-0-ll-3599-v6-profiler
Service locutusque-apollo-2-0-ll-3599-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.07s
Shutdown handler de-registered
locutusque-apollo-2-0-ll_3599_v6 status is now inactive due to auto deactivation removed underperforming models
locutusque-apollo-2-0-ll_3599_v6 status is now torndown due to DeploymentManager action